Sign In

SD XL - DPO Finetune (Direct Preference Optimization)

Download

1 variant available

fp16 SafeTensor

sd_xl_dpo-text2image-v1-unet_0.9vae.safetensors

Half precision, best balance • 6.46 GB

Verified:

Type
Checkpoint Trained
Stats

803

15

Reviews
Published

Dec 20, 2023

Base Model

SDXL 1.0

Hash
AutoV2
A3F62BBB37
default creator card background decoration
Uploads - 18

18

Downloads - 24837

24.8K

Generations - 309972

310K

ComfyUI_00155_.png

SD XL finetuned with Direct Preference Optimization. Tested and working with both ComfyUI and Automatic1111 WebUI.

Credit goes to the fine-tune here: https://huggingface.co/mhdang/dpo-sdxl-text2image-v1. See the Huggingface page for more details.

Text Encoder and VAE from SD XL v1.0 VAE Fix [E6BB9EA85B] https://civitai.com/models/101055/sd-xl

The U-Net of this model (ComfyUI-only model here: https://civitai.com/models/237681/dpo-sdxl-fp16) has been converted into a format compatible with both A1111 and ComfyUI using this tool: https://github.com/arenasys/stable-diffusion-webui-model-toolkit