Flux 2 Klein 4B Base Gay Bara
A model fine-tuned on gay/bara artworks and male photography for image generation only.
Image-caption pairs were generated using a vision-language model whose descriptions naturally tend toward neutral, generalized language. Captions use clean descriptive vocabulary that remains platform-friendly.
Description
FAQ
Comments (5)
Looks good but dont know how to use it, any recommand settings or workflows on comfyui?
Use the same way how you would run FLUX.2-klein-base-4B but replace the safetensor in the transformer with this one. The model is still a work-in-progress, trained on illustrations and later on photos.
@One_One sadly I did not use Flux before. I usually use ILL\pony\zimage. My GPU is RTX4060TI 8gb
I am unable to load it ☹
ComfyUI/comfy/model_detection.py", line 1256, in convert_diffusers_mmdit
hidden_size = state_dict["x_embedder.bias"].shape[0]
KeyError: 'x_embedder.bias
Same error on my end. Will delete this for now.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.