FLUX+LORA+ControlnetV3+Refinement
created 8 months ago
img2img
lora
controlnet
upscale
57 nodes

1.6k

322

Credits
I combined Xlabs' controlnetV3 and flux's lora to test the effect with Black Myth Goku's lora, and it was great
Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output optimized_comfy_workflows_user_uploads/d5cfa17d-e557-4a80-b8d9-730c7acaa0ca/assets/ComfyUI_00720_.webp for workflow.
Description

小红书:362973549

!!!(There are some issues with the MATH node after the update, so we need to add the resolution twice in different nodes.)

You need to upgrade to the latest Comfyui, and the nodes that appear can basically be installed directly in the manager

(需要升级到最新的Comfyui,出现的节点基本都可以在manger里面直接安装。)

TEST:

Black Myth Wukong style repainted(黑神话悟空风格转绘)

flux:

https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/main

Xlabs:

https://github.com/XLabs-AI/x-flux

controlnet:

https://huggingface.co/XLabs-AI     (v3)

lora:

https://civitai.com/models/681691

https://drive.google.com/drive/folders/1XOqGPZQccJGAMTITWT4WFfSXQf_xCDSM?usp=sharing

Built-in nodes
CLIPTextEncodeFlux
BasicGuider
ModelSamplingFlux
SamplerCustomAdvanced
RandomNoise
Custom nodes
PreviewImage
VAELoader
FluxLoraLoader
ApplyFluxControlNet
MiDaS-DepthMapPreprocessor
LoadFluxControlNet
XlabsSampler
LatentUpscaleBy
KSamplerSelect
BasicScheduler
CannyEdgePreprocessor
DualCLIPLoader
LoraLoader
ShowText|pysssss
UNETLoader
AutoNegativePrompt
CM_SDXLResolution
HEDPreprocessor
SaveImage
VAEDecode
Upscale Model Loader
ImageUpscaleWithModel
ImageScale
LoadImage
EmptyLatentImage
2
0
0
0