rRealisMAX X FLUX . Just your another FLUX Checkpoint focused on Asian beauty with slightly better 'anatomy'
this model is EXCLUSIVE for tensor.art for generated service, you can download the model and run in local or other service
just don't reprint.
based on rRealisMAX FLUX + Trained LoRA with dataset focused on Asian image
full model using this clip :
Text Encoders: https://huggingface.co/silveroxides/CLIP-Collection/blob/main/t5xxl_flan_latest-fp8_e4m3fn.safetensors
Recommendation
Sampler: Euler beta
Sampler steps: 20-60
Guidance Scale: 2.5 for realistic, 3.5 default, 5 anime
This model falls under the FLUX.1 [dev] Non-Commercial License
Description
rRealisMAX X V3 :
+ add other ethnicity
if you prefer Asian, use V2 instead .
+ refine some anatomy (again)
- yet still not able to do variety of style and may not compatible with some LoRA