17 lines
1.1 KiB
Markdown
17 lines
1.1 KiB
Markdown
# Example workflows
|
||
|
||
## LTX 2.3 SAM3D BodyMod camera
|
||
|
||
The base LTX 2.3 workflow in [`ltx23_sam3d_bodymod_camera.json`](ltx23_sam3d_bodymod_camera.json) was created by [Mel Massadian (`melMass`)](https://github.com/melMass).
|
||
|
||
Burgstall Labs modified the workflow to add the ComfyUI-SAM3D-BodyMod reference-image shape detection, animated-pose shape application, and keyframed SAM3D camera-drive path. The original workflow authorship remains credited to melMass.
|
||
|
||
The workflow uses Kijai’s [LTX 2.3 SAM3D Body IC-LoRA](https://huggingface.co/Kijai/LTX2-IC-LoRAs/blob/main/ltx23_sam3dbody_v42_restarts-step00004000.comfy.safetensors), published in the [Kijai/LTX2-IC-LoRAs](https://huggingface.co/Kijai/LTX2-IC-LoRAs) model repository.
|
||
|
||
Replace the placeholder media with:
|
||
|
||
- `driver_motion.mp4`: the video whose body motion drives SAM3D.
|
||
- `character_reference.png`: the character image used to detect the replacement body shape.
|
||
|
||
This is an advanced workflow using native ComfyUI SAM3/SAM3D Body and LTX 2.3 nodes plus KJNodes. Select locally available files in its model, LoRA, VAE, and text-encoder loaders; model files and media are not included.
|