Upscaling with Ultimate SD Upscale，Tile Controlnet SD Upscale & Anima Models
基于 Ultimate SD Upscale , Tile Controlnet 和 Anima 模型的放大工作流
This is USDU workflow with tile conrtolnet lite.
Thanks @L_A_X for the tile Controlnet
Thanks Lebensignal for custom USDU node.
Get the Anima Tile ControlNet LLLite model here:
https://civarchive.com/models/2708551/anima-tile-and-repair-controlnet-lllite
Get the Anima-LLLite node here:
https://github.com/kohya-ss/ComfyUI-Anima-LLLite
Or install it via ComfyUI-Manager.
Get the updated USDU node here:
https://github.com/shiranpp/ComfyUI-UltimateSDUpscale-FLS-LLLite
Or install it via ComfyUI-Manager, then apply the following patch:
https://github.com/shiranpp/ComfyUI-UltimateSDUpscale-FLS-LLLite/commit/815b2c5d0d1ad0b18494dd9b37bff31b2e2ba3d9
Parameters:
Prompt: Use the original image prompt, or simply use quality and style prompts with lower Denoising and higher LLLite Strength.
Denoising: Recommended range is 0.25–0.75.
Steps: Adjust according to the Denoising strength. Typically, 8–20 steps are sufficient.
Sampler: er_sde is recommended.
ControlNet Strength: 0.6–1.0.
ControlNet End: 0.6–1.0.
获取 Anima Tile ControlNet LLLite model：
https://civarchive.com/models/2708551/anima-tile-and-repair-controlnet-lllite
获取 Anima-LLLite node：
https://github.com/kohya-ss/ComfyUI-Anima-LLLite
也可以通过 ComfyUI-Manager 安装。
获取新版 USDU node：
https://github.com/shiranpp/ComfyUI-UltimateSDUpscale-FLS-LLLite
也可以通过 ComfyUI-Manager 安装，安装后需要应用以下 patch：
https://github.com/shiranpp/ComfyUI-UltimateSDUpscale-FLS-LLLite/commit/815b2c5d0d1ad0b18494dd9b37bff31b2e2ba3d9
Parameters：
Prompt：使用原图的 Prompt，或者仅使用 Quality 和 Style Prompt，同时降低 Denoising 并提高 LLLite Strength。
Denoising：推荐范围为 0.25–0.75。
Steps：根据 Denoising Strength 调整，通常推荐 8–20 Steps。
Sampler：推荐使用 er_sde。
ControlNet Strength：0.6–1.0。
ControlNet End：0.6–1.0。
Update Log
- 26/04/12: Version 1.1 updated to preview3.
- 26/04/18: Version 1.1 added a Lora loader and adjusted parameters;
- 26/05/14: Version 1.2 introduced the following QoL (Quality of Life) nodes:
- Auto tile sizing
- Comparison preview
- Save with metadata
- 26/06/21: Version 1.2a adjusted baseline parameters for improved default performance.
- 26/06/21: add first controlnet tile upscale experimental workflow
- 26/06/24: moved to Lebensignal's USDU node that support controlnet lllite
- 26/11/03: 1.3.1 minor QOL update
Description
moved to USDU node by Lebensignal that supports controlnet lllite
FAQ
Comments (14)
May I ask, at this stage, is there no similar workflow for Tiled Diffusion like sdxl? The USDU speed is a bit slow.
https://github.com/syntax-one/ComfyUI-Tiled-Diffusion-Anima-Fix. and it is still slow since it just tiled the image in latent compare to tiling image in pixel in USDU/image tile node. u also need to mod the node ur self if u want to use lllite.
@CptCharname oh! thanks! I try it.
谢谢大佬的工作流，我想了解一下有没有anima关于深度图控制和姿势控制的工作流呢？
@CptCharname thank you！！！！
请问target_size 这个是填写原图片的边长吗
分块的大小，直接改USDU里面放大倍率就行了。
@CptCharname 我发现有时候在放大最后一块的时候会出问题，会乱生成一些东西，我原图是832x1216 0.6的重绘幅度 cn强度 0.55
@lingmo 不知道你说的最后一块是什么，你要觉得不符合原图就把cn强度改到0.8-0.9
Ultimate SD Upscale (FLS + LLLite Tile Repair) failed
This node threw an error during execution. Check its inputs or try a different configuration.
post error message here or just post it to AI.
为啥我怎么都跑不起来
用远在Ultimate SD Upscale (FLS + LLLite Tile Repair)
这一步报错,说我缺失了什么东西
发下error message