Downloads · 30 days
136
3% of all-time downloads
FLUX.2-klein-9B-DF11-ComfyUI
mingyi456/FLUX.2-klein-9B-DF11-ComfyUI
FLUX.2-klein-9B-DF11-ComfyUI is a text-to-image model from mingyi456. Use it when you need an image from a text prompt. It is set up for diffusion-single-file. The card lists the license as other.
All-time downloads
4.4K
Public
Repo size
24.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors24.7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusion-single-file
- License
- other
- Access
- Public
- Created
- Jan 20, 2026
- Updated
- Mar 1, 2026
- SHA
- 7fd2ce09
Base models
Model card
From the Hugging Face model README
Update: After some testing, it seems that the bug with DF11 Klein outputs in ComfyUI is limited to situations where CFG is enabled, meaning that the models without "base" in the name are not affected since they are not meant to be used with CFG. I will continue to look into this issue, sorry for the inconvenience.
Note: It appears to me that the DF11 FLUX.2 [klein] models are bugged, often producing outputs that are slightly different from BF16 outputs. I have confirmed that the DF11 weights are indeed 100% identical to BF16 weights when decompressed, so this should be some bug with inferencing that I am struggling to diagnose. In the meantime, I recommend using the this model with the default KSampler node, instead of the CustomSamplerAdvanced node. Also if you have the VRAM to run this model in BF16, I recommend to use the newly added DFloat11Decompressor node to load this model instead. This node fully decompresses the DF11 weights into BF16 weights, and outputs a model that is 100% identical to the Load Diffusion Model node. I apologize for the inconvenience, as I investigate this issue.
- Task
- Text-to-Image
- Library
- diffusion-single-file
- License
- other
- Languages
- en
- Created
- Jan 20, 2026
- Updated
- Mar 1, 2026