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

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Pro studio (SpyGlass) Web

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

Civitai Web

Pay per use

Generate on Civitai's own site; every image is paid for with Buzz credits.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

4,006 downloads · 113 likes on Civitai

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Created by

enfugue

on Civitai

__html__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…__html__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) athttps://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.safe

Creator notes

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 , and wrote a paper about it at . 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 () at and , 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: extracted from . XL: extracted from These are also hosted on HuggingFace at

SHA256

D4EC63A436DBD20E5CAC4A3E9A1FD0C59FB2513018266252C4EE9EBEB5CE6762

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

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

Heat score, last 12 months

Heat score

7,780°

This week

▲

0.1%

7,782° then, 7,780° now

This month

▲

0.4%

7,787° then, 7,780° now

Past year

▲

8.0%

7,845° then, 7,780° now

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,080°

Civitai downloads

4,006 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.

+309°

Likes

113 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

−609°

Age

−609° because the SD15 weights came out in 2022. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 7,780°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
4,006 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,080°
8,080°
running total
3
Add the likes.
113 likes and thumbs up, at half the weight of a download.
+309°
8,389°
running total
4
Take off the age.
The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
−609°
7,780°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
7,780°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Example renders

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.

Get this prompt

Render by Sajrep on

Settings

Sampler

LMS

Steps

Guidance

Seed

987610379621410

Size

512x512

Prompt

cute slime girl, happy, wearing heavy armor, chainmail, green, slime, glowing, bones, looking at viewer, side view, detailed background <lora:Hyper-SD15-8steps-lora:0.75> <lora:sd_v15_dpo_lora_v1:0.5> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:0.5>

Render by Sajrep on

Settings

Sampler

LMS

Steps

Guidance

Seed

345043061657583

Size

512x512

Prompt

Sonic the Hedgehog, bloody, blood, injured, staggering, grinning, determined, surrounded, detailed, hyperdetailed <lora:Hyper-SD15-8steps-lora:0.75> <lora:sd_v15_dpo_lora_v1:0.75> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:0.25>

Render by Sajrep on

Settings

Sampler

DPM++ 2M

Steps

Guidance

7.5

Seed

556051207637958

Size

512x512

Prompt

feral sylveon, angry, barking, dangerous, angular, intimidating, moon, destruction, moonbeam, energy beam from the moon, glitter, realistic detailed fur <lora:sd_v15_dpo_lora_v1:1.0> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:1.0>

Negative prompt

embedding:deformityv6, embedding:boring_e621_fluffyrock_v4

Render by Sajrep on

Settings

Sampler

DPM++ 2M

Steps

Guidance

7.5

Seed

556051207637958

Size

512x512

Prompt

ankha cat, detailed fur <lora:sd_v15_dpo_lora_v1:1.0> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:1.0> <lora:more_details:2.0>

Negative prompt

embedding:deformityv6, embedding:boring_e621_fluffyrock_v4

Render by Sajrep on

Settings

Sampler

DPM++ 2M

Steps

Guidance

Seed

345043061657583

Size

512x512

Prompt

anthro, umbreon, female, drummer, drumming, (white tank top:1.2), grinning, energetic, motion, beating, dramatic lighting, cinematic, realistic detailed fur, photorealistic, viewed from below, (music notes:1.1) <lora:Hyper-SD15-12steps-CFG-lora:1.0> <lora:sd_v15_dpo_lora_v1:0.75> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:0.25>

Render by Sajrep on

Settings

Sampler

DPM++ 2M

Steps

Guidance

Seed

345043061657584

Size

512x512

Prompt

(manga:1.3), monochrome, feral, pegasus, Rainbow Dash, standing, shouting, serious, hooves, low angle view, dutch angle, cinematic <lora:Hyper-SD15-12steps-CFG-lora:1.0> <lora:sd_v15_dpo_lora_v1:0.75> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:0.25>

Render by Sajrep on

Settings

Sampler

DPM++ 2M SDE

Steps

Guidance

Seed

345043061657583

Size

512x512

Prompt

anthro, pegasus, Rainbow Dash, wings, hooves, sport clothes, sitting on cloud, mlp, light blue fur, detailed fur, sunny <lora:Hyper-SD15-8steps-lora:0.75> <lora:sd_v15_dpo_lora_v1:0.75> <lora:spo-sd-v1-5_4k-p_10ep_lora_webui:0.25>

Render by Sajrep on