CCalamitousFelicitousnessfix(pipelines): restore clip-skip text encoding for transformers 5.6+
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
fix(control-units): list zimage controlnets under 'all'; fix LLLite output-block fall-through api_list_models omitted the 'or model_type == all' clause for zimage, so ZImage ControlNets never appeared in the all listing - added it to match every other family. lite_model used pass for the unimplemented root==output branch, which fell through to b = getattr(b, attn_name) with b unbound or stale from a prior iteration (UnboundLocalError or wrong-block patch); use continue to skip it. Co-Authored-By: Claude <noreply@anthropic.com> | 3 个月前 | |
zimage-controlnet-union initial code Signed-off-by: vladmandic <mandic00@live.com> | 8 个月前 | |
more pylint fixes Co-authored-by: Copilot <copilot@github.com> Signed-off-by: Vladimir Mandic <mandic00@live.com> | 4 个月前 | |
fix(control-units): list zimage controlnets under 'all'; fix LLLite output-block fall-through api_list_models omitted the 'or model_type == all' clause for zimage, so ZImage ControlNets never appeared in the all listing - added it to match every other family. lite_model used pass for the unimplemented root==output branch, which fell through to b = getattr(b, attn_name) with b unbound or stale from a prior iteration (UnboundLocalError or wrong-block patch); use continue to skip it. Co-Authored-By: Claude <noreply@anthropic.com> | 3 个月前 | |
extend use of move_model | 2 年前 | |
more pylint fixes Co-authored-by: Copilot <copilot@github.com> Signed-off-by: Vladimir Mandic <mandic00@live.com> | 4 个月前 | |
more pylint fixes Co-authored-by: Copilot <copilot@github.com> Signed-off-by: Vladimir Mandic <mandic00@live.com> | 4 个月前 | |
full codespell coverage Signed-off-by: Vladimir Mandic <mandic00@live.com> | 3 个月前 | |
fix(pipelines): restore clip-skip text encoding for transformers 5.6+ The vendored encode_prompt copies in the PAG, APG, ControlNet-XS and differential diffusion pipelines dereference the .text_model wrapper that transformers 5.6 removed from CLIPTextModel, so their clip-skip path crashes on SD1.5 and SDXL TE1. Apply the same getattr(te, 'text_model', te) fix as the core parser. Mirrors upstream diffusers, which still carries this deref in pipeline encode_prompt; only the single-file loader was fixed there. | 2 个月前 |