Logo

EasyPic

Sign Up
Login

Models>

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

RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
Portrait of a young man with a chiseled jawline, emerald green eyes, and tousled brown hair. He wears a Greek warrior's armor and stands on a cliff overlooking the Aegean Sea. he is holding a sign saying "AIEasyPic"
Portrait of a young man with a chiseled jawline, emerald green eyes, and tousled brown hair. He wears a Greek warrior's armor and stands on a cliff overlooking the Aegean Sea. he is holding a sign saying "AIEasyPic"
Try Full Demo
Quick Generate
Select a style, write what you want to see and click Generate
RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
What you want in the image.
Clear
Random
Sign Up
Train Your Own Model

Model Description by Creator

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/

Images Generated With This Model

RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
N/A
Hidden For Public Users
RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
Info
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
N/A
Hidden For Public Users
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
Info
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
N/A
Hidden For Public Users
RAW photo, a close-up picture of a dog, blue eyes, reflection in it's eyes
Info
RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
N/A
Hidden For Public Users
RAW photo, a close-up picture of a cat, orange eyes, reflection in it's eyes
Info
highres, highest quallity, 1girl, adult, solo, solo_focus, white_hair, red_eye, demon_girl, ahoge, short_hair, black_necktie, white_shirt, black_vest, black_pants, medium breasts, heart-shaped pupils, night, red eyeshadow,reference sheet, expressionless, cross_earrings, orange_theme, festival, bartender, bar, heterochromia, orange_eye,
N/A
Hidden For Public Users
highres, highest quallity, 1girl, adult, solo, solo_focus, white_hair, red_eye, demon_girl, ahoge, short_hair, black_necktie, white_shirt, black_vest, black_pants, medium breasts, heart-shaped pupils, night, red eyeshadow,reference sheet, expressionless, cross_earrings, orange_theme, festival, bartender, bar, heterochromia, orange_eye,
Info
houjuu nue,1girl, solo, crying_with_eyes_open, open_mouth, looking_at_viewer, fang, heart-shaped_pupils, ahoge, red_bowtie, asymmetrical_wings, upper_body, sunset, outdoors, :d, blue_wings, center_frills, yellow_sky, black_dress, orange_sky, red_wings, cloudy_sky, nose_blush <lora:houjuu_nue_image7311_2023-12-20:1>,star-shaped_pupils,symbol-shaped_pupils,. gorgeous,key visual, vibrant, studio anime,award-winning, professional, highly detailed,high budget, cinemascope
N/A
Hidden For Public Users
houjuu nue,1girl, solo, crying_with_eyes_open, open_mouth, looking_at_viewer, fang, heart-shaped_pupils, ahoge, red_bowtie, asymmetrical_wings, upper_body, sunset, outdoors, :d, blue_wings, center_frills, yellow_sky, black_dress, orange_sky, red_wings, cloudy_sky, nose_blush <lora:houjuu_nue_image7311_2023-12-20:1>,star-shaped_pupils,symbol-shaped_pupils,. gorgeous,key visual, vibrant, studio anime,award-winning, professional, highly detailed,high budget, cinemascope
Info
multicolored, mash_kyrielight, japanese_clothes, kimono, 1girl, flower, hair_ornament, open_mouth, floral_print, smile, solo, morning_glory, short_hair, yellow_kimono, hair_flower, hydrangea, bamboo, print_kimono, purple_eyes, sash, looking_at_viewer, purple_flower, orange_kimono, obi, one_eye_closed, eyebrows_visible_through_hair, upper_body, blush, wide_sleeves, fruit, eggplant, holding, bangs, pink_hair, eyes_visible_through_hair, long_sleeves, hair_over_one_eye, multicolored_kimono, hair_between_eyes, breasts, food, blue_flower <lora:style_AnimeOriginal:1>
N/A
Hidden For Public Users
multicolored, mash_kyrielight, japanese_clothes, kimono, 1girl, flower, hair_ornament, open_mouth, floral_print, smile, solo, morning_glory, short_hair, yellow_kimono, hair_flower, hydrangea, bamboo, print_kimono, purple_eyes, sash, looking_at_viewer, purple_flower, orange_kimono, obi, one_eye_closed, eyebrows_visible_through_hair, upper_body, blush, wide_sleeves, fruit, eggplant, holding, bangs, pink_hair, eyes_visible_through_hair, long_sleeves, hair_over_one_eye, multicolored_kimono, hair_between_eyes, breasts, food, blue_flower <lora:style_AnimeOriginal:1>
Info
<lora:zerotwo:1>,1girl, solo, zero_two_\(darling_in_the_franxx\), long_hair, horns, pink_hair, looking_at_viewer, hand_on_hip, smile, hairband, necktie, simple_background, bangs, short_necktie, uniform, white_hairband, grey_background, closed_mouth, straight_hair, aqua_eyes, red_dress, long_sleeves, military_uniform, eyeshadow, orange_necktie, makeup, military, green_eyes, double-breasted
N/A
Hidden For Public Users
<lora:zerotwo:1>,1girl, solo, zero_two_\(darling_in_the_franxx\), long_hair, horns, pink_hair, looking_at_viewer, hand_on_hip, smile, hairband, necktie, simple_background, bangs, short_necktie, uniform, white_hairband, grey_background, closed_mouth, straight_hair, aqua_eyes, red_dress, long_sleeves, military_uniform, eyeshadow, orange_necktie, makeup, military, green_eyes, double-breasted
Info
masterpiece, best quality， <lora:zerotwo:1>,1girl, solo, long_hair, zero_two_\(darling_in_the_franxx\), pink_hair, horns, lollipop, food, candy, uniform, hairband, green_eyes, military_uniform, white_background, looking_at_viewer, simple_background, open_mouth, white_hairband, orange_necktie, necktie, military, bangs, straight_hair, breasts, mouth_hold, arms_up, arms_behind_head, upper_body, red_dress, medium_breasts, dress, eyeshadow
N/A
Hidden For Public Users
masterpiece, best quality， <lora:zerotwo:1>,1girl, solo, long_hair, zero_two_\(darling_in_the_franxx\), pink_hair, horns, lollipop, food, candy, uniform, hairband, green_eyes, military_uniform, white_background, looking_at_viewer, simple_background, open_mouth, white_hairband, orange_necktie, necktie, military, bangs, straight_hair, breasts, mouth_hold, arms_up, arms_behind_head, upper_body, red_dress, medium_breasts, dress, eyeshadow
Info
margaret_odeus, mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, fiery_hair, angry, floating hair, fire, from behind, henshin, fighting stance, backlighting, depth of field, indirect lighting, dim lighting, hand curvy, thick thighs, narrow waist, wide hips, large breasts, <lora:margaret_v01:0.80>
N/A
Hidden For Public Users
margaret_odeus, mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, fiery_hair, angry, floating hair, fire, from behind, henshin, fighting stance, backlighting, depth of field, indirect lighting, dim lighting, hand curvy, thick thighs, narrow waist, wide hips, large breasts, <lora:margaret_v01:0.80>
Info
mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, from behind, library, books, desk, backlighting, depth of field, indirect lighting, dim lighting, curvy, thick thighs, narrow waist, wide hips, large breasts,
N/A
Hidden For Public Users
mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, from behind, library, books, desk, backlighting, depth of field, indirect lighting, dim lighting, curvy, thick thighs, narrow waist, wide hips, large breasts,
Info
margaret_odeus, mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, dancing, backlighting, depth of field, indirect lighting, dim lighting, curvy, thick thighs, narrow waist, wide hips, large breasts, <lora:margaret_v01:0.80>
N/A
Hidden For Public Users
margaret_odeus, mature female, detailed, masterpiece, HDR, detailed sharp, best quality, highres, 1girl, solo, long_hair, orange_eyes, hair_ornament, red_dress, cleavage, thighhighs, boots, makeup, thick lips, lipstick, eyeshadow, dancing, backlighting, depth of field, indirect lighting, dim lighting, curvy, thick thighs, narrow waist, wide hips, large breasts, <lora:margaret_v01:0.80>
Info

Our Main Suite of Tools

AI Generator
AI Generator
Text to Image generation
Text To Video
Text To Video
Create video clips from text
Train Model
Train Model
Train custom models on your own pics
Face Swap
Face Swap
Swap faces in images
Real-Time
Real-Time
Instant image generation
Pro. Headshots
Pro. Headshots
Professional headshots in minutes

Similar Models

SD 1.5 / SD 1.5 inpainting (fp16/cleaned)
V1
SD 1.5 / SD 1.5 inpainting (fp16/cleaned)
(4.80)
0
5 Ratings
SDXL DPO-Turbo-LoRA
V1
SDXL DPO-Turbo-LoRA
(5.00)
0
1 Ratings
SDXL DPO-Turbo-LoRA
V2
SDXL DPO-Turbo-LoRA
(5.00)
0
1 Ratings
LCM-LoRA Weights - Stable Diffusion Acceleration Module
V1
LCM-LoRA Weights - Stable Diffusion Acceleration Module
(4.83)
0
35 Ratings
DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++
V2
DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++
(5.00)
0
13 Ratings
Ui-Ux (LORA) SD 1.5 & SDXL
V1
Ui-Ux (LORA) SD 1.5 & SDXL
(5.00)
0
3 Ratings
SDXL DPO-Turbo-LoRA
V2
SDXL DPO-Turbo-LoRA
(5.00)
0
2 Ratings
LCM-LoRA Weights - Stable Diffusion Acceleration Module
V2
LCM-LoRA Weights - Stable Diffusion Acceleration Module
(4.78)
0
27 Ratings
SD 1.5 / SD 1.5 inpainting (fp16/cleaned)
V1
SD 1.5 / SD 1.5 inpainting (fp16/cleaned)
(5.00)
0
6 Ratings
QoL Positive Embeds
V1
QoL Positive Embeds
(5.00)
0
3 Ratings

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.
Start Creating For Free