Stable diffusion download windows — Ваш верный помощник с OS Windows

Windows

- StableDiffusionGUI-0.2.7-win64.exe
- Size: 76.93
  MB
- SHA256:
  00d3a8129f3d92f1788747f167d343f6eaaca235a466eba0adb082de5ef37fa9

Ubuntu 24.04

- stablediffusiongui_0.2.7-Ubuntu24.04_amd64.deb
- Size: 7.27
  MB
- SHA256:
  f15dedfa3268b5b46f3b8e30d0588197bc4cba932faad74a83d460663177e1a7
- stablediffusiongui-server-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 2.47
  MB
- SHA256:
  c6341f139994ff40200a47aef05eb329a4088ee522bc7f044071424fd047e0e1
- libstablediffusion-vulkan-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 2.69
  MB
- SHA256:
  556e5ea4def714c04b018a737b15ea3a8e2f75c6980066a4b61afc1c2f6ff686
- libstablediffusion-cuda-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 177.85
  MB
- SHA256:
  f213f9fe58240bd51d408f7e9b195afa3da24d7837e16db9fef5c652abc56877
- libstablediffusion-avx512-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 1.93
  MB
- SHA256:
  e31cfa52500fe1c0ec0aa7804a58cffea2d47381b7f727d67f92828e9b5f3fc4
- libstablediffusion-avx2-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 1.92
  MB
- SHA256:
  ad2e598d6e06e96f30b40a22dba807f74ed6eeeb5cbd46b4ae35bb30e31b6026
- libstablediffusion-avx-fbd42b6_0.2.7-Ubuntu24.04_amd64.deb
- Size: 1.92
  MB
- SHA256:
  412ca3e9f5b9d3d068d01a84afe8003c9fa443ea504126929fdd7102e74cfaee
- StableDiffusionGUI-0.2.7-Ubuntu24.04-libsdcpp_avx.tar.gz
- Size: 1.91
  MB
- SHA256:
  cf127366abc8b49b542430795cc60760c086003c7039d87007b34833e3bc61d1
- StableDiffusionGUI-0.2.7-Ubuntu24.04-libsdcpp_avx2.tar.gz
- Size: 1.92
  MB
- SHA256:
  287ee87da7bc748bd2da971ff91963a722454384fd436cd418d179f8c3d69c00
- StableDiffusionGUI-0.2.7-Ubuntu24.04-libsdcpp_avx512.tar.gz
- Size: 1.93
  MB
- SHA256:
  37eebd1b2cd3a3f7a4193090ab0bfbcec6da27cfdfb751e4c49d1352c3761907
- StableDiffusionGUI-0.2.7-Ubuntu24.04-libsdcpp_cuda.tar.gz
- Size: 177.84
  MB
- SHA256:
  09870d38a424bea6fee064c93d3752ead36388a7eed57bd1a9e1b82b80d560a6
- StableDiffusionGUI-0.2.7-Ubuntu24.04-libsdcpp_vulkan.tar.gz
- Size: 2.69
  MB
- SHA256:
  3849fb27214b8be8370daa79392be86343aa1e86e81870aaa000b530f6557b73
- StableDiffusionGUI-0.2.7-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.27
  MB
- SHA256:
  b1db22bdb467d57b4fd03e747fe962bb470f5c5ead24afdcbed71ab559392583
- StableDiffusionGUI-0.2.7-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.27
  MB
- SHA256:
  b1db22bdb467d57b4fd03e747fe962bb470f5c5ead24afdcbed71ab559392583

Ubuntu 22.04

- stablediffusiongui_0.2.7-Ubuntu22.04_amd64.deb
- Size: 6.93
  MB
- SHA256:
  83b9aebef469a764e5c1a29fcd168e004d9c697efe3113261dbf8882a7f7e6ba
- stablediffusiongui-server-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 2.34
  MB
- SHA256:
  3d47d7e634e01bf8bf3f97350c2d2e6e550354f13ff2db3f12dc4f6c193cbf95
- libstablediffusion-vulkan-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 2.66
  MB
- SHA256:
  3850b7fbafdabf4b1e8dcef25ba7fecdc96c836b06b3fa61141159d81b73ed9a
- libstablediffusion-cuda-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 144.8
  MB
- SHA256:
  258af9f3105ed2b9501167ec57802a48711e22af3fb15251df2bbdd02d2386a7
- libstablediffusion-avx512-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 1.92
  MB
- SHA256:
  4c6574dd1d49c60888dde0fe701415156fce625e818366e32de4d47dbc79b2d0
- libstablediffusion-avx2-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  9d6012da2bb2a49e73c2d4d740421bf3a6f8f6abb43f925333d9799341782190
- libstablediffusion-avx-fbd42b6_0.2.7-Ubuntu22.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  75a7467acfae8d32e721d96131d0c27b0e02ffe130bf999072e3781585410a6e
- StableDiffusionGUI-0.2.7-Ubuntu22.04-libsdcpp_avx.tar.gz
- Size: 1.91
  MB
- SHA256:
  93ce960bfae3c41330d2aea3608fba158e3478f06ae0c039bfa8f4ac02bb9a9d
- StableDiffusionGUI-0.2.7-Ubuntu22.04-libsdcpp_avx2.tar.gz
- Size: 1.91
  MB
- SHA256:
  89a1c6b9aee020634713eafa492a9c2ce068bbe9f64d54968e2b9cdf9fd55b8a
- StableDiffusionGUI-0.2.7-Ubuntu22.04-libsdcpp_avx512.tar.gz
- Size: 1.92
  MB
- SHA256:
  66997bdefc0a3f2f8f6751a8ecf175d148ca477de220b1c07a0a54946fe37b51
- StableDiffusionGUI-0.2.7-Ubuntu22.04-libsdcpp_cuda.tar.gz
- Size: 144.8
  MB
- SHA256:
  85a3f5e3c67b407024ede99429be93fabe335641fd8a770c2017772ab89cd498
- StableDiffusionGUI-0.2.7-Ubuntu22.04-libsdcpp_vulkan.tar.gz
- Size: 2.66
  MB
- SHA256:
  70c91c2806265b94f04d075166bd1ad3362e2237d17144ee20c74d1bcb6e0440
- StableDiffusionGUI-0.2.7-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.93
  MB
- SHA256:
  f0faf153c3f0c6f1f4496838e20a1eea3f24b5bee836fa428e4aaffe85864455
- StableDiffusionGUI-0.2.7-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.93
  MB
- SHA256:
  f0faf153c3f0c6f1f4496838e20a1eea3f24b5bee836fa428e4aaffe85864455

v0.2.7 changelog

This update mainly focuses on bug fixes.

Fixes

fixeds tinyencoder url in the docker initial model download phase
fixes Unable to install Cuda backend on Ubuntu 22.04 #33
fixes Local img2img generation: initial images not visible in the job #36
fixes some settings not saved in the Settings window
fixes docker containers

New Contributors

@schorsch1976 made their first contribution in https://github.com/fszontagh/sd.cpp.gui.wx/pull/35

This pre release is compatible with the v0.2.5 & v0.2.6 versions.

The sd.cpp version changed (master-d9b5942)

The sd.cpp fbd42b6 tag fixes the old LoRA model unload issue #410

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/v0.2.6…v0.2.7

Windows

- StableDiffusionGUI-0.2.5-win64.exe
- Size: 76.91
  MB
- SHA256:
  1d0a2853f8040ab8659ba97389992d9e0af8d46daf196acc9db76dff6857ecf9

Ubuntu 24.04

- stablediffusiongui_0.2.5-Ubuntu24.04_amd64.deb
- Size: 7.25
  MB
- SHA256:
  063bda1f12f053613a60588224ced17cdeb508445847b667eefc8788f300d8aa
- stablediffusiongui-server-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 2.47
  MB
- SHA256:
  32c6f7d15023202842836bc993c53bed7a8d65be31db1b2d9d5b2ee1db3add33
- libstablediffusion-vulkan-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 2.68
  MB
- SHA256:
  0d80e84ad1dfec0451ee993a87bedad59fa9815685b8869f7322803093024deb
- libstablediffusion-cuda-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 177.85
  MB
- SHA256:
  89bfabe0fcca478b556622f23e1a9f6119ed8b0267041c9aea2559838665feb8
- libstablediffusion-avx512-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.93
  MB
- SHA256:
  8b0b275bd3045b30d1ae0004c18f9be9617add720d57e3699cc8efb547477ef4
- libstablediffusion-avx2-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  cee7456303d1b422d9bdb92a08b9511f55a0ab222c002648a8bf1d52fc7694f8
- libstablediffusion-avx-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  6d960aa0acf52da28f7a6f4639aabd7037f4e2e1c7a122d3407d173df21303b4
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx.tar.gz
- Size: 1.91
  MB
- SHA256:
  8e4f5bc9f4cfe99c310d69c804df39f539232a75f3f705c9c425f7a6b7fe7c84
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx2.tar.gz
- Size: 1.91
  MB
- SHA256:
  8bd52767624e28e96f0ea10fc197af7a1f384d5816b4a88d14e3b3c64c2dc69f
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx512.tar.gz
- Size: 1.93
  MB
- SHA256:
  18b30f4a844992fb3335be920b36e9869177d1bde070ea4855bff160a03aa2a3
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_cuda.tar.gz
- Size: 177.84
  MB
- SHA256:
  fb702172aba3ce23d650141e38b3118499b244d2397b133fcfec4cd0704af28f
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_vulkan.tar.gz
- Size: 2.67
  MB
- SHA256:
  d7bdc5354cab49887b0fb8d83f15f7eede2b295c556c262bc5327db051391fed
- StableDiffusionGUI-0.2.5-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.25
  MB
- SHA256:
  b41050e0d5b4320e5b28edbedfc3ed05ec0f7bfd8e2a59e8ef94a676159966c1
- StableDiffusionGUI-0.2.5-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.25
  MB
- SHA256:
  b41050e0d5b4320e5b28edbedfc3ed05ec0f7bfd8e2a59e8ef94a676159966c1

Ubuntu 22.04

- stablediffusiongui_0.2.5-Ubuntu22.04_amd64.deb
- Size: 6.92
  MB
- SHA256:
  9a2f74a2a78bea3b4e65418c7419ae5baf81c57d97e9c052477ae8e4d1237da4
- stablediffusiongui-server-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 2.34
  MB
- SHA256:
  9fee85ef32aa63f79669c3157e0967e5e08ee170936445e07a5d085289cde547
- libstablediffusion-vulkan-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 2.67
  MB
- SHA256:
  b7573c6a371c242b0c82f5e6eac649e8c957ad5e7b24dd85cb8d1d8f11655c5b
- libstablediffusion-cuda-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 144.81
  MB
- SHA256:
  4c1427c3176b81a5eb7eb7c79d8eba23ea86d962ee0271fdf8e5c199ef04c8ce
- libstablediffusion-avx512-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.92
  MB
- SHA256:
  b9a9026db9494451e41d63343b848cc1d71e53f5c196013e5fd9020bc83093dc
- libstablediffusion-avx2-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  c237923d902c774368d5a171388b77d98114a12530c33bd7695bd9c264d5228b
- libstablediffusion-avx-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  30786398028dad04d0bd207d102de3868bf7a9db68f951910a1fbc3ad83ccc9b
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx.tar.gz
- Size: 1.9
  MB
- SHA256:
  116f0158d303a638dbd4dc335d4cacbc11d9d6c308a4439490c811751d5149d8
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx2.tar.gz
- Size: 1.9
  MB
- SHA256:
  81a12695f12b93595a067e09a1256033f24cedb94a8d0130586cbec787c7a8ff
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx512.tar.gz
- Size: 1.92
  MB
- SHA256:
  f14dbe4bcf243947014e100abb88ede44fc9b1470882c1f6470975dae5c02417
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_cuda.tar.gz
- Size: 144.81
  MB
- SHA256:
  e3b729dc05e549f0d6b02efa201fbdfeefbe6ae04b546b81335f97bc79b2be50
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_vulkan.tar.gz
- Size: 2.67
  MB
- SHA256:
  2c2866ff36f7baa5a79d2a06cd3e4cb32adad36fa61f6c97417052aa035e295c
- StableDiffusionGUI-0.2.5-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.92
  MB
- SHA256:
  cc9376915d87aad0966acb98bd7c71a5f608d2bdf09f8f5d474fd7c4392292f4
- StableDiffusionGUI-0.2.5-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.92
  MB
- SHA256:
  cc9376915d87aad0966acb98bd7c71a5f608d2bdf09f8f5d474fd7c4392292f4

v0.2.6 changelog

Release Notes for v0.2.5 Hotfix

This hotfix addresses a critical issue in v0.2.5.

Fixes

Prebuilt binaries were compiled with incorrect CPU feature flags, causing SIGILL (Illegal Instruction) errors on unsupported processors

Original change log:

This update primarily focuses on the new server component of the GUI.
For more details, please see the related wiki page.

Fixes

Fixed an issue where the inpainting brush extended beyond the edges.
Simplified some CMake configurations for build and configuration time.
Added compiler optimizations for Windows.
Fixed a bug where the settings window occasionally closed incorrectly.
Corrected the format of some image metadata.

What’s Changed

Closing the settings window no longer causes the main window to restart automatically. (Changing the language still requires a full application restart.)
Added a server selector under the «Generate» button. This is only visible if one or more servers are added in the settings.
The GUI layout has been redesigned.
Added a queue item version check. If a stored queue item’s version differs from the current GUI version, it will be ignored.
Renamed the .deb packages, removing the «~» character from the names.
The .deb package dependencies have been relaxed for better compatibility.

Prompts

Added LoRA and embedding highlighting. If a LoRA tag is present in the prompt but unavailable on the selected server or locally, it will be marked in red.
Added autocomplete for LoRAs and embeddings. (Embeddings are not checked for availability on the selected server or locally.)
Implemented a shortcut to adjust word weight like in Stable Diffusion WebUI:
- Use Ctrl + Up / Ctrl + Down to increase or decrease the weight of the selected text or the word under the cursor.
Added a «Restore Last Prompt» button.
Added a «Clear Prompt» button to empty the input fields.
Added a «Normalize Prompt» button to remove duplicates and trim the string.

Model Manager

Local models are now separated from the server model list into a new parent category.
When selecting a remote model, the server list will automatically select the corresponding model’s server.

New Features

Introduced the TCP server component, which functions as a standalone part of the project.
Added a TCP client to the GUI to connect to the TCP server.

This version is incompatible with old queue job files, but outdated queue items will be automatically hidden due to the version check.

If you encounter errors on startup, please delete all configurations for a clean start.

The sd.cpp version changed (master-d9b5942)

Full Changelog: Compare v0.2.4…v0.2.6

Windows

- StableDiffusionGUI-0.2.5-win64.exe
- Size: 76.91
  MB
- SHA256:
  569b4e135ad452d3cc867c870f7fe41b3fede38c2394122190825852f64303b5

Ubuntu 24.04

- stablediffusiongui_0.2.5-Ubuntu24.04_amd64.deb
- Size: 7.25
  MB
- SHA256:
  aa707e2d2a9626cc817c475c4a080487bd89c30f651aa63f374b159883aa4798
- stablediffusiongui-server-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 2.47
  MB
- SHA256:
  c4417d89538970e8d9893ad93cce934a4c5caa52d479b4deb5aaec25df8dc418
- libstablediffusion-vulkan-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 2.68
  MB
- SHA256:
  de3a427840c31b269264dd2fb37bb9811cb98fb2928570d83aa0c4d2e456bdd6
- libstablediffusion-cuda-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 177.85
  MB
- SHA256:
  c885447a2a74a85a9bb9af78c69b660dc49e458e7d80824d824d20dc0524bbae
- libstablediffusion-avx512-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.93
  MB
- SHA256:
  9b5dcdc05e3a14e5efcbd7a819447bd9cc76beea5f8d7bfec81f05d4fc148004
- libstablediffusion-avx2-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  5c7eb22175ec66c39d5764d6846c3c9a9bc8dc44e1a8b01db7e2747c344beb25
- libstablediffusion-avx-d9b5942_0.2.5-Ubuntu24.04_amd64.deb
- Size: 1.91
  MB
- SHA256:
  2fe453a8ec50470c30a76827d9d3771c55cd9bac4950e261e352dc56885109d2
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx.tar.gz
- Size: 1.91
  MB
- SHA256:
  860265c701cf880d8106c169fcc1dbffa44fc7163d06d056c42bac3b918072c6
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx2.tar.gz
- Size: 1.91
  MB
- SHA256:
  3463e2c7bd898d9db8cffe2fa7f7ee967034bb4cb353838b9129a79e9b7449a8
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_avx512.tar.gz
- Size: 1.93
  MB
- SHA256:
  d0f45ef912749cb070b295f56421861aab0a3f37fabe54b613440db283d1151c
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_cuda.tar.gz
- Size: 177.85
  MB
- SHA256:
  50e057ac4087970944aa271873a3c5ef53644478be86f4827a3c276af086a44b
- StableDiffusionGUI-0.2.5-Ubuntu24.04-libsdcpp_vulkan.tar.gz
- Size: 2.67
  MB
- SHA256:
  b462141523dc85843b2c815b80085cf9b5544a560da658c04138940f643fdba9
- StableDiffusionGUI-0.2.5-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.25
  MB
- SHA256:
  670eb2747c108718b101a094137f19dc2e5df4b164d996ea4a3770d927b34fcb
- StableDiffusionGUI-0.2.5-Ubuntu24.04-StableDiffusionGUI.tar.gz
- Size: 7.25
  MB
- SHA256:
  670eb2747c108718b101a094137f19dc2e5df4b164d996ea4a3770d927b34fcb

Ubuntu 22.04

- stablediffusiongui_0.2.5-Ubuntu22.04_amd64.deb
- Size: 6.92
  MB
- SHA256:
  6b9677a63ef6c26fbde9f3d591ef9254eddebebd50912a2e54082dee3f7b1dd8
- stablediffusiongui-server-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 2.34
  MB
- SHA256:
  0b4d58a2760c961b4b5da69648deb4eb54b3935fb9e75a98f6d40ceccd9b1a41
- libstablediffusion-vulkan-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 2.67
  MB
- SHA256:
  b18f41dfe90c0219aedb1bdeadda7a29099a93c9938a083ba90b5faa85d7495f
- libstablediffusion-cuda-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 144.8
  MB
- SHA256:
  d17e7208828829a654588d7587ff0ec468ecb839144a1e641362dbf436a49e98
- libstablediffusion-avx512-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.92
  MB
- SHA256:
  b45b1f25c0e6095f334f15d572668ce85f1c33b4ae63452be5872a3bf68b790b
- libstablediffusion-avx2-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  b502dce5e67e8491acaecc92a02bada2a5f2960c8b20f1500d59b8b199cabafe
- libstablediffusion-avx-d9b5942_0.2.5-Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  290f6428f538609956d8b76b09e7707ad6eea1d1233db03adbebf3510b029fae
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx.tar.gz
- Size: 1.9
  MB
- SHA256:
  36415cd2a68b65811defbd0c5907a39ed433235f286606ed6ebc96ffc48a7850
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx2.tar.gz
- Size: 1.9
  MB
- SHA256:
  72cce0aa1f694334d0ac106479f5e72f1324e8766b308b1078eb2fa01486aa3e
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_avx512.tar.gz
- Size: 1.92
  MB
- SHA256:
  8dda1368fec29ceb3845329e14fa12520730e71cc66414205d2d17c2e0b40600
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_cuda.tar.gz
- Size: 144.8
  MB
- SHA256:
  b1f650b8de1b33ce48ae0cd73829e611c4f8ca2b6b0caf7642c0d854150d17db
- StableDiffusionGUI-0.2.5-Ubuntu22.04-libsdcpp_vulkan.tar.gz
- Size: 2.67
  MB
- SHA256:
  228314450a87022287d43c0396baf32c777d7fa8a7c3b548c8e2be19bd66c085
- StableDiffusionGUI-0.2.5-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.92
  MB
- SHA256:
  31921b0d5c6fbce3e2213160f1b9b39fafa91573cf05f05d3bcdb4b32e90b055
- StableDiffusionGUI-0.2.5-Ubuntu22.04-StableDiffusionGUI.tar.gz
- Size: 6.92
  MB
- SHA256:
  31921b0d5c6fbce3e2213160f1b9b39fafa91573cf05f05d3bcdb4b32e90b055

v0.2.5 changelog

This update primarily focuses on the new server component of the GUI.
For more details, please see the related wiki page.

Fixes

Fixed an issue where the inpainting brush extended beyond the edges.
Simplified some CMake configurations for build and configuration time.
Added compiler optimizations for Windows.
Fixed a bug where the settings window occasionally closed incorrectly.
Corrected the format of some image metadata.

What’s Changed

Closing the settings window no longer causes the main window to restart automatically. (Changing the language still requires a full application restart.)
Added a server selector under the «Generate» button. This is only visible if one or more servers are added in the settings.
The GUI layout has been redesigned.
Added a queue item version check. If a stored queue item’s version differs from the current GUI version, it will be ignored.
Renamed the .deb packages, removing the «~» character from the names.
The .deb package dependencies have been relaxed for better compatibility.

Prompts

Added LoRA and embedding highlighting. If a LoRA tag is present in the prompt but unavailable on the selected server or locally, it will be marked in red.
Added autocomplete for LoRAs and embeddings. (Embeddings are not checked for availability on the selected server or locally.)
Implemented a shortcut to adjust word weight like in Stable Diffusion WebUI:
- Use Ctrl + Up / Ctrl + Down to increase or decrease the weight of the selected text or the word under the cursor.
Added a «Restore Last Prompt» button.
Added a «Clear Prompt» button to empty the input fields.
Added a «Normalize Prompt» button to remove duplicates and trim the string.

Model Manager

Local models are now separated from the server model list into a new parent category.
When selecting a remote model, the server list will automatically select the corresponding model’s server.

New Features

Introduced the TCP server component, which functions as a standalone part of the project.
Added a TCP client to the GUI to connect to the TCP server.

This version is incompatible with old queue job files, but outdated queue items will be automatically hidden due to the version check.

If you encounter errors on startup, please delete all configurations for a clean start.

The sd.cpp version changed (master-d9b5942)

Full Changelog: Compare v0.2.4…v0.2.5

Windows

- StableDiffusionGUI-0.2.4-win64.exe
- Size: 83.78
  MB
- SHA256:
  e25ece6a11417cb6b1eff88cd81f2d221e84bf19759f2402d6c05193595a4d81

Ubuntu 24.04

- stablediffusiongui_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 5.36
  MB
- SHA256:
  67b8e3a0ca4ee41b8fa18d39dfb4bf72ddc5bb8412399a8d49578f43ca3eb199
- libstablediffusion-vulkan-dcf91f9_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 2.67
  MB
- SHA256:
  55536ce307c6de6a174a94caad3e9b47c3b2802f6324b4ecad3ce1f23861fb4d
- libstablediffusion-cuda-dcf91f9_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 146.8
  MB
- SHA256:
  d1801e909096f97bf6761a3e0b6a8e722ce930000ff8df9dc006afefc4875ec6
- libstablediffusion-avx512-dcf91f9_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  c7b8a24144d19af5b584bd0d07a9bf4dd8ee9c69d16d6e36db7223d2099fc2a6
- libstablediffusion-avx2-dcf91f9_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  2d24fe81ae696f6059d0edd1902cbe8f20dde42894386b4551faa42f3ddfca4a
- libstablediffusion-avx2-dcf91f9_0.2.4-20250108.Ubuntu24.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  2d24fe81ae696f6059d0edd1902cbe8f20dde42894386b4551faa42f3ddfca4a

Ubuntu 22.04

- stablediffusiongui_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 5.08
  MB
- SHA256:
  6360cfed5e919e33197fe6f56a1f148931a789d5b258a18fc311902ae69efc9e
- libstablediffusion-vulkan-dcf91f9_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 2.65
  MB
- SHA256:
  6d49fedbda44a7973673f72d159f2386e8e0799bf3750d152e9196c4644f16b5
- libstablediffusion-cuda-dcf91f9_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 144.81
  MB
- SHA256:
  00be579ed0d6b275392e56850e98c1566cd4832bea647f04adbf4eec0dfd463d
- libstablediffusion-avx512-dcf91f9_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  d088bc573509533edca063e0ae6dec63bfb523a97367e1e216e390716f9c59e4
- libstablediffusion-avx2-dcf91f9_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  2ebd101b3d09e3b9a338969c86f84e84752c4bd597f9415e62aa180a92f204b5
- libstablediffusion-avx2-dcf91f9_0.2.4-20250108.Ubuntu22.04_amd64.deb
- Size: 1.9
  MB
- SHA256:
  2ebd101b3d09e3b9a338969c86f84e84752c4bd597f9415e62aa180a92f204b5

v0.2.4 changelog

Fixes

In model manager, when a model set/removed as [F]avorite, the selection jumped to a wrong model
Improved the image management on queue-d jobs, now images separated by types to better identification
When an image selected eg. a txt2img to send into img2img, after the job start the original image deleted
fixed some GUI lagging too
cpu_features component now can be used from the installed system packages if exists
fixed the job status text on the widget
fixed exif / png metadata reading, now works on all supported platforms
output image metadatas (from any supported OS) now compatible with CivitAi
in the output filename format the month was one character, now this is padded with 0

Changes

the GUI layout is changed, trying to fix it on smaller desktop resolutions or higher / lower DPI
in the queue job list, now possible to select multiple item and delete them
in the queue job list, if you select one or more item you can delete this items with the «delete» key
removed ROCM build, added VULKAN. On systems with AMD GPU, the GUI use the VULKAN backend
Added some metadata to the binaries on Windows for better security
Updated localization files.

New Features

inpaint / outpaint and built-in mask editor (see wiki page)

The sd.cpp version changed (master-dcf91f9)

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/v0.2.3…v0.2.4

Windows

- StableDiffusionGUI-0.2.3-win64.exe
- Size: 94.17
  MB
- SHA256:
  023620324e82433c48e38df4afb727153bb8eae85f0aea78ca1880d845492aa4

Ubuntu 24.04

- stablediffusiongui_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 5.3
  MB
- SHA256:
  afe8f46169350ce55697c02eb463abb440d2e21b91c187c24cd5d0fce4ff1bee
- libstablediffusion-hipblas-b5f4932_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 27.63
  MB
- SHA256:
  b81addfd4996007351c868b2203027971e03f20804f5421105cfb207bfed60bd
- libstablediffusion-cuda-b5f4932_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 145.97
  MB
- SHA256:
  798a4b1f53d9a5b98f53341f2e3c489f0b413fcb94c8b165f3dd38b84f89fade
- libstablediffusion-avx512-b5f4932_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  bbb939ebbf0958f62f465c15aa5b32c772b564a37d4cb04abf7e6a16223076f1
- libstablediffusion-avx2-b5f4932_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  dcced2be820bcbfdbb72d33fdd9016853882980af6bc1c87442da9a184e74784
- libstablediffusion-avx2-b5f4932_0.2.3-20241215.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  dcced2be820bcbfdbb72d33fdd9016853882980af6bc1c87442da9a184e74784

Ubuntu 22.04

- stablediffusiongui_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 5.03
  MB
- SHA256:
  5084fcf8bd38b99aaed300f5459471af6ba1e367124f060dab7e399fa76df3f6
- libstablediffusion-hipblas-b5f4932_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 27.64
  MB
- SHA256:
  8ea0e944b93ac1983afeeed687efbf653db034866e16b12422e2f0d00d32c721
- libstablediffusion-cuda-b5f4932_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  080a7964b159b461250bd2c36ab24cd4f59666a2562a828af2676c9c9906a88d
- libstablediffusion-avx512-b5f4932_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  612076862f24ae8b8fd298756479b54604febf5b2c26b55cf69e1d74184fa0a4
- libstablediffusion-avx2-b5f4932_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  8058998ea851e1677661ba8f7ca06c8c10ae13c999f2fb81e747255dccadffea
- libstablediffusion-avx2-b5f4932_0.2.3-20241215.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  8058998ea851e1677661ba8f7ca06c8c10ae13c999f2fb81e747255dccadffea

v0.2.3 changelog

Fixes

Resolved an issue in the new config system where certain parameters were not reloaded into the settings window.
Fixed an issue where the application’s temporary folder was not created on the first launch.
Included missing shared libraries in the AppImage.
Addressed graphical lags in scrolled panels when using the GTK backend.
Fixed certain context menus for images.
Resolved an issue where model metadata was lost after changing a model’s path. (If a model is moved to a new path, it must be reloaded in the GUI.)

Changes

Replaced the old model manager’s list view with wxTreeListCtrl.
Redesigned the main GUI layout.
Simplified validation by introducing a single «Job Start» button.
Non-checkpoint models are now treated as checkpoint models, enabling hashing and CivitaI metadata checks for these models.
Removed model search and filter features.
Updated localization files.

New Features

Model Manager

Introduced the «Model Favorite» feature:
- Allows users to mark models as favorites. You can configure the main GUI to display only favorite models—useful for managing a large number of models.
Models are now categorized by type (e.g., Checkpoint, LoRA, ControlNet, etc.).
Subfolders in the model manager now act as categories. For example, creating a folder named SD1x and moving models into it will separate those models (e.g., CHECKPOINTS/SD1x).
Added the ability to delete model files directly from the GUI, which also removes their metadata.

Generation Settings

Added prompt presets (styles/templates). See the GitHub Wiki for more details.

Build system

New cmake parameters:
- WXWIDGETS_EXTRA_PATH: additional path, where wxWidgets installation will be searched #24
- WXWIDGETS_VERSION: this forces cmake to search for the specified version of the wxWidgets. Defaults: 3.2.6. #24

The sd.cpp version not changed (master-b5f4932)

Full Changelog: v0.2.2…v0.2.3

Windows

- StableDiffusionGUI-0.2.2-win64.exe
- Size: 94.14
  MB
- SHA256:
  8b9b3055d02b3c178890f2ce9fd99531a7790caae995b1fa4ce2aa860d68a3a7

Ubuntu 24.04

- stablediffusiongui_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 5.24
  MB
- SHA256:
  17755dd61c136d1be88a3d2da278e7b90aee71a3927abdf12b29da9e92e98c9f
- libstablediffusion-hipblas-b5f4932_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 27.63
  MB
- SHA256:
  f26f8f7499eb261df941d5584285691ee0f5960ae10a53046ac5b0bb64ac3143
- libstablediffusion-cuda-b5f4932_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 145.97
  MB
- SHA256:
  0b3e129db4c5a1db41e6ddd8f51e8d1be7ec32f5963185b7292afdb5d76fce05
- libstablediffusion-avx512-b5f4932_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  9a7d700b57172a2fadcf038ccc92279ffd32134b0fc7df503fa31490b4054d58
- libstablediffusion-avx2-b5f4932_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  b4fd7fdf74442b19576488ffc0757268a5e0ed04bed3a2e01d1371690c0b4cac
- libstablediffusion-avx2-b5f4932_0.2.2-20241205.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  b4fd7fdf74442b19576488ffc0757268a5e0ed04bed3a2e01d1371690c0b4cac

Ubuntu 22.04

- stablediffusiongui_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 4.97
  MB
- SHA256:
  f26c191be0b2446ab0f7569c2cfbc442663dfd3cc153d373fddc4babcb4f59c9
- libstablediffusion-hipblas-b5f4932_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 27.64
  MB
- SHA256:
  19537924265d0229d91bda25b22cd1afd879729f555370979bf090610295c89d
- libstablediffusion-cuda-b5f4932_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  671c8bf8e004c49af24e9cbacb8a254cf2cfee242098f2f8021481f41fb35562
- libstablediffusion-avx512-b5f4932_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  875bfa8eee64f65736150bc30089e66f5bbb0a082f6a9dae00d50aece85b559b
- libstablediffusion-avx2-b5f4932_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  8e14ce9d42718ae5156403fe91124323117f5cb6c12a98de241f575d94144f4a
- libstablediffusion-avx2-b5f4932_0.2.2-20241205.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  8e14ce9d42718ae5156403fe91124323117f5cb6c12a98de241f575d94144f4a

v0.2.2 changelog

This update addresses issues present in version 0.2.1:

Fixed a deadlock issue that caused the GUI to freeze, preventing queue jobs from completing once started.
Resolved the missing model hash information in the metadata of output images.
Corrected some metadata reading issues for images in the Image Info tab

UPDATE:

Added a desktop widget, now available for both Windows and Linux.

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/v0.2.1…v0.2.2

Windows

- StableDiffusionGUI-0.2.1-win64.exe
- Size: 94.14
  MB
- SHA256:
  fcd63468836aac9cb3e36273aef5e499518b636bbddc7fc6d1858bc760c6b13e

Ubuntu 24.04

- stablediffusiongui_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 5.22
  MB
- SHA256:
  5337a9c00fe81947b8a218da368852a3a2c22c39b980fa14c0bcf3c2ac6e0302
- libstablediffusion-hipblas-b5f4932_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 27.63
  MB
- SHA256:
  ca84b180a90cc15828862bc99b99d51dbec6dbb901663ccb079a4b3ddecef848
- libstablediffusion-cuda-b5f4932_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 145.97
  MB
- SHA256:
  2733754d5d661046582dc4850b709e9648b839b821fb50047b8e70ba666788b6
- libstablediffusion-avx512-b5f4932_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  2b5efa1524c57c14d7bdf552c9a412d93f517bac7e663c834b30617a01a38610
- libstablediffusion-avx2-b5f4932_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  b296f73717b8e340b4ee4bade6bac71121f586933afaa3e4e3ac75097ee0e733
- libstablediffusion-avx2-b5f4932_0.2.1-20241204.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  b296f73717b8e340b4ee4bade6bac71121f586933afaa3e4e3ac75097ee0e733

Ubuntu 22.04

- stablediffusiongui_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 4.97
  MB
- SHA256:
  bf1a550902a65a1805b16a1861bb324b2edec2b201b4a17ac2c366119201fb9e
- libstablediffusion-hipblas-b5f4932_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 27.64
  MB
- SHA256:
  e6f0260d91fdb10597a4caefc8e4a7126868a3523370be4cae7fb3f815ba5e99
- libstablediffusion-cuda-b5f4932_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  34389d77c9cd37173b9e731d224d7034a2e0f244d28fcad9417ac77061459c97
- libstablediffusion-avx512-b5f4932_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  a843896150babb96bbc0376a267ca258c06f6d609d9c5cf17ff6762baccc22bd
- libstablediffusion-avx2-b5f4932_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  5bf9b137101ce148cf6b6d259d2b8f26050d2cd39e0aa35a0e7ba63f9d68821a
- libstablediffusion-avx2-b5f4932_0.2.1-20241204.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  5bf9b137101ce148cf6b6d259d2b8f26050d2cd39e0aa35a0e7ba63f9d68821a

v0.2.1 changelog

This update primarily includes minor, less visible fixes and some new GUI features.

Changes

The secret store name has changed, requiring you to re-enter your CivitAi API key.
Fixed CMake dependency checks to make it easier to build from source on a wider variety of Linux distributions (see: #22 ).
Several small improvements were made to the CivitAi downloader, including more robust handling of HTTP errors.
Resolved an issue where the model name used in img2img did not appear in the queue list.
Queue jobs are now sorted by default so that the newest jobs appear at the top.
Image-related processes have been optimized.
The language selector in settings has been fixed to ensure each language appears only once.
The language detector on first startup is fixed (again)
Added the -vulkan parameter to the GUI (vulkan is coming)
Minor logging issues have been fixed.
Improved external process detection on both Windows and Linux.
Language files have been updated again.
Refactored config handler
Fixed some bug on the selectors handling (sample method, scheduler, wtype…)

New Features

PNG compression level can now be configured (this does not affect image quality).
The existing quality setting for JPG images remains the same.
Output image filename formatting is now customizable (e.g.: [mode]/[year]-[month]-[day]/[jobid][seed][width]x[height]). Please see the new wiki page for details.
Image metadata handling has been improved:
- Generated PNG images now embed PNG metadata compatible with Stable Diffusion WebUI (PNG info).
- EXIF data is now embedded into JPEG formats
Added an Image Info Tab into the GUI, where images can be checked for generation data (similar to Stable Diffusion Webui PNG Info tab). Compatible with the most image generators.
Added an progressbar and a status label to the main gui
Added an experimental floating Widget which is shows the current running job’s details. This curretly only available on GTK and in non Release builds.

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/v0.2.0…v0.2.1

Windows

- StableDiffusionGUI-0.2.0-win64.exe
- Size: 93.02
  MB
- SHA256:
  46ec10e9a0c09a10dc7141ce2e0b6cfdd38cfde8fed6f1117ac7d879d693693f

Ubuntu 24.04

- stablediffusiongui_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 6.76
  MB
- SHA256:
  b6766ad63699dfa6017e8213fa4955dd1c8cc5ab9b3809b8f953c131047830b8
- libstablediffusion-hipblas-b5f4932_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 27.63
  MB
- SHA256:
  8a0e5f345a9d5e1c8543e73b4b7c69ae7865d688c66ee3fc313d023c171882a9
- libstablediffusion-cuda-b5f4932_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 145.97
  MB
- SHA256:
  3b90c3227c49e7250e2883236125c11502de7afc5ec09ae3b3d56262fcca4f6d
- libstablediffusion-avx512-b5f4932_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  c258ceb9ca9b18e2942acbeb089dd6b9f233ea61310f99f895b4ac997bb49f77
- libstablediffusion-avx2-b5f4932_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  8ab08e769a12123c28c9f0ccde2befef6dcc79b746ab93c13ac7a80382bee54f
- libstablediffusion-avx2-b5f4932_0.2.0-20241124.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  8ab08e769a12123c28c9f0ccde2befef6dcc79b746ab93c13ac7a80382bee54f

Ubuntu 22.04

- stablediffusiongui_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 6.43
  MB
- SHA256:
  9bd34252b0c2aa79f1bad2659664696a8bea4fa67948917dfbf162d9990a24a6
- libstablediffusion-hipblas-b5f4932_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 27.64
  MB
- SHA256:
  fd778c4c0ae8d49eb9c15bc38d215a083827f7a5ae11bdfa5f285a2e3e16dc8d
- libstablediffusion-cuda-b5f4932_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  00dcdbf7dbfe6e9ca7da7c5ec9fd89057cf6c8cc923884c126668cec4fcb5794
- libstablediffusion-avx512-b5f4932_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  19f0d6fee9a0be3f748ecdf7515077fba66b4d383e13d041d444d09b4827bddd
- libstablediffusion-avx2-b5f4932_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  9c084f4c4a479ba064f8b08985f8a322be057ef7bbd16b645f364a674f9cfb01
- libstablediffusion-avx2-b5f4932_0.2.0-20241124.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  9c084f4c4a479ba064f8b08985f8a322be057ef7bbd16b645f364a674f9cfb01

v0.2.0 changelog

New Features

New Options on the GUI:
The following options related to keeping components on the CPU have been added to the graphical interface.
Any changes to these options are immediately saved in the configuration file and will persist when restarting the application.
- Keep VAE on CPU
- Keep CLIP on CPU
- Keep ControlNet on CPU
Support for New Models:
Added support for ClipL, ClipG, and T5XXL models (currently available only on the txt2img tab). This also enables compatibility with SD3x and FLUX models. For FLUX models, the file must currently be manually selected on the txt2img interface. However, it is recommended to store these models in the same directory as other models.
More information is available on the wiki page.
- Queue jobs generated using these models can now also be reloaded.
- For Diffusion models, the GUI will attempt to locate any additional required models in the VAE directory.
Skip Layer Guidance for SD3.5 Medium Models:
Added support for the «skip layer guidance» feature.
(See details: GitHub PR #451)
Flash Attention for Diffuser models:
Added the option to use Flash Attention with the diffusion models, which may reduce the memory usage
Updated sd.cpp:
Updated to version master-b5f4932.
FLUX 1 Lite 8B Support:
Added support for the Flux 1 Lite 8B (Freepik) model.
(See details: GitHub PR #474)

Several GUI updates have been made, and the language files have also been updated.
This version nearly covers all the features available in the sd.cpp example program. However, minor and/or major bugs may still be present.

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/preview11…v0.2.0

Windows

- StableDiffusionGUI-0.1.9-win64.exe
- Size: 92.95
  MB
- SHA256:
  48df9021fd8a67d13950397ba260b6c4b29670ecbb64fa79f6590c6b107afc6d

Ubuntu 24.04

- stablediffusiongui_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 6.72
  MB
- SHA256:
  154b9f57b02139cdfbc7d0f5bd66a80bddb01385647e3bc6d675c25717684f3f
- libstablediffusion-hipblas-ac54e00_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 27.6
  MB
- SHA256:
  3267bc70e3ebc84ab00336cf69798769f12fa80f95a66b29070149b1ddb9286f
- libstablediffusion-cuda-ac54e00_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 145.95
  MB
- SHA256:
  b44d8ea1f7a13b719809e7d3247113259fa00c1fc43b7a9a065344fb4f185e36
- libstablediffusion-avx512-ac54e00_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  650a2f827d31302b38c7d8d68b9612095cd685a15c1c6b00f2a5447fa672b642
- libstablediffusion-avx2-ac54e00_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  65f3f0487b729db9c6b7252bd5400432db68b6d7e66b490486e479d4b7b6a55d
- libstablediffusion-avx2-ac54e00_0.1.9-20241114.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  65f3f0487b729db9c6b7252bd5400432db68b6d7e66b490486e479d4b7b6a55d

Ubuntu 22.04

- stablediffusiongui_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 6.39
  MB
- SHA256:
  892663647ad61056ce63ede5877a672b54d307a1d7ddbc31b2484024d10577ab
- libstablediffusion-hipblas-ac54e00_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 27.62
  MB
- SHA256:
  7209809e72e7f7fdad69ceb84d5880113e6c42e7b2966a774f7d039ce744e886
- libstablediffusion-cuda-ac54e00_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  f2fca71d8ff7b8b1b35f285c7b146de458ef988ce8a8c390e889de110543ba46
- libstablediffusion-avx512-ac54e00_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  9c80cbf770d61bcd0f800d9915963f2e8dfab635c750b1b34df2e7e2e7863dc6
- libstablediffusion-avx2-ac54e00_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  2046528f20592b48200ba007bc7bb2a233bdf069231d4836fb94ccaea05c68a9
- libstablediffusion-avx2-ac54e00_0.1.9-20241114.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  2046528f20592b48200ba007bc7bb2a233bdf069231d4836fb94ccaea05c68a9

preview11 changelog

This is the first preview with multi-language support. On the first start, the GUI will detect the OS locale and search for available language files. If no match is found, the fallback language is always English.
To change the GUI language, you can go into the Settings -> GUI
In this version, if you close the settings window, the GUI will fully reload. (All modified generation settings will be lost)

This version includes some refactoring, with a precompiled header added to the main app and a refactored main configuration logic. Due to the refactoring, you may need to delete old configuration files if the app fails to start.

Fixed some bugs:

After model quantization, the model list now reloads correctly
Fixed some GUI spacing issues when non-English words have more characters than English
and other QoL bugs

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/preview10v2…preview11

Windows

- StableDiffusionGUI-0.1.8-win64.exe
- Size: 92.88
  MB
- SHA256:
  e3d0425fac72198b56bd6dccd95088fee4f9ade0267e453ed6a275b749c074d0

Ubuntu 24.04

- stablediffusiongui_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 6.64
  MB
- SHA256:
  bd7d1134e9619a633c070f2da4ed289fbeb230730d777f84a9ff766c05c14f0e
- libstablediffusion-hipblas-ac54e00_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 27.6
  MB
- SHA256:
  b865237ff913ed7280b610a9bf4b20bf136c221024c40ddb473060e89fc03d0a
- libstablediffusion-cuda-ac54e00_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 145.95
  MB
- SHA256:
  8903a7231ec1c6f3b268ff3fdc67253b93a602a293a26071eb37a1a6d4805e44
- libstablediffusion-avx512-ac54e00_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  c2aed7e2b2112d7820607dde328040b9462a32dcfbf51e9202def8095397a7c7
- libstablediffusion-avx2-ac54e00_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  9cb1b434da8e3ee5b66550425ff0a34a5842963db5465454ad9270047a79d5cf
- libstablediffusion-avx2-ac54e00_0.1.8-20241108.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  9cb1b434da8e3ee5b66550425ff0a34a5842963db5465454ad9270047a79d5cf

Ubuntu 22.04

- stablediffusiongui_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 6.33
  MB
- SHA256:
  91fd995377bc744c99167e85b0144e35b0bdb40715f9318bdd4896c71bdc4fb2
- libstablediffusion-hipblas-ac54e00_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 27.62
  MB
- SHA256:
  f153b3498f4486ad763b473ed5a8033e905aafae2671692a2d5653128580096d
- libstablediffusion-cuda-ac54e00_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  4b68236b738e5d90d69be0c27e129e4f2814da898471f69c64b073bd1cf532e8
- libstablediffusion-avx512-ac54e00_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  9ad37e41d16b26793a0185fbc3f01fc517d16c9890627b6c1f0691c95f8e567e
- libstablediffusion-avx2-ac54e00_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  cd729e71c49e7414954e5195e23f1ef452bf1753ffffdff6b2c039294454f98d
- libstablediffusion-avx2-ac54e00_0.1.8-20241108.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  cd729e71c49e7414954e5195e23f1ef452bf1753ffffdff6b2c039294454f98d

preview10v2 changelog

Full Changelog: https://github.com/fszontagh/sd.cpp.gui.wx/compare/preview10…preview10v2

This is a fix for the preview10:

fixed on windows the temp path name in the external process
fixed the shared library naming on windows
fixed the job status reading from the shared memory + changed the maximum size the shared memory to 1MB
fixed when a job started, the selected floating type was ignored

Windows

- StableDiffusionGUI-0.1.8-win64.exe
- Size: 92.87
  MB
- SHA256:
  c89d80ead11b7fc4d51df78eac110e5324830c1e2809387de8a514187d738f39

Ubuntu 24.04

- stablediffusiongui_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 6.64
  MB
- SHA256:
  f0221af8680c748f5cb6635015efba9461f529c77de46f7206e5ee5ed097798e
- libstablediffusion-hipblas-ac54e00_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 27.6
  MB
- SHA256:
  9c1fc08ae1474b1e735faec928f25c948a2129d566f70f2c90042221e84afb87
- libstablediffusion-cuda-ac54e00_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 145.95
  MB
- SHA256:
  8458a06dc296f13a40ef28bb1cc430b872423b4fc18b4272de702a3360f6c109
- libstablediffusion-avx512-ac54e00_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  95651d266579e38c6f54dacdaeab83f43471cccabb0c2c64a68d033d08c73fcd
- libstablediffusion-avx2-ac54e00_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  de17afb76b1c5c6f32837426966de5218ccd46ddf11433f77aaa8b889c955fa2
- libstablediffusion-avx2-ac54e00_0.1.8-20241107.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  de17afb76b1c5c6f32837426966de5218ccd46ddf11433f77aaa8b889c955fa2

Ubuntu 22.04

- stablediffusiongui_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 6.33
  MB
- SHA256:
  4b8384e2dcdd1ceebc5107a5851a3a4fa67540d5126a362e2d102441c25ef945
- libstablediffusion-hipblas-ac54e00_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 27.62
  MB
- SHA256:
  c1a11b29b4b3fcc7d0644f53df47749c8a78418a09d3327688deecbfbb310c8d
- libstablediffusion-cuda-ac54e00_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  d09d7370060d4c49b0c9372361be33edff830f43243a73898159685d4350fe8c
- libstablediffusion-avx512-ac54e00_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  d813788dc6fb4923fabb72bd93ef56b9553e818f88cbe9549198e10b05996f1c
- libstablediffusion-avx2-ac54e00_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  7defbc7407f08f21171466f32aeaf06be0d0efae5aa60cfba9869599dc87e686
- libstablediffusion-avx2-ac54e00_0.1.8-20241107.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  7defbc7407f08f21171466f32aeaf06be0d0efae5aa60cfba9869599dc87e686

preview10 changelog

This release introduces several updates and improvements:

this release uses the latest tag from sd.cpp master-ac54e00
Resolution Presets: Added resolution presets to the GUI. (Note: prompt presets are not yet implemented.)

Model Converter: A model converter/quantization has been added to the Models list. For details, see the Wiki page.
CivitAi Toggle: The settings now include an option to enable or disable CivitAi features (enabled by default).

Disabling CivitAi features will hide related buttons and menu items, and prevent the app from downloading CivitAi information after model hash generation (no online model hash verification).

«Stop and Restart Background Process» Button: Added a new button for stopping and restarting the background process.

This feature is part of a recent refactoring. For more information, refer to the GitHub Wiki.

Major Refactoring: Background Process

The major update in this release is a background process that manages tasks and runs the queue separately from the main app, reducing the risk of segmentation faults (segfaults) in the GUI. If the background process stops unexpectedly, the main GUI will automatically restart it, enhancing overall stability.

Enhanced Job Statistics: Additional statistical information is now included in the job JSON files, which will be useful for future enhancements.
Fixed CivitAi downloader: added some checks into the model downloader. Checking if the model file already exists or the download just failed
Fixed character encoding: on linux and windows, if a path contained a special character (áéíőó), the string returned as empty.

There was more code enhancements in the background, but there is still much to do

Upgrading from the previous prereleases

Please before installing the new version, backup and remove the old job files from the data directory. The old job files format are incompatible with the new.
Please see the wiki for the application paths.

The screenshots are created under Kubuntu 24

Windows

- StableDiffusionGUI-0.1.7-win64.exe
- Size: 92.48
  MB
- SHA256:
  b438a9144e2b52b9731e58d65f68acafbb48795804e577d0add2af18aafb276e

Ubuntu 24.04

- stablediffusiongui_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 5.6
  MB
- SHA256:
  98abe819d4a28e69984c80a237270c16eaa9982ba66bcf8117d1e037749a1353
- libstablediffusion-hipblas-ac54e00_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 27.6
  MB
- SHA256:
  feb3516b2d48f3c82bbc99280a817b5107e15c9e0364af36f4999e0ad217b0fd
- libstablediffusion-cuda-ac54e00_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 145.95
  MB
- SHA256:
  ac70bf712d76d3c625a3856d16add400fb2fc760f93d5bbb9a945cd9b47f5212
- libstablediffusion-avx512-ac54e00_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  80f2a7453080a8c3ec08b1592f811ac2508c7497922f3a3ebd0c599c824e8718
- libstablediffusion-avx2-ac54e00_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  71ef0e986c329c1af9cea9ae0a6d9c0d5f0facce7973f69d39514a6e3ead477d
- libstablediffusion-avx2-ac54e00_0.1.7-20241031.Ubuntu24.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  71ef0e986c329c1af9cea9ae0a6d9c0d5f0facce7973f69d39514a6e3ead477d

Ubuntu 22.04

- stablediffusiongui_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 5.36
  MB
- SHA256:
  77dc61041af5c708d129f875ebfb1e04a80265189f10cf98f7581c9def81bfdb
- libstablediffusion-hipblas-ac54e00_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 27.62
  MB
- SHA256:
  0e870c9d1e7abbb93e0d5b256ddb009354b7fcbb02525b16dae5138bbd65fc36
- libstablediffusion-cuda-ac54e00_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 144.06
  MB
- SHA256:
  59fe179e964ab0f420ae4778097ebbf7968b44f19f3123b23cd7d2984a7bcfac
- libstablediffusion-avx512-ac54e00_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  f8898d89960eda6f095b98be54262adf5e01a4f6f17f240d441761b0c4189441
- libstablediffusion-avx2-ac54e00_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  e80f1bb0302c8c08c17e080a536441efaf893e7b185a04adea1ac1c6b22b6b76
- libstablediffusion-avx2-ac54e00_0.1.7-20241031.Ubuntu22.04_amd64.deb
- Size: 1.84
  MB
- SHA256:
  e80f1bb0302c8c08c17e080a536441efaf893e7b185a04adea1ac1c6b22b6b76

preview9 v2 changelog

This is the same as the preview9, only the packaging changed. Added hibplas and fixed the AppImage naming

Windows

- StableDiffusionGUI-0.1.7-win64.exe
- Size: 80.46
  MB
- SHA256:
  721f2c07a04350422604b2e71ae39a46d4b7db9dd3097e29379d04e6bbe67de7

Ubuntu 24.04

- stablediffusiongui_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 5.59
  MB
- SHA256:
  d18c12ad4c15d64099cc22ffde61e0f63bde7ef24e6f8b592cb195c4bafb6687
- libstablediffusion-cuda-e410aeb_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 145.96
  MB
- SHA256:
  9de76d36aa0d88544353d7bd0ae8485a1016f782932aec3bd76342ebb15ebf53
- libstablediffusion-avx512-e410aeb_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 1.87
  MB
- SHA256:
  5f4e5aa52d9ec0c9dc9f50cefd582a2c135a0cfff205f65b6041d22001337271
- libstablediffusion-avx2-e410aeb_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  dc5af2f1b9b6ea248bd056d0d0d1cce044a37d8ac2dcaa0d5fd65b4c2c8143ae
- libstablediffusion-avx-e410aeb_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  de65fc52c07d6cc530109ea516ef542507927b72446b899ffb72ccc7556b5868
- libstablediffusion-avx-e410aeb_0.1.7-20241027.Ubuntu24.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  de65fc52c07d6cc530109ea516ef542507927b72446b899ffb72ccc7556b5868

Ubuntu 22.04

- stablediffusiongui_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 5.35
  MB
- SHA256:
  cb10a08c35d696abe24adca91e92a938a6fff6d55073688fea722c380e7b5c58
- libstablediffusion-cuda-e410aeb_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 144.05
  MB
- SHA256:
  a8f2445f7ea0cd204454db2a8e15149295ac8bd8177792d16574220978cc80f1
- libstablediffusion-avx512-e410aeb_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 1.86
  MB
- SHA256:
  df926157b3b6167d0b48dbff3afec59c2cb0e4e8fa498c00eae3d5d2ca335eff
- libstablediffusion-avx2-e410aeb_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  b559601a6fb34795002136cced8a1a468f5832a2a13e38f727d11ebd0b8fe41f
- libstablediffusion-avx-e410aeb_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  a2f561c96ca95d99d510aa24669837338e37ece64b228b99672e5c497c414c8b
- libstablediffusion-avx-e410aeb_0.1.7-20241027.Ubuntu22.04_amd64.deb
- Size: 1.85
  MB
- SHA256:
  a2f561c96ca95d99d510aa24669837338e37ece64b228b99672e5c497c414c8b

preview9 changelog

What’s Changed

changed sd.cpp version to newer (master-e410aeb)
replaced fully the build system to cmake
fixed nvidia detection on linux
fixed progressbar on civitai downloder + added check if the downloaded file is too small (eg. no permission to download a model without civitai api key)
added some help text + updated help urls in the ui
replaced installer on windows to NSIS #18
fixed deb dependencies
added AppImage version #16
added .tar.gz version
Ubuntu22, Ubuntu24 and windows support (other linux distributions may work with the AppImage / .tar.gz variations)
added the missing ‘scheduler’ selector into the gui
renamed the default Type from ‘Default’ to ‘Count’. Count means: get the model type from the modelfile
added all available Sampler into the selector
added .pt extension when searching for upscaler models
removed the limitation to set the image target resolution
added more system information into the About window
added a disclaimer into the About window
added translator python script into the po directory, to generate translation with ollama

The build system change give the opporunity to use github workflow for auto builds. Currently it is working as — is.

Known failures, TODO-s:

need more time to improve the CivitaiDownloader part of the app (save download history, more error handling)
handle the assertions what is comming from sd.cpp / ggml.cpp
- currently if not enought cuda memory or the ggml can’t handle a model, the assertion occurs and the app exiting without user notification
currently the multilanguage feature is implemented in-half, po files are ready, but need to implement the language handler into the GUI
delete model files from the disk in the Models tab
add hipblas, vulkan versions

preview7 — 0.1.6 changelog

Added features

CivitAi.com model downloader/browser

Limitations
- download history not saved
- when the window is closed, the download will be aborted without user notification
- aborted downloads part file (modelname.download) will not be deleted, need to be delete manually or it will be overwritten when a new download start with the same model file
- no auto hash calculation after downloads
- only locally hashed models will be marked in the CivitAi downloader as locally available model (if you not hashed a model file, and you will download the same file with same name, the old model file will be overwritten without notification)
CivitAi api key for private model download (CivitAi docs). You can add your key in the Settings -> CivitAi tab

Modifications

limit target image resolutions, only allowed resolutions with dividet by 256 (except for loading settings from old images)
wxWidgets now statically linked into the binary

Some bug fixed in the linux versions. The deb files are created on Ubuntu 22. Now the gnome-secret / ksecretsservice etc.. is required to store the CivitAi api key.
The CPU and VGA versions are now in separated .deb files.

preview7 — 0.1.5 changelog

This preview release have some gui enhancement and inner data handling refactoring. This may cause unexpected behaviours. If you experience it, please report it in a new bug on the github’s issues page.

Added features

On windows and linux, dynamically load the library which is required / best to (currently available rocm, cuda, avx, avx2, avx512) the HW
fully reworked build system, no more cmake just chalet
on linux, the dependencies are depends from the OS, not vcpkg (supported wxwidgets 3.2 on linux)
preview images are now on the bottom of the lists (queue job list & model info llist)
some gui behaviour is just changed. When settings is open, the main ui will freezee and hide to disable unexpected behaviours on settings change
added the following args to override the detected HW configurations:
- «-cuda» to force to load cuda
- «-rocm» to force to load rocm
- «-avx»
- «-avx2»
- «-avx512»
- «-allow-multiple» to allow multiple instances to run. Eg. if you wamt to start a cuda and an avx512 instance too:
  sd.gui.exe -cuda -allow-multiple
  sd.gui.exe -avx512 -allow-multiple
  The first instance no need to start with the «-allow-multiple» parameter to run another new one.
currently the logging is set to debug in the log on the bottom. Are logs are now written in a log file into the appdata directory
New sd.cpp branch appeared, but when i tested i found some bugs which is prevents to upgrade.

preview6 — 0.1.4 changelog

These preview release have some gui enhancements and inner thread signaling / data handling refactoring. This may cause unexpected behaviours. If you experience it, please report it in a new bug on the github’s issues page.

Added features

CivitAi model info and model images previews for embeddings too

Картинка с сайта: stable-diffusion.fsociety.hu
Thumbnails are cached wich downloaded from CivitAi info or generated by diffusion
Queue jobs more details and features per image:

Картинка с сайта: stable-diffusion.fsociety.hu
Queue item right click features:
Incompatible controls are disabled respect to the generation mode, eg. on upscaler tab the CFG is ignored
Added splash screen while application startup and loading
Only one instance allowed to run in one time
Pending queue items now are possible to pause. If you set to paused, then it just ignored from the queue. Running job can not be paused (not implemented in sd.cpp)
Paused queue items now possible to set to pending
On a queue item a Requeue clones the job, but set the Status to paused (so not started automatically)
Added semi-auto versioning (see the cube button next to the Settings and Refresh button)
Added some place holder images to the ui

Bug fixes

after a txt2img job a new img2img job causing segfault
on model tab the model filters are works with text filter too
refresh models now works with the model list (on the Model tab)
some json converter got more validation (as always)
more data check on events (eg. data table index check)

Update from previous preview versions

Just run the attached installer. Stop all instances before running the installer.
Queue job files (.json) partially compatible with the new format. May the old jobs images visible as «deleted».
If the application won’t start after upgrade, please remove all .json files

Current limitations / known bugs

large textual embeddings are causing crash

preview5 — 0.1.2beta changelog

These preview release have some gui design refactoring and inner thread signaling refactoring. This may cause unexpected behaviours. If you experience it, please report in a new bug on the github’s issues page.

Added features

CivitAi model info and model image previews for Lora and Checkpoints in the model list
CivitAi model info and model image previews now will downloading after the model’s hash check finished using own thread, so the window not freezee while it’s downloading
App icon on Windows
UI redesign, resizable window
On job queue list now the generated and input images are visible, with double click it’s opens in the OS default app
10 char length sha256 (Aka Autov2 hash)
updated readme
updated the backend to the latest stabble-diffusion.cpp

Bug fixes

after an upscale job a new job causing segfault
on model tab the search is now faster, but some bug still in at filter
better «Refresh models» button behavior — but in model list it’s make some weird things

Update from previous preview versions

Just run the attached installer. Stop all instances before running the installer. Currently the config only compatible with the preview3 and preview4 versions. Older versions config files are incompatible, need to delete before run the app. If you experience freezee on startup, please delete all .json file witch is generated by the app.

Current limitations / known bugs

large textual embeddings are causing crash

preview4 changelog

Added features

ESRGAN upscaler (more details here)

Upscaler limitations

only 4x upscaling available (sd.cpp limitation), but you can upscale an upscaled image (eg. drag and drop into the «Upscale» tab the already upscaled image )
only tested with RealESRGAN_x4plus_anime_6B.pth. The RealESRGAN_x4plus may work too (with a lot of warning log)
the upscaler working as tiled upscaler, so tile artifacts sometimes visible

Update from previous preview versions

Just run the attached installer. Stop all instances before running the installer. Currently the config only compatible with the preview3 version. Older versions config files are incompatible, need to delete before run the app.

Current limitations / known bugs

with controlnet, the base model have to be reloaded on all new image generation (it’s automatic at least)
max 75 tokens in all prompts, more tokens are just ignored
when lora is specified in the prompt from the previous job, and base model not changed, the old lora keep in context
when textual embedding is specified in the prompt from the previous job, and base model not changed, the previous textual embedding keep in context
CivitAi info only works on checkpoints
CivitAi info downloading is working on the foreground, the window freezee
SD.next using (10char length sha256) — ??

preview3 changelog

Added features

Job management (Jobs and Images tab)

double click will show some details about the job (in an ugly window. You can resize it if you want )
now is possible to delete a job (depends on his status) Only one job at once. Just hit right click on it and select «Delete»
With right click on a queue item you can:
- Requeue: this will make a clone and start the job
- Copy to text2img: copy some parameters from the job into the current settings (no prompts will be copied)
- Copy prompts to … : copy the prompts from the queue job
- Detail…: open up the same ugly window as double click. Here you can find some details about the job (nothing fancy, nothing functionality at)
Job items now sortable by date

GUI enhancements

re-added desktop notifications, configurable from the settings (turn on/off, set timeout)
addedd drag and drop functions:
- text2img accept image drop-in (drag&drop). It can detect meta info from jpeg (which jpeg was generated by this gui or the SD.next)
- img2img accept image drop-in (drag&drop). It can detect meta info from jpeg (which jpeg was generated by this gui or the SD.next)
The new default output image format is now jpeg with quality 95. The output images will now store the meta-info from the parameters of the image generation. This images can be drop-in into eg. img2img. It will autofill the prompts and other settings from the image. Some enhancments requied here too. I didn’t tested, but in theory, this is compatible with SD.next.

Model management (Models tab)

Added two checkbox: Lora & Checkpoints
- This will filter when you use the searchbox
Added searchbox which will filter the list by name (min. 3 char required to work). If the Lora checkbox is checked but Checkpoints not, then only Lora will be filtered. Need more enhancements
You can sort the models by name
Loras now in the model list too
right click:
- Calculate hash: calclute the sha256 hash from the file. The hash is needed to identify the model by CivitAi. (currently the hash is not compatible with Automatic and other webuis)
- Select model … : this will select the model on the top list. When hit the «Queue» button somewhere, then this model will be used
Doubleclick:
- On checkpoint type model, a new window will popup with some model info from CivitAi. This currently only works with Checkpoints. With lora, it wil freezee the gui and drop a segfault.
- Currently the model info is not optimized, so the window will freezee while downloading the infos and the images. Please use with cauction

Current limitations / known bugs

with controlnet, the base model have to be reloaded on all new image generation (it’s automatic at least)
max 75 tokens in all prompts, more tokens are just ignored
when lora is specified in the prompt from the previous job, and base model not changed, the old lora keep in context
when textual embedding is specified in the prompt from the previous job, and base model not changed, the previous textual embedding keep in context
On start, the gui has no default selected quantation (this is not interfere with the normal working)
CivitAi info only works on checkpoints
CivitAi info downloading is working on the foreground, the window freezee
on job start if the selected model need hash, the hashing is starting, but progressbar not upgraded in the Model tab.
SD.next using (10char length sha256) — ??

If you have an earlier preview release and the gui won’t start, please delete all settings / presets / model info files (all is in .json files) and try again.

preview2 changelog

Current features:

text to image
image to image
keep model in the memory between generations (see limitations)
controlnet
optional tiled vae
optional TAESD encoder
optional VAE model
custom quantation, model converting on the fly
save / load / delete presets
job queue
progressbar
desktop notifications
lora support in the prompts (see limitations) lora:lora_filename_without_extension:weight
textual embedding support in prompt (see limitations)
auto generate sha256 from model files
manual sha256 generation from model files and lora files in model tab
clone a job
copy prompt from a job
copy settings from a job

Current limitations / known bugs

with controlnet, the base model have to be reloaded on all new image generation (it’s automatic at least)
max 75 tokens in all prompts, more tokens are just ignored
when lora is specified in the prompt from the previous job, and base model not changed, the old lora keep in context
when textual embedding is specified in the prompt from the previous job, and base model not changed, the previous textual embedding keep in context
On start, the gui has no default selected quantation (this is not interfere with the normal working)

preview1 changelog

Current features:

text to image
image to image
keep model in the memory between generations (see limitations)
controlnet
optional tiled vae
optional TAESD encoder
optional VAE model
custom quantation, model converting on the fly
save / load / delete presets
job queue
progressbar
desktop notifications
lora support in the prompts (see limitations) lora:lora_filename_without_extension:weight
textual embedding support in prompt (see limitations)

Current limitations / known bugs

with controlnet, the base model have to be reloaded on all new image generation (it’s automatic at least)
max 75 tokens in all prompts, more tokens are just ignored
when lora is specified in the prompt from the previous job, and base model not changed, the old lora keep in context
when textual embedding is specified in the prompt from the previous job, and base model not changed, the previous textual embedding keep in context
if base model changed and lora used in previous job’s prompt, the gui is just crashing

Источник

- GitHub Copilot
  
  Write better code with AI
- GitHub Advanced Security
  
  Find and fix vulnerabilities
- Actions
  
  Automate any workflow
- Codespaces
  
  Instant dev environments
- Issues
  
  Plan and track work
- Code Review
  
  Manage code changes
- Discussions
  
  Collaborate outside of code
- Code Search
  
  Find more, search less
Explore
- Learning Pathways
- Events & Webinars
- Ebooks & Whitepapers
- Customer Stories
- Partners
- Executive Insights
- GitHub Sponsors
  
  Fund open source developers
- The ReadME Project
  
  GitHub community articles
- Enterprise platform
  
  AI-powered developer platform
Pricing

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Repository files navigation

Portable Stable Diffusion

This is a portable version based on the Stable Diffusion by AUTOMATIC1111 version

Running on Windows

Download Stable Diffusion Portable
Unzip the stable-diffusion-portable-main folder anywhere you want
Root directory preferred, and path shouldn’t have spaces and Cyrillic
Example: D:\stable-diffusion-portable-main
Run webui-user-first-run.cmd and wait for a couple seconds
When you see the models folder appeared (while cmd working),
place any model (for example Deliberate) in the ...\models\Stable-diffusion directory
Example of a full path:
D:\stable-diffusion-portable-main\models\Stable-diffusion\Deliberate_v5.safetensors
After complete download your browser will run Stable Diffusion
The main launcher for the future will be the webui-user.bat file

P.S. Due to Windows specifics, any attempt to block network access may crash the install/update processes, so you will have to rerun .bat again.

Our community

Tutorial and Settings

Источник

We will go through how to download and install the popular Stable Diffusion software AUTOMATIC1111 on Windows step-by-step.

Stable Diffusion is a text-to-image AI that can be run on a consumer-grade PC with a GPU. After this tutorial, you can generate AI images on your own PC.

Table of Contents

Systems requirements
- Installing on AMD GPU
Installation steps
- Step 1: Install python
- Step 2: Install git
- Step 3: Clone web-ui
- Step 4: Download a model file
- Step 5: Run webui
Options
- Additional arguments
Next Step
RTX 4000 series graphic cards
Update Stable Diffusion Webui AUTOMATIC1111
- Option 1: Automatic update
- Option 2: Update with a command
Resetting Stable Diffusion Webui
- Reverting to a previous version
Frequently Asked Questions
- AUTOMATIC1111 does not start after updating.
- Does it work on AMD GPU?
- What Python version should I use?
- How to resolve NaN errors when generating images?
- How to resolve out-of-memory errors?
- Python doesn’t work correctly.
- Is there an easier way to install AUTOMATIC1111?
- I tried everything, but it still does not work.

Systems requirements

Your PC should run Windows 10 or higher with a discrete Nvidia video card (GPU) with 4 GB VRAM or more. An integrated GPU will not work.

If your PC does not meet these requirements, alternatives are

Fully managed A1111 service – Think Diffusion. (Affiliate link, you get 20% extra credits.)
Cloud service – Google Colab.
Mac Apple Silicon M1/M2.

Installing on AMD GPU

AUTOMATIC1111 does not officially support AMD GPUs, but it is possible to make it work if you are tech-savvy or willing to try. See the unofficial installation guide on the official GitHub page.

Installation steps

Step 1: Install python

You will need Python 3.10.6. (DON’T use Python 3.11 or newer) There are two ways to install Python on Windows

Option 1: Install from the Microsoft store.

Option 2: Use the 64-bit Windows installer provided by the Python website. (If you use this option, make sure to select “Add Python to 3.10 to PATH“)

I recommend installing it from the Microsoft store.

First, remove all Python versions you have previously installed. You can do that in Control Panel → Add or remove programs.

Visit Python 3.10 on Microsoft Store and install the Python software.

This step is most likely to go wrong. Let’s do a check.

Press the Windows key on your keyboard and type “cmd” to find a program called “Command Prompt”.

Open the Command Prompt App. You should see a black terminal like you are a hacker…

Type “python” and press Enter. You should see you see it prints out Python 3.10. This tells you your Python is installed correctly.

Now you can close the Command Prompt App.

Don’t proceed to the next step until you get Python 3.10 installed correctly.

If you don’t see Python 3.10 running, try

Restarting the PC
Removing all the previous versions of Python and reinstalling from the Microsoft Store
If the one from Microsoft Store doesn’t work for you, remove it and try the one on the Python website.

Step 2: Install git

Git is a code repository management system. You will need it to install and update AUTOMATIC1111.

Go to this page to download the windows version.

Open the installer. Click Install to accept the license and install the software.

Follow the instruction to complete the installation.

Step 3: Clone web-ui

This step downloads the Stable Diffusion software (AUTOMATIC1111).

Press the Window key (It should be on the left of the space bar on your keyboard), and a search window should appear. Type cmd.

Click on Command Prompt. The command prompt window would show up.

First, make sure you are in your home folder by typing the following command and then pressing Enter. (Tip: You should be able to use right-click to paste in Command Prompt.)

cd %userprofile%

You should see your prompt shows something like C:\Users\YOUR_USER_NAME>.

Next type the following command and press Enter to clone the AUTOMATIC1111 repository.

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git

A folder called stable-diffusion-webui should be created in your home directory.

It’s ok to clone the repository in a different folder instead of %userprofile%, as long as you can find the newly created stable-diffusion-webui folder. You will need to change the folder location accordingly in the following steps.

Step 4: Download a model file

Next, go to the newly created folder in File Explorer. Put in

%userprofile%\stable-diffusion-webui

in the address bar and press enter.

Navigate to the folder models and then Stable-diffusion. You should see a file Put Stable Diffusion checkpoints here.txt like below.

Download the Stable Diffusion v1.5 model checkpoint file (download link). Put it in that folder.

Step 5: Run webui

Now in File Explorer, go back to the stable-diffusion-webui folder. That is, go back up two levels or type

%userprofile%\stable-diffusion-webui

again in the address bar.

Find a file called webui-user.bat. Double-click to run and complete the installation.

This last step is going to take a while. When it is done, you will see a message

Running on local URL: http://127.0.0.1:7860

like the one below.

In your web browser, go to the URL

http://127.0.0.1:7860/

You should see the AUTOMATIC1111 webui! Put in a prompt (e.g. “a cat”) and hit Generate to test if Stable Diffusion is running correctly.

When you are done using Stable Diffusion, close the cmd black window to shut down Stable Diffusion.

To rerun Stable Diffusion, you need to double-click the webui-user.bat.

Options

You can speed up Stable Diffusion models with the --opt-sdp-attention option. If you have less than 8 GB VRAM on GPU, it is a good idea to turn on the --medvram option to save memory to generate more images at a time.

To enable them, right-click on the file webui-user.bat and select Edit. (You may need to select “Show More Options” first if you use Windows 11).

Replace the line

set COMMANDLINE_ARGS=

With

set COMMANDLINE_ARGS=--opt-sdp-attention --medvram

Save and close the file.

Double-click the webui-user.bat file to run Stable Diffusion.

Additional arguments

Add --gradio-img2img-tool color-sketch to COMMANDLINE_ARGS to enable the color sketch tool, which could be helpful in img2img. For example, the new line should look like:

set COMMANDLINE_ARGS=--opt-sdp-attention --medvram --gradio-img2img-tool color-sketch

If you want to use the computer as a server and access the GUI with another computer, use the add --listen to enable a connection from another computer. You will need to grant permission to allow outside connection the first time you run it.

Next Step

That’s it! I hope you will have fun making AI images.

If you are new to Stable Diffusion, check out the Quick Start Guide for some quick tips to use Stable Diffusion.

Head to our beginner’s series to learn Stable Diffusion step by step.

Check out this prompt generator for building high-quality prompts.

RTX 4000 series graphic cards

Good news for you if you use RTX 4070, RTX 4080 or RTX 4090 Nvidia graphic cards. The latest version of AUTOMATIC1111 supports these video card. (with torch 2.0 and cuda 11.8)

I will provide a benchmark speed so that you can make sure your setup is working correctly. The settings are:

batch size: 4
batch count: 10
Image size: 512×512
Sampling steps: 20
Sampling method: Euler a
Model: SD v1.5

Using a batch size of 1 is not recommended, as the measured speed is likely to be highly dependent on other components on your system.

You should see the speed of generating each image. Pick a stable value, usually in the middle like the 5th batch. The speed is in it/s (iterations per second).

You should get about 10 its/s on RTX 4090. (Note that this is 4 images per iteration) This is the max speed you can get nowadays.

You can use one of the following speed-up parameters.

Option 1:

--xformers

Option 2:

--opt-sdp-no-mem-attention --no-half-vae --opt-channelslast

Option 2 is slightly faster, but test them out to see what works best for you.

Update Stable Diffusion Webui AUTOMATIC1111

Your copy of AUTOMATIC1111 won’t be automatically updated by default. Given how fast things are moving, you will likely need to update it to use the latest and coolest.

Two update options:

Automatic update
Updating with a command

Option 1: Automatic update

You can configure Stable Diffusion WebUI to update every it starts.

Edit the file webui-user.bat. Add “git pull” before the line call webui.bat. The file should look something like

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--xformers --medvram
git pull
call webui.bat

Save the file.

From now on, webui will update itself every time it starts.

Option 2: Update with a command

“If it is not broken, don’t fix it.” This principle applies to Stable Diffusion, which involves updating the software only when a new feature is needed.

In Windows, open the file explorer and navigate to the installation directory of Stable Diffusion WebUI (stable-diffusion-webui). Then, type cmd in the address bar and press Enter.

Stable Diffusion webui directory. Type cmd in address bar.

A terminal should appear. Run the following command and press Enter to update update Stable Diffusion WebUI.

git pull

Resetting Stable Diffusion Webui

If git pull shows an error, it is usually because you have accidentally changed some files. You can reset the webui folder using the following two commands.

git checkout -f master

And then run git pull again.

git pull

Note that all files will be reset. You will need to make changes to webui-user.bat again.

Reverting to a previous version

Sometimes the latest version of webui is broken, and you don’t want to use it. You can revert to a previous version by following the instructions below.

Step 1: Go to this page to view previous versions. Each row is an earlier version.

Step 2: Pick a previous version you want to restore. You can judge it by the date and comment.

Step 3: Press the copy button to copy the hash code of the version.

Step 4: In the command prompt, run the following commands. The hash code (highlighted below) is just an example. You will paste the one you just copied.

git checkout 076d624a297532d6e4abebe5807fd7c7504d7a73

If you see errors, reset the webui (see the previous section) and retry.

After checking out the previous code, delete the venv folder and restart WebUI.

Frequently Asked Questions

AUTOMATIC1111 does not start after updating.

Delete the venv folder and restart AUTOMATIC1111.

If it still doesn’t work, delete both the venv and the repositories folders and restart.

If it still doesn’t work and you have recently installed an extension, delete the folder of that extension in the extensions folder. Delete the venv folder and restart.

Does it work on AMD GPU?

No, you have to have an NVIDIA GPU.

What Python version should I use?

Python 3.10.6. Later versions of 3.10 work fine. But don’t use 3.11 or later.

How to resolve NaN errors when generating images?

Add --no-half argument to webui-user.bat (See Adding arguments)

How to resolve out-of-memory errors?

Use --lowvram instead of --medvram argument in webui-user.bat (See Adding arguments)

For optimizing memory usage for SDXL models:

Nvidia (12GB+) --xformers
Nvidia (8GB) --medvram-sdxl --xformers
Nvidia (4GB) --lowvram --xformers

See this article for more details.

Python doesn’t work correctly.

Try removing the previously installed Python using Add or remove programs.

There are two options for installing Python listed. Try the other one if the one you used didn’t work.

Is there an easier way to install AUTOMATIC1111?

The above is the official install instructions. Two alternatives:

Recently they started to tag release builds. They are supposed to work after downloading and unzipping.
There’s an unofficial easy installer for Windows you can try.

I tried everything, but it still does not work.

You can use Google Colab to run AUTOMATIC1111. This is what I use. The notebook launches AUTOMATIC1111 with one mouse click.

Or Use AUTOMATIC1111 online.

Источник

На чтение 6 мин Просмотров 97.3к. Опубликовано 29.03.2023

Добавил самое полное руководство по Stable Diffusion – идеально для первого знакомства!

Если вас интересует нейросеть Stable Diffusion и как ее скачать – я подготовил для вас исчерпывающее руководство. Отсутствие понятных ответов в сегменте русского интернета побудили написать меня данную заметку, ведь неподготовленному пользователю невероятно сложно разобраться со всеми дистрибутивами и настройками.

Для данного изображения был использован stable diffusion prompts girl cyberpunk computer

Я всегда завидовал людям, которые умеют хорошо рисовать – данный дар меня обошел стороной. Очень хотел этому научиться, однако интересы всегда смещались в сторону железа, игрушек и прочего. Поиск изображений и иллюстраций для моих заметок всегда занимал много времени. Мне хотелось привнести немножечко уникальности в оформление… но вы понимаете, что если для пошаговых инструкций это не было проблемой (скриншоты уникальны), то для заголовков и в местах где нужно проиллюстрировать – с моими навыками я мог только криво отредактировать, ни о каких вариантах нарисовать с нуля даже и речи не было.

Последние две недели я все свое время потратил на изучение нейросети и составление текстовых описаний картинок (это в среде Stable Diffusion называется PROMPT). Вся суть использования заключается в максимально подробном описании изображения, которое вы хотите сгенерировать.

Содержание

Как скачать Stable Diffusion на свой компьютер
Устанавливаем Python
Устанавливаем GIT
Загрузка Stable Diffusion от AUTOMATIC1111
Настройка параметров видеопамяти
Редактирование webui-user для слабых видеокарт
Загрузка модели
Запуск WebUI
Известные проблемы на этом этапе
Что дальше

Как скачать Stable Diffusion на свой компьютер

В отличии от DALLE и популярной сегодня Midjourney (именно с ее поиска я и узнал про Stable Diffusion) – мы имеем возможность установить нейросеть на свой компьютер и использовать ее автономно без каких либо ограничений. После нескольких неудач с запуском официальной версии и перебиранием различных приложений и расширений для Windows мне повезло встретить веб версию от AUTOMATIC1111 – это работает так, как я себе и представлял, именно эту версию мы сегодня будем рассматривать.

Устанавливаем Python

Для успешного запуска нам понадобится среда Python – не нужно скачивать самую последнюю версию, сам разработчик пишет о корректной работе в Python 3.10.9. Именно ее мы и установим (ниже ссылка на 64 разрядную версию, ввиду того что нейросеть требовательная до ресурсов компьютера – рассматривать 32 битку даже не буду)

https://www.python.org/ftp/python/3.10.9/python-3.10.9-amd64.exe

Во время установки обязательно установите галочку напротив “Add Python to PATH”, иначе ничего работать не будет, Windows не будет знать что у вас установлен Python.

Устанавливаем GIT

Тут все элементарно, даже комментировать не буду, просто переходим по ссылке и жмем “Click here to download”, после загрузки устанавливаем нажимая везде “Далее”.

https://git-scm.com/download/win

Во многих инструкциях установка GIT опциально и не требуется, ее используют непосредственно для удобства скачивания Stable Diffusion Webui. В моем случае нейросеть не запустилась без установленного Git – поэтому скачивать будем через него!

На этом этапе у нас все готово для загрузки Stable Diffusion на компьютер. Теперь необходимо выбрать расположение для нашей нейросети. Несмотря на свой скромный размер – реально, после установки всех необходимых моделей и расширений папка будет занимать не менее 30 гигабайт на диске. Следовательно необходимо заранее продумать о свободном месте. НЕЛЬЗЯ чтобы в пути использовались кириллица или пробелы – т.е. желательно положить в корень диска и использовать имя вроде STABLEDIFFUSION.

Загрузка Stable Diffusion от AUTOMATIC1111

Кликаем правой кнопкой мыши в подготовленной папке и жмем “Git Bash Here” (если у вас Windows 11, то сперва выбираем пункт “Показать дополнительные параметры”).

Вводим команду ниже и жмем Enter…

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui

…останется только дождаться загрузки (там совсем немного).

По окончанию загрузки вы обнаружите у себя вновь созданную папку “stable-diffusion-webui”.

Папка с загруженной нейросетью на компьютере

Я бы и рад написать что – можно уже приступать к творчеству, но нет… мы только начали!

Настройка параметров видеопамяти

Перед первым запуском лучше заранее настроить параметры VRAM, чтобы не столкнуться с ошибками “Out of memory”. Для видеокарт с небольшим количеством памяти необходимо прописать дополнительные параметры запуска в файле конфигурации (хотя если у вас современная видеокарта от nvidia 30xx или 40xx то можете пропустить эту часть руководства по запуску).

Если вы новичок в ИТ, то вам поможет руководство “Как узнать объем видеокарты на компьютере” – далее нам понадобится информация об объеме вашей видеокарты.

--lowvram - данный параметр необходимо использовать если у вас 2гб или меньше,

--medvram - используется если у вас 4гб видеопамяти или менее,

Если у вас видеокарта с объемом памяти более 4гб без необходимости не вписывайте никакие дополнительные параметры (если будет наблюдаться ошибки, тогда уже пробовать различные конфиги). Использование данных токенов замедляют работу stable diffusion, но позволяют работать на старом железе.

Редактирование webui-user для слабых видеокарт

Открываем папку “stable-diffusion-webui” которую вы только что загрузили на свой компьютер с репозитория github. Кликните правой кнопкой мыши по webui-user (Тип: Пакетный файл Windows) и нажмите “Редактировать” (в Windows 11 сперва выберите “Показать дополнительные параметры”.)

Команды необходимо добавлять после строки“set COMMANDLINE_ARGS=”

Выше приведен пример для видеокарты с 4 гигабайтами графической памяти – это все, что необходимо для первичной настройки. Почти все готов для запуска WebUI!

Загрузка модели

Модель – отвечает за конечный результат генерации изображения. Как правило они имеют расширение ‘.ckpt’ или ‘.safetensors’. Я не буду рекомендовать стандартную модель – для новичков на мой взгляд идеальными будут:

Deliberate – 2 гиговая модель от нашего соотечественника, чем подробнее вы опишите свои хотелки, тем лучше будет результат.

Dreamshaper – на мой взгляд подходит исключительно для артов или иллюстраций.

На самом деле перейдя по ссылкам вы возможно найдете модель лучшую для вас, выбор сейчас пугающе огромен!

Скачанные модели необходимо положить в ‘../stable-diffusion-webui/models/Stable-diffusion’

Запуск WebUI

Все готов для запуска Stable Diffusion на компьютере. Найдите файл ‘webui-user’ и запустите его

Веб интерфейсу потребует несколько минут для установки всех необходимых компонентов. В какой-то момент вам может показаться что ничего не происходит – почти всегда это нет так, все зависит от скорости вашего интернет соединения (у меня с 500мбит интернетом первый запуск занял около 7 минут).

Для входа в Stable Diffusion UI просто перейдите в браузере по адресу http://127.0.0.1:7860/

Известные проблемы на этом этапе

RuntimeError: Couldn’t install torch.

Для работы Stable Diffusion лучше всего установить версию Python 3.10.6 из начала руководства. Если вы скачали последнюю версию с официального сайта — произведите удаление и установите рекомендованную

Не открывается WebUI в браузере

Проверьте что вы не пытаетесь подключиться по протоколу ‘https://’, адрес всегда начинается с ‘http://’. После удачной загрузки адрес всегда можно подсмотреть в командной строке, закрывать ее не нужно.

Что дальше

А дальше забыть о свободном времени и пытаться составить идеальный запрос. В поле prompt пишем что хотим увидеть (на английском конечно, можете использовать переводчик как я), жмем Generate и смотрим как происходит Магия!

Интерфейс Stable Diffusion от Automatic1111

Друзья, тема с установкой Stable Diffusion первая на блоге в разделе нейросетей, хотелось бы узнать ваше мнение – есть ли смысл в подробных разборах, существует ли необходимость в обучающих руководствах?

Источник

Всё моё свободное время в последние четыре дня было потрачено на одну задачу — составление запросов для нейросети Stable Diffusion, нейросети для создания изображений по текстовому описанию. Все изображения для статьи (кроме скриншотов) были созданы лично в этой нейросети, совершенно не художником.

В этой инструкции подробно о том, как установить Stable Diffusion на ваш компьютер или ноутбук, о возможности попробовать нейросеть в работе без установки и некоторые дополнительные детали, которые могут оказаться полезными, если вы решите нырнуть в это также, как и я.

Установка Stable Diffusion

Нейросеть Stable Diffusion отличается от таких аналогов как DALL-E 2 или Midjourney открытым исходным кодом: то есть, при наличии соответствующего оборудования, вы можете совершенно бесплатно установить необходимое ПО на свой компьютер и использовать для создания изображений по текстовому запросу (в обсуждениях часто используют кальку с английского «промпт»).

Нейросеть Stable Diffusion для генерации изображений

Официальное ПО Stable Diffusion не имеет удобного графического интерфейса, за исключением доступного на официальном сайте https://beta.dreamstudio.ai/, с которого и рекомендую начать эксперименты и посмотреть, нужно ли вам это: после регистрации у вас будет 200 бесплатных генераций с параметрами по умолчанию (регистрироваться можно и больше раз с разными адресами электронной почты).

При установке официального софта на компьютере все действия придётся выполнять в командной строке. Кроме того, вы мало что сможете сгенерировать с видеокартой, имеющей 6 Гб памяти или менее.

Однако, благодаря открытому исходному коду, почти сразу после релиза Stable Diffusion появились альтернативные варианты ПО («форки»), оптимизирующие запуск на более слабом оборудовании (4 Гб VRAM, есть даже варианты, работающие на CPU, но очень медленно), предоставляющие удобный доступ к настройкам и упрощающие использование нейросети.

С одного из таких альтернативных вариантов, который я нашел наиболее удачным, и начнем установку. Если же вам требуется описание процесса установки официального варианта, его вы также сможете найти далее в статье.

Установка Stable Diffusion WebUI от Automatic

Внимание: с момент написания инструкции процесс установки менялся и уточнить необходимые шаги лучше на официальном GitHub проекта.

Сначала о том, что нам потребуется: достаточно мощный компьютер или ноутбук, видеокарта NVIDIA GeForce, не менее 4 Гб видеопамяти. Все устанавливаемые компоненты займут около 10 Гб на жестком диске или SSD. Если всё это в наличии, можно приступать:

Установите Python 3.10.6 (разработчик указывает именно эту версию) с официального сайта https://www.python.org/downloads/windows/. При установке отметьте пункт «Добавить Python в переменную PATH».
Установите Git с официального сайта https://git-scm.com/download/win. Если вам не ясны параметры при установке, их можно оставить в рекомендуемых по умолчанию значениях.
Зайдите на страницу Automatic1111 на GitHub https://github.com/AUTOMATIC1111/stable-diffusion-webui, нажмите по стрелке справа от кнопки «Code» вверху справа и загрузите ZIP-архив со Stable Diffusion WebUI. Распакуйте в удобное расположение, но так, чтобы путь не содержал пробелов или кириллических символов (это может вызвать проблемы).
Скачайте обученную модель Stable Diffusion последней версии с официального источника https://huggingface.co/CompVis/stable-diffusion-v-1-4-original (потребуется регистрация) или из этого хранилища.
Переименуйте скачанный файл в model.ckpt и переместите его в папку, куда были распакованы файлы на 3-м шаге (в ту же папку, где находится файл webui.bat).
Запустите файл webui-user.bat (не от имени администратора, простой запуск двойным кликом) и дождитесь, когда скрипт автоматически скачает и установит недостающие компоненты. Учитывайте: строка прогресса не отображается, поэтому при загрузке объемных компонентов (Torch и CUDA) может показаться, что процесс завис.
По завершении установки вы увидите сообщение
```
Running on local URL: http://127.0.0.1:7860/
```
перейдите по указанному адресу (не закрывайте окно консоли, это прервет работу Stable Diffusion WebUI) в любом браузере и начните использование.
Если ваша видеокарта имеет 6 Гб видеопамяти или меньше, при попытке сгенерировать изображение даже в выставленном по умолчанию расширении 512×512 вы можете получить сообщение о недостатке VRAM (видеопамяти). В этом случае, закройте окно консоли (или прервите выполнение, нажав Ctrl+C в окне консоли), откройте файл webui-user.bat с помощью текстового редактора и измените строку с параметрами запуска на
```
set COMMANDLINE_ARGS=--medvram
```
Затем снова запустите веб-интерфейс файлом webui-user.bat
Дополнительные возможности настройки Stable Diffusion WebUI и параметры запуска можно найти на официальной странице разработчика.

Установка официальной версии Stable Diffusion

При установке официальной версии Stable Diffusion все необходимые компоненты почти те же самые, но их потребуется устанавливать вручную. Требования те же самые, за исключением необходимости использования видеокарты с не менее чем 6 Гб VRAM.

Скачайте и установите Git https://git-scm.com/download/win используйте рекомендуемые параметры (оставьте возможность использования Git в командной строке и сторонних программах).
Установите Miniconda3 с официального сайта https://docs.conda.io/en/latest/miniconda.html, при установке выберите опцию «Установить для всех пользователей).
Скачайте архив Stable Diffusion с официального источника https://github.com/CompVis/stable-diffusion (нажать по кнопке «Code», затем выбрать пункт «Download ZIP»).
Скачайте модель Stable Diffusion последней версии с https://huggingface.co/CompVis/stable-diffusion-v-1-4-original (потребуется регистрация) или: из этого хранилища (без регистрации), переименуйте файл в model.ckpt
Запустите консоль Miniconda3 (Anaconda Prompt), для этого можно использовать поиск в панели задач Windows 11 и Windows
В открывшейся консоли используйте команды для создания папки (в нашем варианте — на диске C) для файлов Stable Diffusion
```
cd C:/
mkdir stable-diffusion
cd stable-diffusion
```
Не закрывайте окно консоли.
Откройте скачанный на 3-м шаге архив и скопируйте папку stable-diffusion-main (саму папку, а не файлы в ней) в C:\stable-diffusion\
По порядку используйте следующие команды в консоли Miniconda3
```
cd C:\stable-diffusion\stable-diffusion-main
conda env create -f environment.yaml
conda activate ldm
mkdir models\ldm\stable-diffusion-v1
```
Процесс займет продолжительное время, так как из сети будут скачиваться дополнительные компоненты.
Переместите файл model.ckpt в папку C:\stable-diffusion\stable-diffusion-main\models\ldm\stable-diffusion-v1
Готово. Теперь мы можем запустить Stable Diffusion, введя команду
```
conda activate ldm
```
В дальнейшем запуск будет всегда производиться именно с помощью этой команды.
Генерация изображений выполняется здесь же в консоли с помощью передачи параметров. Например, вы можете ввести
```
python scripts/txt2img.py --prompt "concept robot, colorful, cinematic" --plms --n_iter 5 --n_samples 1
```
Команда создаст набор из 5 изображений с разрешением 512×512 по запросу «concept robot, colorful, cinematic», которые будут помещены в папку
```
C:\stable-diffusion\stable-diffusion-main\outputs\txt2img-samples\samples
```
Картинка с сайта: remontka.pro

Чтобы увидеть информацию по доступным параметрам командной строки используйте команду

python scripts/txt2img.py --help

Использование Stable Diffusion WebUI

После запуска webui-user.bat и перехода в браузере на адрес 127.0.0.1:7860 перед вами будет веб-интерфейс, доступный локально на вашем компьютере (для работы Интернет не требуется), первая вкладка которого — txt2img, где и происходит всё самое интересное. Экспериментировать можно начать сразу же: просто введите текст на английском в поле сверху и нажмите кнопку «Generate», чтобы получить готовую картинку с параметрами по умолчанию (на скриншоте они уже изменены).

Если поднести указатель мыши к названию доступных параметров, большинство из них имеют описания на английском. Среди основных:

Sampling Method — алгоритм создания изображения. Влияет на результат, скорость, требуемую видеопамять.
Sampling Steps — количество шагов, в течение которых нейросеть «приводит» результат к желаемому. Влияет на время генерации. Больше — не всегда лучше: нужный результат может получиться за 30-50 шагов, а дальнейшая работа может не добавить деталей, а исказить результат (но бывает и иначе). Если то, что получилось, вам понравилось, можно использовать тот же Seed для генерации изображения по этому же запросу, но с другим количеством шагов и оценить результат.
Batch count — количество наборов создаваемых изображений.
Batch size — количество изображений в наборе (влияет на требуемую память).
CGF Scale — «свобода» обработчика изображения, влияет на то, насколько точно результат будет соответствовать описанию. При более низких значениях получаем большее разнообразие.
Height и Width — ширина и высота изображения, очень сильно влияет на требования к памяти.
Seed — «зерно». По умолчанию равно -1, при этом значении оно будет задано случайно при каждом очередном нажатии кнопки «Generate». Если с определенным Seed вы получили интересный результат, можете скопировать его в это поле, чтобы продолжить эксперименты над понравившимся изображением, изменяя параметры.

По умолчанию изображения сохраняются во вложенных папках в папке outputs в расположении, куда вы установили Stable Diffusion WebUI, но при желании автоматическое сохранение можно отключить на вкладке «Settings», здесь же можно настроить и другие параметры.

Вкладка img2img позволяет модифицировать имеющееся изображение в соответствии с текстовым описанием.

На вкладке Extras собраны дополнительные инструменты. Основное — увеличение разрешения изображения с использованием нейросети.

Значения параметров в большинстве своем вам придётся подбирать самостоятельно, отслеживая результат. Но даже при одних и тех же значениях он может сильно отличаться и прежде всего зависит от заданного запроса, прописанных в нем требований к изображению и стилей. Это может быть простой рисунок в стиле плаката:

Простой стилизованный рисунок в Stable Diffusion

А может быть и почти фотография:

Фотореалистичное изображение в Stable Diffusion

Легко создать таких роботов:

И посложнее — таких:

Усложненное изображение в Stable Diffusion

Не забывайте проявлять фантазию, нарисовать можно многое, главное уметь это описать:

Изображение, созданное в Stable Diffusion

Вспоминайте названия кинематографических эффектов, свойств материалов и описания форм:

Чтобы получить лучшие результаты, рекомендую изучить чужие работы и используемые запросы: на тему создания изображений в Stable Diffusion есть множество тематических каналов в мессенджерах, социальных сетях и тематических сайтах. Но и собственные идеи часто могут дать интересный и красивый эффект, время для неожиданных находок в запросах ещё не вышло.

Источник