indigo/LTX-2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Automated PR - 2026-03-04

Browse Source
This commit is contained in:
sync-bot
2026-03-04 19:34:46 +00:00
parent 28c3c73fe5
commit 822ce3c4b1
73 changed files with 4984 additions and 1220 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+5 -2
View File
@@ -63,15 +63,18 @@ Download the following models from the [LTX-2 HuggingFace repository](https://hu
### Available Pipelines
* **[TI2VidTwoStagesPipeline](packages/ltx-pipelines/src/ltx_pipelines/ti2vid_two_stages.py)** - Production-quality text/image-to-video with 2x upsampling (recommended)
* **[TI2VidTwoStagesRes2sPipeline](packages/ltx-pipelines/src/ltx_pipelines/ti2vid_two_stages_res2s.py)** - Same two-stage flow as above but uses the res_2s second-order sampler (fewer steps, different quality/speed trade-off)
* **[TI2VidOneStagePipeline](packages/ltx-pipelines/src/ltx_pipelines/ti2vid_one_stage.py)** - Single-stage generation for quick prototyping
* **[DistilledPipeline](packages/ltx-pipelines/src/ltx_pipelines/distilled.py)** - Fastest inference with 8 predefined sigmas
* **[ICLoraPipeline](packages/ltx-pipelines/src/ltx_pipelines/ic_lora.py)** - Video-to-video and image-to-video transformations
* **[ICLoraPipeline](packages/ltx-pipelines/src/ltx_pipelines/ic_lora.py)** - Video-to-video and image-to-video transformations (uses distilled model.)
* **[KeyframeInterpolationPipeline](packages/ltx-pipelines/src/ltx_pipelines/keyframe_interpolation.py)** - Interpolate between keyframe images
* **[A2VidPipelineTwoStage](packages/ltx-pipelines/src/ltx_pipelines/a2vid_two_stage.py)** - Audio-to-video generation conditioned on an input audio file
* **[RetakePipeline](packages/ltx-pipelines/src/ltx_pipelines/retake.py)** - Regenerate a specific time region of an existing video
### ⚡ Optimization Tips
* **Use DistilledPipeline** - Fastest inference with only 8 predefined sigmas (8 steps stage 1, 4 steps stage 2)
* **Enable FP8 transformer** - Enables lower memory footprint: `--enable-fp8` (CLI) or `fp8transformer=True` (Python)
* **Enable FP8 quantization** - Enables lower memory footprint: `--quantization fp8-cast` (CLI) or `quantization=QuantizationPolicy.fp8_cast()` (Python). For Hopper GPUs with TensorRT-LLM, use `--quantization fp8-scaled-mm` for FP8 scaled matrix multiplication.
* **Install attention optimizations** - Use xFormers (`uv sync --extra xformers`) or [Flash Attention 3](https://github.com/Dao-AILab/flash-attention) for Hopper GPUs
* **Use gradient estimation** - Reduce inference steps from 40 to 20-30 while maintaining quality (see [pipeline documentation](packages/ltx-pipelines/README.md#denoising-loop-optimization))
* **Skip memory cleanup** - If you have sufficient VRAM, disable automatic memory cleanup between stages for faster processing