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 cmd and hit enter) and run git 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.txt or use the docker image
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 https://github.com/lllyasviel/Fooocus/discussions/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
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 https://github.com/lllyasviel/Fooocus/discussions/3217)
feat: add image editor functionality to mask upload (same as for inpaint, now correctly resizes and allows more detailed mask creation, discussion in https://github.com/mashb1t/Fooocus/discussions/44)
feat: add persistent model cache for metadata. Use --rebuild-hash-cache to manually rebuild the cache for all non-cached hashes (optional, cache will otherwise be lazy-loaded. Remove --rebuild-hash-cache after executing once)
refactor: rename --enable-describe-uov-image to --enable-auto-describe-image to better reflect its purpose (now also works for enhance image upload)
feat: adjust playground_v2.5 preset by @mashb1t in https://github.com/lllyasviel/Fooocus/pull/3136
fix: correctly identify and remove performance LoRA by @mashb1t in https://github.com/lllyasviel/Fooocus/pull/3150
apply performance from metadata by @mashb1t in https://github.com/lllyasviel/Fooocus/pull/3153
hotfix: add missing method in performance enum by @mashb1t in https://github.com/lllyasviel/Fooocus/pull/3154
feat: add vae to possible preset keys by @mashb1t in https://github.com/lllyasviel/Fooocus/pull/3177
feat: add restart sampler by @licyk in https://github.com/lllyasviel/Fooocus/pull/3219
build(deps): bump docker/build-push-action from 5 to 6 by @dependabot in https://github.com/lllyasviel/Fooocus/pull/3223
New Contributors
@licyk made their first contribution in https://github.com/lllyasviel/Fooocus/pull/3219
@dependabot made their first contribution in https://github.com/lllyasviel/Fooocus/pull/3223
Full Changelog: https://github.com/lllyasviel/Fooocus/compare/v2.4.3...v2.5.0