accept t5xxl style prompts
training performed on a large dataset with llm-generated captions on the base dpo sd1.5 model
may produce NSFW material
Description
t5xxl
base model
distillate
big models reduction
dpo
flux1.d
midjourney
base models
experimental
high quality
sd3.5
Details
Downloads
697
Platform
CivitAI
Platform Status
Available
Created
11/13/2024
Updated
1/9/2026
Deleted
-
Files
sd15HK_v075.safetensors
Mirrors
Huggingface (2 mirrors)
CivitAI (1 mirrors)