The trigger word is not required. The recommended scale is 0.6 to 0.8 in diffusers. The generated character costumes will have a fluid metallic texture. The image is accompanied by some magical or technological light effects. It tends to generate images with a dark atmosphere.

You can also run this model at Shakker AI, where we provide an online interface to generate images.

This model is trained by our copyrighted users GUIZANG(歸藏). We release this model under permissions. The model follows flux-1-dev-non-commercial-license.