> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-comfy-docs-comfyapi-search.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# TripoSplatConditioning - ComfyUI Built-in Node Documentation

> This node encodes an input image with the DINOv3 image encoder and the Flux2 VAE to produce positive and negative conditioning data for the TripoSplat model.

This node encodes an input image with the DINOv3 image encoder and the Flux2 VAE to produce positive and negative conditioning data for the TripoSplat model. It also creates a fixed-size noise target (latent plus camera data) that serves as the starting point for the KSampler.

## Inputs

| Parameter     | Description                    | Data Type    | Required | Range |
| ------------- | ------------------------------ | ------------ | -------- | ----- |
| `clip_vision` | DINOv3 ViT-H/16+ image encoder | CLIP\_VISION | Yes      | -     |
| `vae`         | Flux2 VAE                      | VAE          | Yes      | -     |
| `image`       | The input image to encode      | IMAGE        | Yes      | -     |

## Outputs

| Output Name | Description                                                                                                                                                              | Data Type    |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ |
| `positive`  | Positive conditioning data containing the DINOv3 feature sequence and the Flux2 VAE latent carried as a reference latent                                                 | CONDITIONING |
| `negative`  | Negative conditioning data containing zero-filled DINOv3 features and a zero-filled Flux2 VAE reference latent                                                           | CONDITIONING |
| `latent`    | The fixed size noise target (latent + camera) for the KSampler. The latent is a constant-shape shape-code sequence (8192 x 16) paired with a single camera token (1 x 5) | LATENT       |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoSplatConditioning/en.md)

***

**Source fingerprint (SHA-256):** `59ebeef272d125a2cc2045f4ff54f99268b1273d0a1fd46f7462e6d312f3a805`