ComfyUI Node Runs on cloud
TripoSplat Conditioning
Encode the image with DINOv3 and the Flux2 VAE into TripoSplat positive/negative conditioning, and create the fixed size noise target (latent + camera) for the KSampler
TripoSplat Conditioning
- clip_vision
- vae
- image
- positive
- negative
- latent
Categorymodel/conditioning/triposplat
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| clip_vision | CLIP_VISION | DINOv3 ViT-H/16+ image encoder | |
| vae | VAE | Flux2 VAE | |
| image | IMAGE | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | The fixed size noise target (latent +camera). |