ComfyUI-LTXVideo
ComfyUI-LTXVideo copied to clipboard
For improved readability and UX, it is suggested to present the news content using a Markdown table.
like this:
| Model Name | Version | Size | Steps | Description | Download Link |
|---|---|---|---|---|---|
| LTXV 13B Distilled 🥳 | 0.9.7 | 28GB | 4~8steps | Delivers cinematic-quality videos with only 4 or 8 steps needed for generation. | Download |
| LTXV 13B Distilled-FP8 | 0.9.7 | 15.7 GB | 4~8steps | Offers reduced memory requirements and faster inference speeds, ideal for consumer-grade GPUs (e.g., NVIDIA 4090, 5090). Important: In order to get the best performance with the quantized version please install q8_kernels package and use dedicated flow below. |
Download |
| LTV 13B-FP8 | Latest | 28.6 GB | 25steps | All 8-bit quantized models now run natively in ComfyUI; use the Q8 patcher node for best performance. |
Download |