ComfyUI Node
FunUI Decode
Decode a latent to images, and to audio when the model has any.
FunUI Decode
- samples
- vae
- model
- audio_vae
- images
- audio
- status
◄tile_size0►
CategoryFunUI/Output
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| samples | LATENT | — | |
| vae | VAE | The picture VAE. | |
| modelopt | MODEL | The model this latent came from. Needed only when a model has its own way of being decoded. | |
| audio_vaeopt | VAE | Only for models that generate sound alongside the video. | |
| tile_sizeopt | INT | 00–4096 | Decode in tiles of this many pixels, to fit less VRAM. 0 = the model's own way. MiniMax H3: 0 is ComfyUI's 256px tiles, the size its decoder was trained on; bigger tiles show a grid. An X2 Detail VAE is always tiled (256 at least). |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| audio | AUDIO | — |
| status | STRING | — |