Base model and placeholder for showcasing nice image creations @ the edge of the actual Flux capabilities.

v3.0 uses its own way to generate images - fewer steps, other samplers and cfg ne 1

impatiens demanda

v2.0 is not intended to generate NSFW content!

quid variabilis est variabilis

Parameters used:

Workspace: ComfyUI

Model precision: fp8, Decoders: fp16

ViT-L-14-TEXT-detail-improved-hiT-GmP-HF.safetensors from

https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/tree/main

Sampler1: euler, sgm_uniform, 25 steps, guidance 3.3

Sampler2: dpm_pp_2s_ancestral, beta, 16 steps, guidance 3.3