ComfyUI Node
VAE Decode (Batched)
Same as the built-in VAE Decode, but adds a batch_size field that controls how many latents are decoded by the VAE at once. Decoding fewer at a time (e.g. 1) can lower peak VRAM and speed things up.
VAE Decode (Batched)
- samples
- vae
- IMAGE
◄batch_size1►
CategoryvsLinx/latent
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| samples | LATENT | The latent to be decoded. | |
| vae | VAE | The VAE model used for decoding the latent. | |
| batch_size | INT | 11–4096 | How many latents to hand to the VAE per decode call. Lower values reduce peak VRAM at the cost of more sequential calls; the default of 1 decodes one image at a time. Values >= the batch size behave exactly like the built-in node (single decode). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | The decoded image. |