VVladimir Mandiclora: keep parsed network data through pipeline
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
linting Signed-off-by: Vladimir Mandic <mandic00@live.com> | 2 个月前 | |
feat(ltx): add the ltx-2.5 model family 2.5 reuses the LTX-2 pipeline classes, so it is described through the capability table: Gemma 4 text encoder, cross-timestep conditioning, and the upsampler and stage 2 LoRA that now ship inside the model repo. The repo carries the distilled scheduler config, so Dev rows restore the terminal shift, and the Dev transformer sits in transformer_full. Distilled rows stop forcing dynamic shifting on, which remapped their sigma schedule. Auto duration hands the clip length to the duration head. | 1 个月前 | |
fix(ltx): apply the 2.5 stage-2 lora to the text connectors The stage 2 LoRA stores its connector deltas as diffusion_model.{video,audio}_embeddings_connector, but LTX2LoraLoaderMixin.lora_state_dict recognizes connectors only under the 2.3 text_embedding_projection prefix. All 3544 keys are routed into the transformer namespace and peft drops the 224 that land nowhere, leaving refine with a transformer-only adapter. Wrapping lora_state_dict moves those keys onto the connectors component using the rename table from the convert_ltx2_to_diffusers script. The wrapper is inert once no misrouted keys appear, so it needs no version check. | 1 个月前 | |
docs(ltx): correct the refine default comment and stale file references The refine-default comment claimed Condition variants are excluded from two-stage refine, but supports_two_stage_refine has no such carve-out and ltx_process builds a second condition set so conditioning survives the upsample. Two file references had also drifted: ltx_process.py:179 moved, and the offload hook keying now lives in sd_offload_balanced. Name the symbols instead of the line numbers. | 24 天前 | |
docs(ltx): correct the refine default comment and stale file references The refine-default comment claimed Condition variants are excluded from two-stage refine, but supports_two_stage_refine has no such carve-out and ltx_process builds a second condition set so conditioning survives the upsample. Two file references had also drifted: ltx_process.py:179 moved, and the offload hook keying now lives in sd_offload_balanced. Name the symbols instead of the line numbers. | 24 天前 | |
lora: keep parsed network data through pipeline Signed-off-by: Vladimir Mandic <mandic00@live.com> | 6 天前 |