videolora training
LTX Video 13B Distilled
13B distilled LTX blending text, image, and video inputs with extend, LoRA, and 720p options.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 4
- Eligible
- 4
- Input schemas imported
- 4 / 4
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
LTX Video-0.9.7 13B Distilled blends prompts with image and video inputs for multi-conditional transformation and video-to-video generation. Extend, image-to-video, and multiconditioning endpoints join the base model. Output spans 480p and 720p with custom LoRA integration plus configurable frame rates and compression.
Capabilities
- 13B multi-conditional architecture
- Text plus image plus video blending
- Clip extension endpoint
- Custom LoRA integration
Best for
- Footage transformation
- Artistic style application
- Hybrid compositions
Use cases
- Complex creative workflows
- Style-locked v2v passes
- Resolution-flexible delivery
Endpoints
4 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/ltx-video-13b-distilled | video editing | Eligible | 17 fields · requires prompt |
fal-ai/ltx-video-13b-distilled/extend | video editing | Eligible | 19 fields · requires prompt, video |
fal-ai/ltx-video-13b-distilled/image-to-video | image to video | Eligible | 19 fields · requires prompt, image_url |
fal-ai/ltx-video-13b-distilled/multiconditioning | video editing | Eligible | 20 fields · requires prompt |
Questions
Which inputs combine?
Text prompts with image and video together.
Custom styles?
Custom LoRA integration for control.