ComfyUI Workflow for Flux.2 Klein
Any feedback would be appreciated.
📂 Required Models
Diffusion Model: flux2-klein-4b or any of the other versions .../ComfyUI/models/diffusion_models/
Text Encoder: qwen_3__4b or qwen_3__8b .../ComfyUI/models/text_encoders/
VAE: flux2-vae .../ComfyUI/models/vae/
🧩 Required Custom Nodes
🟩 ComfyUI-Manager (by Comfy-Org)
https://github.com/Comfy-Org/ComfyUI-Manager🟩 rgthree-comfy (by rgthree)
https://github.com/rgthree/rgthree-comfy🟩 ComfyUI-GGUF (by city96)
https://github.com/city96/ComfyUI-GGUF
⚙️ Recommended Settings
Steps: 4 (distilled)
CFG: 1.0 (distilled)
Sampler: Euler
Experiment and enjoy!
Description
Upload of V1.0
(This is not an exhaustive changelog)
Added V1.0:
flux2_klein_image_edit
FAQ
Comments (4)
Keep up the good work!
Wanted to comment on this, because it really looks simple - exactly like the workflows from https://civitai.com/user/UmeAiRT/
It's really something good for us, normal folks coming from Automatic1111 to comfyui and don't know that much about it.
Seeing clean workflows and not 1000 spaghetti nodes in 100 different places is encouraging for comfyui noobs :)
Works great for 4B, but doesn't seem to work with 9B:
SamplerCustomAdvanced
mat1 and mat2 shapes cannot be multiplied (512x7680 and 12288x4096)
For Klein 9B, you need to use qwen_3_8b instead of 4b.
Could we please get an upscaler in the next version, its great BTW <3