Latent Upscale Workflow

5.0

1 reviews
24
39.0K
9.8K
4
Description

The latent can be upscaled directly but the loss in quality is important. That means that the second pass after the upscale has to be done at a very high denoise (0.55+).

This option is offered as it's very inexpensive computationally and it can be useful if you don't need the final image to be 100% of the initial generation.

If the final image can be rather different from the first pass, you should use latent upscale as it's faster and very light computationally.

Node Diagram
Discussion

Is it worth to have multiple latent upscales ?

---

The answer is no. Better to get higher scale_by and resample.

(Edited)
G
Go Happya month ago

can I use it online ?

Author

33
368.4K
1.1K
1.2M

Reviews

a

alexmercerzz

7 months ago

Versions (2)

  • - latest (a year ago)

  • - v20240102-075351

Primitive Nodes (2)

Note (2)

Custom Nodes (12)

ComfyUI

  • - CLIPTextEncode (2)

  • - SaveImage (1)

  • - VAEDecode (2)

  • - PreviewImage (1)

  • - LatentUpscaleBy (1)

  • - KSampler (2)

  • - EmptyLatentImage (1)

  • - VAELoader (1)

  • - CheckpointLoaderSimple (1)

Checkpoints (1)

dreamshaper_8.safetensors

LoRAs (0)