ComfyUI Node
🖼️ LDM VAE Decode
Decodes a latent tensor back into pixel space using the f8 VAE decoder. The latent is divided by the training scale factor (0.18215 for f8 VAE) before decoding. If the output appears too dark or washed out, adjust vae_scale. Output: IMAGE tensor in [0, 1] range, BHWC layout.
🖼️ LDM VAE Decode
- samples
- vae
- IMAGE
◄vae_scale0.1822►
CategoryLDM
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| samples | LDM_LATENT | Latent tensor from the Sampler node. | |
| vae | LDM_VAE | VAE output from Load LDM Checkpoint. | |
| vae_scale | FLOAT | 0.18220.01–1 | Latent scaling factor. Standard f8 VAE value is 0.18215. Adjust if output brightness looks incorrect. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |