






All images I experimented on ComfyUI. You can just simply use my images for nodes and workflows.
Do not generate ???? contents from this model.
Here are models that I used: flux-1dev, fp8_e4m3fn, t5xxl_fp16, and the original vae Flux
Use Flux sentence-style prompts.
no trigger words required
Lora weight between 0.90-1.00
scheduler: sgm_uniform with sampler: Euler
you can place prompts only in t5xxl box and leave clip_1 empty even though a DualClipLoader is used
max_shift: 1.15
base_shift: 0.50
Steps: 20 or 50
denoise: 1.00
Share your creations here and give some suggestions for whom you'd like me to make a LoRA model of.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
