feat: Add Anima support - #860
Merged
Merged
Conversation
|
This does not support using existing anima_baseV10.safetensors as model path, could you support that?
|
You should not use that model file directly, use this instead： |
|
Why is it not merged? Seems to be working fine (trained a slider with it) |
|
Is there any config file to train anima?? In my case on model doesn't appear the circlestone model |
Contributor
|
Thank you |
socrasteeze
added a commit
to socrasteeze/ai-toolkit
that referenced
this pull request
Jul 16, 2026
Upstream shipped its own diffusers-based Anima (ostris#860), so the fork's vendored sd-scripts port (Phase 4) is retired: the anima extension dir, diffusion_models/__init__.py, and options.ts are byte-identical to upstream again. Fork enhancements survive, adapted to upstream's implementation: presets v2.0 + example config (diffusers-name ignore_if_contains replaces adaln_modulation; sigmoid_scale dropped - unsupported upstream) and the unchanged advisor recipe. Also adds a community 16GB+ KREA2 preset (automagic3, qfloat8, layer offloading). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
perfectgf
pushed a commit
to perfectgf/lora-dataset-studio
that referenced
this pull request
Jul 18, 2026
…s into CHANGELOG.md The README now carries a Roadmap section (directions, not dates) mirroring the Discord roadmap: Merge Lab, Anima family (unblocked by ostris/ai-toolkit#860), WAN video LoRAs, smarter watermark detection, more base models. Older Recent improvements entries roll into a new CHANGELOG.md to keep the README readable, and the Table of contents gains the missing Roadmap link. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011jyNdV4Cyo4Lo9L6hGkCzA
perfectgf
pushed a commit
to perfectgf/lora-dataset-studio
that referenced
this pull request
Jul 22, 2026
…s into CHANGELOG.md The README now carries a Roadmap section (directions, not dates) mirroring the Discord roadmap: Merge Lab, Anima family (unblocked by ostris/ai-toolkit#860), WAN video LoRAs, smarter watermark detection, more base models. Older Recent improvements entries roll into a new CHANGELOG.md to keep the README readable, and the Table of contents gains the missing Roadmap link.
socrasteeze
added a commit
to socrasteeze/ai-toolkit
that referenced
this pull request
Aug 4, 2026
Upstream shipped its own diffusers-based Anima (ostris#860), so the fork's vendored sd-scripts port (Phase 4) is retired: the anima extension dir, diffusion_models/__init__.py, and options.ts are byte-identical to upstream again. Fork enhancements survive, adapted to upstream's implementation: presets v2.0 + example config (diffusers-name ignore_if_contains replaces adaln_modulation; sigmoid_scale dropped - unsupported upstream) and the unchanged advisor recipe. Also adds a community 16GB+ KREA2 preset (automagic3, qfloat8, layer offloading).
MiddlePathLabs
pushed a commit
to MiddlePathLabs/ai-toolkit
that referenced
this pull request
Aug 19, 2026
* Add Anima training support * Update Anima modular training * Use sample guidance for Anima * Fix Anima sampling * Limit Anima LoRA targets * Convert Anima LoRA exports * Fix Anima local loading * Update Anima default model * Pin upstream Anima diffusers * Adjust template defaults to be consistent with other models. Update README --------- Co-authored-by: Jaret Burkett (Ostris) <jaretburkett@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds Anima support following the Diffusers support introduced in huggingface/diffusers#13732
Fixes #791
cc @tdrussell