anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/offline_inference/image_to_video/README.md
+2 -2
View File
@@ -237,7 +237,7 @@ 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" \
@@ -252,7 +252,7 @@ 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.
examples/offline_inference/image_to_video/image_to_video.py
+1 -1
View File
@@ -29,7 +29,7 @@ Usage:
--frame-rate 24 --fps 24 --output ltx2_i2v.mp4
# LTX-2.3 image-to-video
python image_to_video.py --model dg845/LTX-2.3-Diffusers \
python image_to_video.py --model diffusers/LTX-2.3-Diffusers \
--model-class-name LTX23ImageToVideoPipeline \
--image input.jpg --prompt "A cinematic dolly shot of a boat" \
--height 384 --width 512 --num-frames 25 --num-inference-steps 20 \
examples/offline_inference/text_to_video/text_to_video.md
+3 -3
View File
@@ -8,7 +8,7 @@ A unified script for text-to-video generation. Supports multiple models with mod
|---|---|---|---|---|---|
| `Wan-AI/Wan2.1-VACE-1.3B-diffusers` | 480x832 | 81 | 30 | 5.0 | ~20 GiB (RTX 5090, VAE tiling) |
| `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | 720x1280 | 81 | 40 | 4.0 | ~60 GiB |
| `dg845/LTX-2.3-Diffusers` | 384x512 | 25 | 20 | 4.0 | 96GB-class GPU |
| `diffusers/LTX-2.3-Diffusers` | 384x512 | 25 | 20 | 4.0 | 96GB-class GPU |
| `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v` | 480x832 | 121 | 50 | 6.0 | 1×A100 80GB |
| `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | 720x1280 | 121 | 50 | 6.0 | FP8 + VAE tiling required |
| `nvidia/Cosmos3-Nano` | 720x1280 | 189 | 35 | 6.0 | ~46 GiB (peak, 720p) |
@@ -75,7 +75,7 @@ python text_to_video.py \
```bash
python text_to_video.py \
--model dg845/LTX-2.3-Diffusers \
--model diffusers/LTX-2.3-Diffusers \
--model-class-name LTX23Pipeline \
--prompt "Cherry blossoms swaying gently in the breeze with synchronized ambient sound" \
--negative-prompt "worst quality, inconsistent motion, blurry, jittery, distorted" \
@@ -90,7 +90,7 @@ python text_to_video.py \
--output ltx23_t2v_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 LTX23Pipeline` to select the LTX-2.3
text-to-video pipeline explicitly.