Readme: Add official Control Models
This commit is contained in:
45
README.md
45
README.md
@@ -2,14 +2,14 @@
|
||||
|
||||
# LTX-Video
|
||||
|
||||
This is the official repository for LTX-Video.
|
||||
[](https://www.lightricks.com/ltxv)
|
||||
[](https://huggingface.co/Lightricks/LTX-Video)
|
||||
[](https://app.ltx.studio/motion-workspace?videoModel=ltxv-13b)
|
||||
[](https://arxiv.org/abs/2501.00103)
|
||||
[](https://github.com/Lightricks/LTX-Video-Trainer)
|
||||
[](https://discord.gg/Mn8BRgUKKy)
|
||||
|
||||
[Website](https://www.lightricks.com/ltxv) |
|
||||
[Model](https://huggingface.co/Lightricks/LTX-Video) |
|
||||
[Demo](https://app.ltx.studio/motion-workspace?videoModel=ltxv-13b) |
|
||||
[Paper](https://arxiv.org/abs/2501.00103) |
|
||||
[Trainer](https://github.com/Lightricks/LTX-Video-Trainer) |
|
||||
[Discord](https://discord.gg/Mn8BRgUKKy)
|
||||
This is the official repository for LTX-Video.
|
||||
|
||||
</div>
|
||||
|
||||
@@ -28,6 +28,7 @@ This is the official repository for LTX-Video.
|
||||
- [Model User Guide](#model-user-guide)
|
||||
- [Community Contribution](#community-contribution)
|
||||
- [Training](#training)
|
||||
- [Control Models](#control-models)
|
||||
- [Join Us!](#join-us-)
|
||||
- [Acknowledgement](#acknowledgement)
|
||||
|
||||
@@ -47,8 +48,24 @@ The model supports image-to-video, keyframe-based animation, video extension (bo
|
||||
|  |  |  |
|
||||
|  |  |  |
|
||||
|
||||
### Controlled video examples
|
||||
| | | |
|
||||
|:---:|:---:|:---:|
|
||||
|  |  |  |
|
||||
|
||||
| | |
|
||||
|:---:|:---:|
|
||||
|  |  |
|
||||
|
||||
# News
|
||||
|
||||
## July, 8th, 2025: New Control Models Released!
|
||||
- Released three new control models for LTX-Video on HuggingFace:
|
||||
* **Depth Control**: [LTX-Video-ICLoRA-depth-13b-0.9.7](https://huggingface.co/Lightricks/LTX-Video-ICLoRA-depth-13b-0.9.7)
|
||||
* **Pose Control**: [LTX-Video-ICLoRA-pose-13b-0.9.7](https://huggingface.co/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7)
|
||||
* **Canny Control**: [LTX-Video-ICLoRA-canny-13b-0.9.7](https://huggingface.co/Lightricks/LTX-Video-ICLoRA-canny-13b-0.9.7)
|
||||
|
||||
|
||||
## May, 14th, 2025: New distilled model 13B v0.9.7:
|
||||
- Release a new 13B distilled model [ltxv-13b-0.9.7-distilled](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-distilled.safetensors)
|
||||
* Amazing for iterative work - generates HD videos in 10 seconds, with low-res preview after just 3 seconds (on H100)!
|
||||
@@ -162,7 +179,7 @@ python -m pip install -e \[inference\]
|
||||
|
||||
### Inference
|
||||
|
||||
📝 **Note:** For best results, we recommend using our [ComfyUI](#comfyui-integration) workflow. We’re working on updating the inference.py script to match the high quality and output fidelity of ComfyUI.
|
||||
📝 **Note:** For best results, we recommend using our [ComfyUI](#comfyui-integration) workflow. We're working on updating the inference.py script to match the high quality and output fidelity of ComfyUI.
|
||||
|
||||
To use our model, please follow the inference code in [inference.py](./inference.py):
|
||||
|
||||
@@ -290,11 +307,21 @@ please let us know by opening an issue or pull request.
|
||||
# ⚡️ Training
|
||||
|
||||
We provide an open-source repository for fine-tuning the LTX-Video model: [LTX-Video-Trainer](https://github.com/Lightricks/LTX-Video-Trainer).
|
||||
This repository supports both the 2B and 13B model variants, enabling full fine-tuning as well as LoRA (Low-Rank Adaptation) fine-tuning for more efficient training.
|
||||
This repository supports both the 2B and 13B model variants, enabling full fine-tuning as well as LoRA (Low-Rank Adaptation) fine-tuning for more efficient training. This includes:
|
||||
|
||||
- **Control LoRAs**: Train custom control models like depth, pose, and canny control
|
||||
- **Effect LoRAs**: Create specialized effects and transformations for video generation
|
||||
|
||||
Explore the repository to customize the model for your specific use cases!
|
||||
More information and training instructions can be found in the [README](https://github.com/Lightricks/LTX-Video-Trainer/blob/main/README.md).
|
||||
|
||||
# 🎬 Control Models
|
||||
|
||||
[ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo) repository now contains workflows and models for 3 specialized models that enable precise control over LTX-Video generation:
|
||||
|
||||
Pose Control, Depth Control and Canny Control
|
||||
|
||||
**Example ComfyUI Workflow (for all control types):** [ic-lora.json](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/main/example_workflows/ic_lora/ic-lora.json)
|
||||
|
||||
# 🚀 Join Us
|
||||
|
||||
|
||||
3
docs/_static/ltx-video_ic_2v_example_00000.gif
vendored
Normal file
3
docs/_static/ltx-video_ic_2v_example_00000.gif
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a70c182ecf7477a8e291f89559b9ddd6bd1cb87aa41fc286c0d5fa853fbf64d7
|
||||
size 37147005
|
||||
3
docs/_static/ltx-video_ic_2v_example_00001.gif
vendored
Normal file
3
docs/_static/ltx-video_ic_2v_example_00001.gif
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cff7d1c49f4e51ff29e670eda111d1947702b5ffd51a9ac89fd2b539a8a2ebcf
|
||||
size 77564878
|
||||
3
docs/_static/ltx-video_ic_2v_example_00002.gif
vendored
Normal file
3
docs/_static/ltx-video_ic_2v_example_00002.gif
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:220ecd1cffe3badecd573e7ad3c954b872bea7ecbafecedaafb11b40f791bde1
|
||||
size 32596519
|
||||
3
docs/_static/ltx-video_ic_2v_example_00003.gif
vendored
Normal file
3
docs/_static/ltx-video_ic_2v_example_00003.gif
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57d4e848a3dc76e2b1a8b2562ae5c213399d5aeb98587cc8d9a21faefc470ead
|
||||
size 32318190
|
||||
3
docs/_static/ltx-video_ic_2v_example_00004.gif
vendored
Normal file
3
docs/_static/ltx-video_ic_2v_example_00004.gif
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac7a88e756ad15e04f645f69b3d8b4b0f2dd61a7ee39924f18f63ddfc8a926bf
|
||||
size 10254972
|
||||
Reference in New Issue
Block a user