ComfyUI Node
💪TB | Tiny Encode
Encode an image into a latent representation using the provided VAE. This node optimizes memory usage by dividing the process into smaller tiles.
💪TB | Tiny Encode
- image
- vae
- latent
◄tile_size512px►
◄overlap100%►
Category💪TinyBreaker/latent
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | The image to be encoded to a latent representation. | |
| vae | VAE | The VAE model used for encoding the image. | |
| tile_size | COMBO | 512px | The size of the tiles used to divide the image into smaller regions for processing, expressed in pixels of the input image. A lower tile size reduces memory usage but may result in lower image quality. |
| overlap | COMBO | 100% | The percentage of overlap between adjacent tiles. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| latent | LATENT | Latent representation of the input image. |