Releases: lllyasviel/Fooocus
Releases · lllyasviel/Fooocus
v2.5.0
How to update
This version includes various package updates. If the auto-update doesn't work:
- Open a terminal in the Fooocus folder (go to the location of config.txt, open terminal by clicking in the address bar of the file explorer, type
cmdand hit enter) and rungit pull. If you do not have git installed, skip to step 2. - Update packages
- Windows (installation through zip file): run
..\python_embeded\python.exe -m pip install -r .\requirements_versions.txt(Windows using embedded python, installation method zip file) or download Fooocus again (zip file attached to this release) - other: manually update the packages using
python.exe -m pip install -r requirements_versions.txtor use the docker image
- Windows (installation through zip file): run
What's Changed
- feat: update python dependencies and add segment_anything
- sync enhance feature and code refactoring from mashb1t/Fooocus
- feat: add enhance feature, which offers easy image refinement steps (similar to adetailer, but based on dynamic image detection instead of specific mask detection models). See #3281.
- feat: improve GroundingDINO and SAM image masking
- refactor: rewrite async worker code, make code much more reusable to allow iterations and improve reusability
- refactor: move checkboxes Enable Mask Upload and Invert Mask When Generating from Developer Debug Mode to Inpaint Or Outpaint
- refactor: rename checkbox Enable Mask Upload to Enable Advanced Masking Features
- fix: get upscale model filepath by calling downloading_upscale_model() to ensure the model exists
- i18n: rename tab titles and translations from singular to plural
- i18n: rename document to documentation
- feat: update default models to latest versions
- animaPencilXL_v400 => animaPencilXL_v500 (#2943)
- DreamShaperXL_Turbo_dpmppSdeKarras => DreamShaperXL_Turbo_v2_1
- SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4 => SDXL_FILM_PHOTOGRAPHY_STYLE_V1
- feat: add preset for pony_v6 (using ponyDiffusionV6XL, discussion in #3217)
- feat: add style
Fooocus Pony(discussion in #3217) - feat: remove
by wlopfrom styleFooocus Masterpieceas it has been causing unintended watermarks - feat: add restart sampler (paper)
- feat: add config option for default_inpaint_engine_version, sets inpaint engine for pony_v6 and playground_v2.5 to None for improved results (incompatible with inpaint engine, discussion in #3217)
- feat: add image editor functionality to mask upload (same as for inpaint, now correctly resizes and allows more detailed mask creation, discussion in mashb1t#44)
- feat: add persistent model cache for metadata. Use
--rebuild-hash-cacheto manually rebuild the cache for all non-cached hashes (optional, cache will otherwise be lazy-loaded. Remove--rebuild-hash-cacheafter executing once) - refactor: rename
--enable-describe-uov-imageto--enable-auto-describe-imageto better reflect its purpose (now also works for enhance image upload) - feat: adjust playground_v2.5 preset by @mashb1t in #3136
- fix: correctly identify and remove performance LoRA by @mashb1t in #3150
- apply performance from metadata by @mashb1t in #3153
- hotfix: add missing method in performance enum by @mashb1t in #3154
- feat: add vae to possible preset keys by @mashb1t in #3177
- feat: add restart sampler by @licyk in #3219
- build(deps): bump docker/build-push-action from 5 to 6 by @dependabot in #3223
New Contributors
- @licyk made their first contribution in #3219
- @dependabot made their first contribution in #3223
Full Changelog: v2.4.3...v2.5.0
Contributors
mashb1t, dependabot, and licyk
Assets 3
16
Join discussion
v2.5.0-rc1
What's Changed
- feat: update python dependencies and add segment_anything
- sync enhance feature and code refactoring from mashb1t/Fooocus
- feat: add enhance feature, which offers easy image refinement steps (similar to adetailer, but based on dynamic image detection instead of specific mask detection models). See #3281.
- feat: improve GroundingDINO and SAM image masking
- refactor: rewrite async worker code, make code much more reusable to allow iterations and improve reusability
- refactor: move checkboxes Enable Mask Upload and Invert Mask When Generating from Developer Debug Mode to Inpaint Or Outpaint
- refactor: rename checkbox Enable Mask Upload to Enable Advanced Masking Features
- fix: get upscale model filepath by calling downloading_upscale_model() to ensure the model exists
- i18n: rename tab titles and translations from singular to plural
- i18n: rename document to documentation
- feat: update default models to latest versions
- animaPencilXL_v400 => animaPencilXL_v500 (#2943)
- DreamShaperXL_Turbo_dpmppSdeKarras => DreamShaperXL_Turbo_v2_1
- SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4 => SDXL_FILM_PHOTOGRAPHY_STYLE_V1
- feat: add preset for pony_v6 (using ponyDiffusionV6XL, discussion in #3217)
- feat: add style
Fooocus Pony(discussion in #3217) - feat: remove
by wlopfrom styleFooocus Masterpieceas it has been causing unintended watermarks - feat: add restart sampler (paper)
- feat: add config option for default_inpaint_engine_version, sets inpaint engine for pony_v6 and playground_v2.5 to None for improved results (incompatible with inpaint engine, discussion in #3217)
- feat: add image editor functionality to mask upload (same as for inpaint, now correctly resizes and allows more detailed mask creation, discussion in mashb1t#44)
- feat: add persistent model cache for metadata. Use
--rebuild-hash-cacheto manually rebuild the cache for all non-cached hashes (optional, cache will otherwise be lazy-loaded. Remove--rebuild-hash-cacheafter executing once) - refactor: rename
--enable-describe-uov-imageto--enable-auto-describe-imageto better reflect its purpose (now also works for enhance image upload) - feat: adjust playground_v2.5 preset by @mashb1t in #3136
- fix: correctly identify and remove performance LoRA by @mashb1t in #3150
- apply performance from metadata by @mashb1t in #3153
- hotfix: add missing method in performance enum by @mashb1t in #3154
- feat: add vae to possible preset keys by @mashb1t in #3177
- feat: add restart sampler by @licyk in #3219
- build(deps): bump docker/build-push-action from 5 to 6 by @dependabot in #3223
New Contributors
- @licyk made their first contribution in #3219
- @dependabot made their first contribution in #3223
Full Changelog: v2.4.3...v2.5.0-rc1
v2.4.3
What's Changed
- fix: correctly set alphas_cumprod by @mashb1t in #3106
- feat: parse env var strings to expected config value types by @mashb1t in #3107
Full Changelog: v2.4.2...v2.4.3
v2.4.2
What's Changed
- feat: add support and preset for playground v2.5 (only works with performance Quality or Speed, use with scheduler edm_playground_v2) by @mashb1t in #3073
- feat: make textboxes (incl. positive prompt) resizable by @mashb1t in #3074
- fix: use default vae name instead of None on file refresh by @mashb1t in #3045
- fix: correctly use translation and dynamic label for aspect ratios by @mashb1t in #3046
- feat: optimize performance lora filtering in metadata by @mashb1t in #3048
- feat: rework intermediate image display for restricted performances by @mashb1t in #3050
- fix: turbo scheduler loading issue by @mashb1t in #3065
- fix: chown files directly at copy in Dockerfile by @mashb1t in #3066
- feat: sync cmd args in readme by @mashb1t in #3075
- fix: correct sampling for tcd scheduler when gamma is 0 by @mashb1t in #3093
Full Changelog: v2.4.1...v2.4.2
v2.4.1
What's Changed
- fix: adjust clip skip default value from 1 to 2 by @mashb1t in #3011
- fix: add type check for undefined, use fallback when no translation for aspect ratios was given by @mashb1t in #3025
- feat: build docker image tagged "edge" on push to main branch by @mashb1t in #3026
Full Changelog: v2.4.0...v2.4.1
v2.4.0
What's Changed
- feat: support download huggingface files from a mirror site by @chenxinlong in #2637
- chore: update interposer from v3.1 to v4.0 by @mashb1t in #2717
- feat: add button to reconnect UI without having to reload the page by @mashb1t in #2727
- feat: add optional model VAE select by @mashb1t in #2867
- feat: choose random style by @mashb1t in #2855
- feat: update anime from animaPencilXL_v100 to animaPencilXL_v310 by @mashb1t in #2454
- refactor: rename label for reconnect button by @mashb1t in #2893
- feat: add full raw prompt to history log by @docppp in #1920
- fix: use correct border radius css property by @khanvilkarvishvesh in #2845
- fix: do not close meta tag in HTML header by @e52fa787 in #2740
- feat: automatically describe image on uov image upload by @mashb1t in #1938
- add nsfw image censoring via config and checkbox by @mashb1t in #958
- feat: add align your steps scheduler by @mashb1t in #2905
- feat: add support for lora inline prompt references by @cantor-set in #2323
- feat: add tcd sampler and discrete distilled tcd scheduler based on sgm_uniform (same as lcm) by @mashb1t in #2907
- feat: add performance hyper-sd based on 4step LoRA by @mashb1t in #2812
- fix: remove leftover code for hyper-sd testing by @mashb1t in #2959
- feat: optimize model management of nsfw image censoring by @mashb1t in #2960
- feat: progress bar improvements by @mashb1t in #2962
- feat: inline lora optimisations by @mashb1t in #2967
- feat: change code owner from @lllyasviel to @mashb1t by @mashb1t in #2948
- feat: only use valid inline loras, add subfolder support by @mashb1t in #2968
- feature: Reads the size and ratio of the image and gives the recommended size by @xhoxye in #2971
- feat: build and push container image for ghcr.io, update docker.md, and other related fixes by @xynydev in #2805.
See available images - feat: adjust line ending default config by @mashb1t in #2991
- feat: add translation for image size describe by @mashb1t and @xhoxye in #2992
- feat: read value 'CFG Mimicking from TSNR' from presets by @Alexdnk in #2990
- feat: add inpaint brush color picker by @mashb1t in #2997
- feat: remove labels from most of the image input fields by @mashb1t in #2998
- feat: add clip skip handling by @mashb1t in #2999
- feat: make ui settings more compact by @Alexdnk and @mashb1t in #2590
New Contributors
- @chenxinlong made their first contribution in #2637
- @docppp made their first contribution in #1920
- @khanvilkarvishvesh made their first contribution in #2845
- @e52fa787 made their first contribution in #2740
- @cantor-set made their first contribution in #2323
- @xynydev made their first contribution in #2805
- @Alexdnk made their first contribution in #2990
Full Changelog: 2.3.1...v2.4.0
Join the discussion: #3003
Contributors
chenxinlong, mashb1t, and 8 other contributors
Assets 2
2.4.0-rc2
2.4.0-rc1
What's Changed
- feat: support download huggingface files from a mirror site by @chenxinlong in #2637
- chore: update interposer from v3.1 to v4.0 by @mashb1t in #2717
- feat: add button to reconnect UI without having to reload the page by @mashb1t in #2727
- feat: add optional model VAE select by @mashb1t in #2867
- feat: choose random style by @mashb1t in #2855
- feat: update anime from animaPencilXL_v100 to animaPencilXL_v310 by @mashb1t in #2454
- refactor: rename label for reconnect button by @mashb1t in #2893
- feat: add full raw prompt to history log by @docppp in #1920
- fix: use correct border radius css property by @khanvilkarvishvesh in #2845
- fix: do not close meta tag in HTML header by @e52fa787 in #2740
- feat: automatically describe image on uov image upload by @mashb1t in #1938
- add nsfw image censoring via config and checkbox by @mashb1t in #958
- feat: add align your steps scheduler by @mashb1t in #2905
- feat: add support for lora inline prompt references by @cantor-set in #2323
- feat: add tcd sampler and discrete distilled tcd scheduler based on sgm_uniform (same as lcm) by @mashb1t in #2907
- feat: add performance hyper-sd based on 4step LoRA by @mashb1t in #2812
New Contributors
- @chenxinlong made their first contribution in #2637
- @docppp made their first contribution in #1920
- @khanvilkarvishvesh made their first contribution in #2845
- @e52fa787 made their first contribution in #2740
- @cantor-set made their first contribution in #2323
Full Changelog: 2.3.1...2.4.0-rc1
2.3.1
What's Changed
- fix: remove positive prompt from anime prefix by @mashb1t in #2571
- fix: add enabled value to LoRA when setting default_max_lora_number by @mashb1t in #2576
- fix: correctly set preset config and loras in meta parser by @mashb1t in #2588
- fix: correctly load image number from preset / do not reset to 1 anymore by @mashb1t in #2611
- fix: use correct base dimensions for outpaint mask padding by @mashb1t in #2612
- fix: add compatibility for LoRAs in a1111 metadata scheme by @mashb1t in #2615
Full Changelog: 2.3.0...2.3.1
2.3.0
What's Changed
- fix: parse width and height as int when applying metadata by @mashb1t in #2452
- fix: do not attempt to remove non-existing image grid file by @mashb1t in #2456
- feat: add troubleshooting guide to bug report template again by @mashb1t in #2489
- feat: use jpeg instead of jpg, use enums instead of strings by @mashb1t in #2453
- feat: add performance lightning with 4 step LoRA by @mashb1t in #2415
- fix: change synthetic refiner switch from 0.5 to 0.8 by @xhoxye in #2165
- feat: add config for temp path and temp path cleanup on launch by @midareashi and @mashb1t in #1992
- feat: scan wildcard subdirectories by @Cruxial0 and @mashb1t in #2466
- fix: use correct method call for interrupt_current_processing by @mashb1t in #2506
- feat: read wildcards in order 通配符增强，切换顺序读取。 by @xhoxye and @mashb1t in #1761
- feat: use scrollable 2 column layout for styles by @hswlab in #1883
- feat: allow to add disabled LoRAs in config by @mashb1t in #2507
- fix: prioritize VRAM over RAM in Colab, preventing out of memory issues by @Peppe289 and @mashb1t in #1710
- fix: update xformers to 0.0.23 by @mashb1t in #2517
- feat: update xformers to 0.0.23 in Dockerfile by @josephrocca in #2519
- fix: parse seed as string to display correctly in metadata preview by @mashb1t in #2536
- feat: allow user add custom preset without block
git pullby @Zxilly in #2520 - feat: add preset selection to Gradio UI (session based) by @mashb1t in #1570
- fix: add error output for unsupported images by @shaye059 in #2537
- feat: improve anime preset by adding style Fooocus Semi Realistic by @DavidDragonsage in #2492
- feat: add backwards compatibility for presets without disable/enable LoRA boolean by @mashb1t
New Contributors
- @midareashi made their first contribution in #1992
- @Cruxial0 made their first contribution in #2466
- @hswlab made their first contribution in #1883
- @Peppe289 made their first contribution in #1710
- @josephrocca made their first contribution in #2519
- @Zxilly made their first contribution in #2520
- @shaye059 made their first contribution in #2537
- @DavidDragonsage made their first contribution in #2492
Full Changelog: 2.2.1...2.3.0
