Latent Upscale Workflow

5.0

1 reviews
28
49.2K
11.5K
5
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
insect_animated_566 months ago

Is it worth to have multiple latent upscales ?

---

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

(Edited)
G
Go Happy6 months ago

can I use it online ?

M
Marcio - BoredWhy2 months ago

嗨!

我是 BoredWhy 的 Marcio。

您的这个工作流程真是太棒了!我们已将其在 BoredWhy 上线,方便大家体验和使用。希望您不介意!

请点击这里查看:https://boredwhy.com/workflow/6835daacb2ca8c82608a7714

当然,所有的功劳都归您所有!


-----------------


Hey there! Marcio from BoredWhy here.

Super cool workflow! We've put it online for people to easily try out on BoredWhy – hope you don't mind!

Check it out here: https://boredwhy.com/workflow/6835daacb2ca8c82608a7714

And of course, full credit goes to you!

Author

33
445.7K
1.2K
1.5M

Reviews

a

alexmercerzz

a year ago

Versions (2)

  • - latest (2 years 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)