Diffus
Get started
models/DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++ - SDXL - V1.0

DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++ - SDXL - V1.0

enfugue
|
7/26/2025
|
3:07:16 AM
| Discussion|
0
A female warrior clad in silver armor stands in a forest holding a glowing sword and a blue shield with red emblem.
Macro shot of an extraterrestrial creature with iridescent blue and green feathers, large expressive eyes, and glowing bioluminescent highlights, perched on a red alien plant.
Young woman with blonde pixie haircut sitting on a red armchair wearing a school uniform with a red tie in a living room setting with plants and red curtains.
A detailed Neo-Byzantine style circular mosaic featuring ruby, sapphire, amethyst, and gold elements in an intricate floral and fractal pattern with silver leaves.
A sharp mountain peak silhouetted against a fiery orange sunset sky, reflected in a clear lake with visible rocks beneath the surface.
Colorful cute robot character with multiple arms, generated using Stable Diffusion AI.
A mountain temple surrounded by misty peaks and calm waters, AI generated using Stable Diffusion.

Recommended Prompts

RAW photo, a close-up picture of a cat, a close-up picture of a dog, orange eyes, blue eyes, reflection in it's eyes

Recommended Parameters

samplers

DPM2

steps

25

cfg

5

Creator Sponsors

What is DPO?

DPO is Direct Preference Optimization, the name given to the process whereby a diffusion model is finetuned based on human-chosen images. Meihua Dang et. al. have trained Stable Diffusion 1.5 and Stable Diffusion XL using this method and the Pick-a-Pic v2 Dataset, which can be found at https://huggingface.co/datasets/yuvalkirstain/pickapic_v2, and wrote a paper about it at https://huggingface.co/papers/2311.12908.

What does it Do?

The trained DPO models have been observed to produce higher quality images than their untuned counterparts, with a significant emphasis on the adherence of the model to your prompt. These LoRA can bring that prompt adherence to other fine-tuned Stable Diffusion models.

Who Trained This?

These LoRA are based on the works of Meihua Dang (https://huggingface.co/mhdang) at

https://huggingface.co/mhdang/dpo-sdxl-text2image-v1 and https://huggingface.co/mhdang/dpo-sd1.5-text2image-v1, licensed under OpenRail++.

How were these LoRA Made?

They were created using Kohya SS by extracting them from other OpenRail++ licensed checkpoints on CivitAI and HuggingFace.

1.5: https://civitai.com/models/240850/sd15-direct-preference-optimization-dpo extracted from https://huggingface.co/fp16-guy/Stable-Diffusion-v1-5_fp16_cleaned/blob/main/sd_1.5.safetensors.

XL: https://civitai.com/models/238319/sd-xl-dpo-finetune-direct-preference-optimization extracted from https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors

These are also hosted on HuggingFace at https://huggingface.co/benjamin-paine/sd-dpo-offsets/

Contributor

enfugue

Previous
NightVisionXL - NightVisionXL_v9.0.0
Next
CHOo1NE | Shiiro's Styles - v1.0
Use this model

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

SDXL - V1.0

Model hash

c100ec5708

Creator

enfugue's avatar
enfugue

Discussion

Please log in to leave a comment.

Model Collection - DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++

Macro shot of an extraterrestrial creature with iridescent blue and green feathers, large expressive eyes, and glowing bioluminescent highlights, perched on a red alien plant.
LORAMODELS

DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++ - SDXL - V1.0

Short Hash:
c100ec5708

Images by DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++ - SDXL - V1.0

A female warrior clad in silver armor stands in a forest holding a glowing sword and a blue shield with red emblem.
Macro shot of an extraterrestrial creature with iridescent blue and green feathers, large expressive eyes, and glowing bioluminescent highlights, perched on a red alien plant.
Young woman with blonde pixie haircut sitting on a red armchair wearing a school uniform with a red tie in a living room setting with plants and red curtains.
A detailed Neo-Byzantine style circular mosaic featuring ruby, sapphire, amethyst, and gold elements in an intricate floral and fractal pattern with silver leaves.
A sharp mountain peak silhouetted against a fiery orange sunset sky, reflected in a clear lake with visible rocks beneath the surface.
Colorful cute robot character with multiple arms, generated using Stable Diffusion AI.
A mountain temple surrounded by misty peaks and calm waters, AI generated using Stable Diffusion.

dpo Images

A female warrior clad in silver armor stands in a forest holding a glowing sword and a blue shield with red emblem.
A sharp mountain peak silhouetted against a fiery orange sunset sky, reflected in a clear lake with visible rocks beneath the surface.

lora Images

A white-haired girl with red eyes, wearing a black outfit and a golden spiked gauntlet, holding a red glowing sword, standing amid rolling fog in a sword tomb.
A fantasy male with demon wings kneeling in a blood-red pool under a glowing red moon, surrounded by swords and dramatic lighting.
Close-up of a dark fantasy female elf with white hair, black horns, pale skin, wearing intricate golden armor with skull motifs, holding a glowing red sword.
A realistic renaissance-style female elf with long black hair, green eyes, and pointed ears, wearing a long black dress with silver buttons, holding a gnarled staff in a mist-shrouded graveyard.
An AI generated image using stable diffusion showing a grand wizard in a blue robe with a mystical figure behind him.
Anime-style depiction of a female warrior with green hair, wearing a teal outfit with a brown belt, a purple cape, and orange gloves and boots. The image is generated using stable diffusion.
A vintage woman with red hair in a black dress holding two skulls and laughing joyfully. This is an AI generated image using Stable Diffusion.
Samurai standing in a dimly lit alley at night, generated by AI using Stable Diffusion.
A realistic 3D model of a man standing in a uniform created using Stable Diffusion.
Anime girl with long blonde hair wearing a cap, orange t-shirt, white pants, and red sneakers sitting in an urban environment, generated using Stable Diffusion AI.

stable diffusion Images

Schoolgirl with brown hair, wearing a beige vest and blue skirt, sitting stylishly on a school chair in a classroom with sunlight streaming through windows.
Vampire woman with red eyes and hair in a black and red theme, limited palette, monochrome and greyscale.
Anime girl with tan skin in a sunflower field wearing overalls and a straw hat, smiling at the viewer with a light blush.
Artistic portrayal of an elf girl indoors with glowing volumetric lighting and large breasts, facing the viewer.
Anthro fox man with glasses in a suit, holding a bloody hammer.
A goth punk teacher with dark green hair and glasses leans against a wall, wearing a leather corset and long skirt, in an alley with plants.
Illustration of WeissSchnee with white hair and a curvy figure wearing a detailed blue and white outfit in a snowy city setting.
A sci-fi warrior witch with silver hair, glowing pink eyes, and intricate tattoos, wearing an inquisitor tunic in a high-contrast, theatrical setting.
Anime-style goth punk teacher with red eyes and pixie cut, standing in an alley with butterflies and plants.
Anime-style goth succubus with green eyes in latex bodysuit, featuring dark blue hair in an alley with butterflies.

tool Images

A furry humanoid character with a backpack and axe walking through a post-apocalyptic landscape. This is an AI generated image using Stable Diffusion.