ComfyUI Node Runs on cloud
Make Training Dataset
Encode images with VAE and texts with CLIP to create a training dataset of latents and conditionings.
Make Training Dataset
- images
- vae
- clip
- latents
- conditioning
◄texts—►
Categorymodel/training
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| images | IMAGE | List of images to encode. | |
| vae | VAE | VAE model for encoding images to latents. | |
| clip | CLIP | CLIP model for encoding text to conditioning. | |
| textsopt | STRING | List of text captions. Can be length n (matching images), 1 (repeated for all), or omitted (uses empty string). |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| latents | LATENT | List of latent dicts |
| conditioning | CONDITIONING | List of conditioning lists |