Diffus
Get started
models/Pony Detail Tweaker - v2.0

Pony Detail Tweaker - v2.0

Yolup
|
9/5/2025
|
11:15:17 PM
| Discussion|
0
A red-skinned elf woman with white fire hair wearing gold Greek-style clothing, sitting in a flirty pose under autumn leaves and glowing stars, holding magical fire in her hand at night.
A pale-skinned girl wearing a white robe decorated with gold details and a matching veil covering her eyes, standing inside a church with stained glass windows.
A giant brain glowing in green water inside a large stasis tank surrounded by tubes and cables in a dimly lit military laboratory with scientists observing.
Hyper realistic portrait of a young woman with striking golden orange and green hair, golden earrings, vivid yellow lips, and piercing amber eyes.
A haunted village under a full moon with bats flying, featuring a tall figure with a scythe on a horse, amidst an eerie atmosphere.
AI generated anime girl with long blonde hair and red eyes in a high school outfit created using Stable Diffusion.
An anime-style AI generated image of a red-haired woman with a golden halo and angel wings, created using Stable Diffusion.
Pixel art of a mansion exterior illuminated by lanterns on a rainy night, created using stable diffusion.
A woman standing on rocky terrain holding a red umbrella under a dramatic sky. The image is an anime-style rendering created using Stable Diffusion AI technology.
AI generated image of a gamer girl with red hair and glasses. She is sitting in a gaming chair, wearing a white tank top and black pants, with a computer setup in the background.
A cat sits in a rainy alleyway near a window. AI generated using Stable Diffusion.
An anime-style girl with short, wavy brown hair standing on a balcony in an urban setting, illuminated by sunlight. She is wearing a black jacket over a white top and holding a wicker basket. This is an AI-generated image using Stable Diffusion.

Recommended Prompts

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, rating_safe, source_anime, 1girl

Recommended Negative Prompts

realistic,3d

realistic, 3d

Recommended Parameters

samplers

DPM++ 2M Karras

steps

20

cfg

7

resolution

1024x768, 768x1024

other models

Pony_DetailV2.0 (26ab1868ae7b), ponyDiffusionV6XL_v6StartWithThisOne (67ab2fd8ec)

Tips

Use the Detail Tweaker with caution on V1 at higher weights to avoid uncanny valley effects.

V2 version works more reliably for desired realism adjustments.

Version Highlights

Trained with the new and improved disentanglement method

much better at preserving the content of the original generation

Creator Sponsors

Speaking of training, training models is expensive and I run training on my own private server, if you like what I do, consider supporting the development here!

https://ko-fi.com/yolup

This model changes the level of detail

Detail tweakers aren't new, but here we go anyway. This model increases the number of intricate lines and the complexity of shading, essentially it is a realism LoRA, the higher the weight it is at, the more features will be present in the image with marginal impact on the composition.

Inspiration

I just noticed there wasn't a detail tweaker for Pony Diffusion XL yet and I decided it was prime time to train one. it was quite easy to train and only took about an hour because this is the first and only version I made, if there is an abundance of issues that I haven't recognized thus far, I will make updates, but as it stands it seems pretty good I think.

Donations

Speaking of training, training models is expensive and I run training on my own private server, if you like what I do, consider supporting the development here!

https://ko-fi.com/yolup

Key Benefits

  1. allows the alteration of details on a finely controlled level

  2. far more predictable than just prompting for "detailed" and praying to a deity of your choice

  3. allows for more extreme detail than would be possible with mere prompt weighting

Quirks

I would recommend putting "realistic" and "3d" in the negatives for V1 because V1 has a tendency to make some uncanny valley things at higher weights.

V2 seems to function exactly how I would want it to. if you encounter any strange behavior please let me know.

Contributor

Yolup avatar

Yolup

Previous
All We Imagine as Light - v3.0
Next
BusyShiny Style [Flux] - v1.0
Use this model

Model Details

Model type

LORA

Base model

Pony

Model version

v2.0

Model hash

8a2e39a88f

Creator

Yolup's avatar
Yolup

Discussion

Please log in to leave a comment.

Images by Pony Detail Tweaker - v2.0

A red-skinned elf woman with white fire hair wearing gold Greek-style clothing, sitting in a flirty pose under autumn leaves and glowing stars, holding magical fire in her hand at night.
A pale-skinned girl wearing a white robe decorated with gold details and a matching veil covering her eyes, standing inside a church with stained glass windows.
A giant brain glowing in green water inside a large stasis tank surrounded by tubes and cables in a dimly lit military laboratory with scientists observing.
Hyper realistic portrait of a young woman with striking golden orange and green hair, golden earrings, vivid yellow lips, and piercing amber eyes.
A haunted village under a full moon with bats flying, featuring a tall figure with a scythe on a horse, amidst an eerie atmosphere.
AI generated anime girl with long blonde hair and red eyes in a high school outfit created using Stable Diffusion.
An anime-style AI generated image of a red-haired woman with a golden halo and angel wings, created using Stable Diffusion.
Pixel art of a mansion exterior illuminated by lanterns on a rainy night, created using stable diffusion.
A woman standing on rocky terrain holding a red umbrella under a dramatic sky. The image is an anime-style rendering created using Stable Diffusion AI technology.
AI generated image of a gamer girl with red hair and glasses. She is sitting in a gaming chair, wearing a white tank top and black pants, with a computer setup in the background.
A cat sits in a rainy alleyway near a window. AI generated using Stable Diffusion.
An anime-style girl with short, wavy brown hair standing on a balcony in an urban setting, illuminated by sunlight. She is wearing a black jacket over a white top and holding a wicker basket. This is an AI-generated image using Stable Diffusion.

concept Images

Portrait of a cyborg girl with pink skin, yellow eyes with black sclera, wearing a steampunk-inspired mechanical outfit with gears, cogs, and a mechanical limb, set against a background featuring an antique clock face.
A mysterious woman with flowing black hair and a dark, lace-adorned dress stands in a field of flowers, bathed in an ethereal glow from a futuristic sunset and surrounded by glowing sparks.

detail Images

A cyberpunk woman crouching on broken debris in a neon-lit dystopian city, wearing sleek futuristic armor with a mechanical arm and glowing visor glasses.
Digital painting of a mysterious woman with black short hair and pale skin, wearing a white hooded gown with a red hood, sitting on a tree branch surrounded by glowing autumn leaves at night.
A cyberpunk anime illustration of Major Motoko Kusanagi seated sideways on a yellow wooden chair, with short black hair, glowing blue eyes, bare back revealing cybernetic ports, draped in red cloth against a crimson background with crumbling bricks and Japanese kanji.
High resolution image of a Disney-style animated blue bird with neon lighting, glossy melting feathers, and detailed eyes on a dark background.
Kyojuro Rengoku standing against an orange sunset background with fiery wings spreading out, holding a flaming sword, dressed in traditional Japanese clothes.
Close-up portrait of a Siberian shaman with realistic details, highlighted by cinematic neon pink and blue lighting, featuring wet skin texture and intense gaze.
A punk-inspired woman wearing a vibrant red wide-brimmed hat, red sunglasses, and a stylish red jacket, smoking a pipe with soft, cinematic lighting highlighting her features.
Hyperrealistic portrait of a dragon girl with luminous, colorful, and ethereal features, intricate textures, and fantasy elements.
A surreal forest scene inside a transparent glass apple using Stable Diffusion AI.
AI generated image of an origami cat paper sculpture with glowing eyes standing in a street at night using stable diffusion.