[Refactor] Unify the LTX-2 and LTX-2.3 pipeline runtime (#5147)

Signed-off-by: mglyn <1203789601@qq.com>
This commit is contained in:
Mu GuanLin authored and GitHub committed 2026-07-20 20:02:30 +08:00
1 parent 6cd1ff7e64
commit a06664a243
36 files changed
+3886 -4835

No files matched your search

@@ -57,7 +57,7 @@ python image_to_video.py \
```bash
python image_to_video.py \
--model dg845/LTX-2.3-Diffusers \
--model diffusers/LTX-2.3-Diffusers \
--model-class-name LTX23ImageToVideoPipeline \
--image cherry_blossom.jpg \
--prompt "Cherry blossoms swaying gently in the breeze with synchronized ambient sound" \
@@ -72,7 +72,7 @@ python image_to_video.py \
--output ltx23_i2v_output.mp4
```
Use a Diffusers-format checkpoint such as `dg845/LTX-2.3-Diffusers`; the
Use the Diffusers-format checkpoint `diffusers/LTX-2.3-Diffusers`; the
upstream `Lightricks/LTX-2.3` raw safetensors repo is not directly loadable by
this pipeline. Pass `--model-class-name LTX23ImageToVideoPipeline` to select
the LTX-2.3 image-to-video pipeline.