Diffus
Get started
models/Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA - SD3.5L_pnte_2.0_rank64

Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA - SD3.5L_pnte_2.0_rank64

doctor_diffusion
|
8/26/2025
|
10:46:03 AM
| Discussion|
0
A surreal alien figure wearing a vibrant orange and blue biomechanical suit and a large robotic helmet stands amidst colorful, bulbous flora on a fantastic, otherworldly planet under a bright cloudy sky.
Surreal digital painting of an anthropomorphic white cat with yellow eyes, intricate golden accents, and an abstract background blending into the feline figure.
Calico cat sitting gracefully amid watercolor-style oriental flowers and red moon, blending traditional Asian art with modern digital techniques.
Two-story pink house with a blue door and colorful laundry hanging on clotheslines under a bright blue sky with clouds and birds. A cat sits on a white washing machine outside.
Digital artwork of a fantasy girl with angel wings and cat ears, curly hair, wearing a black dress and golden earrings.
A woman wearing a summer dress and sun hat walks barefoot on a sandy pathway toward the ocean with crashing waves, bordered by stone steps and rustic wooden railings.

Recommended Negative Prompts

PNTE LoRA should be used with negative strength values

Recommended Parameters

samplers

DPM++ 2M

steps

40

cfg

4.5

Tips

Use negative LoRA strength values when applying PNTE, with recommended starting strength at -0.45.

LoRA strengths below -0.75 may cause deterioration in image quality.

ComfyUI users can use the SnakeOil custom node to handle negative LoRAs more effectively and organize LoRA folders.

Version Highlights

Trained with my experimental aitoolkit config file. See article below for more information.

This works very well as an incremental detail slider. I normally start around -0.45 for overall better results. Things can get a little strange the closer to -1 you get and there are at times a noticeable shift between -0.78 to -0.98. Use as low as -0.01 for extremely subtle quality increases.

This version was trained with a network rank of 64

Creator Sponsors

Check out the SnakeOil custom_node suite for ComfyUI to easily manage negative LoRAs with auto-inversion and folder organization.

"PNTE" Negative Stable Diffusion LoRA

Increase the quality and amount of details in images with these negative LoRAs for Stable Diffusion models.


How to use:

THESE ARE MEANT TO BE USED WITH NEGATIVE STRENGTH VALUES.
To do this simply add the LoRA to the negative prompt or manually adjust the LoRA strength depending on the diffusion interface you are using.

For ease of use, ComfyUI users can use the SnakeOil custom_node suite I created. This node not only automatically inverts negative LoRAs but it also looks for them in models/nloras folder rather than the normal models/loras folder. This helps with organization and keeping our ever growing lists of LoRAs a little shorter.

SD3.5L:

The most recent updated version my "point-e" negative embedding for use with Stable Diffusion 3.5 Large was trained with my experimental custom config for aitoolkit.


I set CLIP to 0 as I did not train the text encoders.
LoRA strength can range from -0.01 to -2.00 but there will often be deterioration past -0.75 in most cases. -0.45 is a good place to start. Works as low as -0.01.

Previous
Madly Mix ver NightNoob - v2
Next
Midjourney Whisper V7 - alpha_v01 [FLUX]
Use this model

Model Details

Model type

LORA

Base model

SD 3.5 Large

Model version

SD3.5L_pnte_2.0_rank64

Model hash

337177f3ec

Creator

doctor_diffusion's avatar
doctor_diffusion

Discussion

Please log in to leave a comment.

Model Collection - Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA

Surreal digital painting of an anthropomorphic white cat with yellow eyes, intricate golden accents, and an abstract background blending into the feline figure.
LORAMODELS

Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA - SD3.5L_pnte_2.0_rank64

Short Hash:
337177f3ec

Images by Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA - SD3.5L_pnte_2.0_rank64

A surreal alien figure wearing a vibrant orange and blue biomechanical suit and a large robotic helmet stands amidst colorful, bulbous flora on a fantastic, otherworldly planet under a bright cloudy sky.
Surreal digital painting of an anthropomorphic white cat with yellow eyes, intricate golden accents, and an abstract background blending into the feline figure.
Calico cat sitting gracefully amid watercolor-style oriental flowers and red moon, blending traditional Asian art with modern digital techniques.
Two-story pink house with a blue door and colorful laundry hanging on clotheslines under a bright blue sky with clouds and birds. A cat sits on a white washing machine outside.
Digital artwork of a fantasy girl with angel wings and cat ears, curly hair, wearing a black dress and golden earrings.
A woman wearing a summer dress and sun hat walks barefoot on a sandy pathway toward the ocean with crashing waves, bordered by stone steps and rustic wooden railings.

detail Images

A fiery phoenix with spreading wings perched above a girl in a long, embroidered dress standing on a rocky cliff with a dark, dramatic background.
A cyberpunk woman in a sleek armored bodysuit crouching on broken bricks and electronic debris, surrounded by neon-lit skyscrapers and holographic billboards in a dystopian cityscape.
Digital painting of a woman with black hair and red eyes sitting on a tree branch, wearing a white hooded gown with a red inner lining, surrounded by glowing autumn leaves against a dark background.
Cyberpunk anime illustration of Major Motoko Kusanagi seated sideways on a yellow chair against a vibrant red background. Her bare back is exposed with visible cybernetic ports, short black hair, and glowing blue eyes looking over her shoulder, surrounded by crumbling bricks and Japanese kanji text.
Portrait of Kyojuro Rengoku standing with flaming wings and a fire-infused sword, dressed in traditional Japanese attire, against a vibrant orange sunset sky.
Close-up portrait of a female with wet hair illuminated by cinematic pink and blue neon lighting, detailed with realistic wet skin texture and dark atmospheric background.
Close-up portrait of a dragon girl with ethereal, colorful, and intricate hair, glowing eyes, and detailed skin, rendered in hyperrealistic digital art style.
Stylized digital artwork of a punk woman wearing a vivid red wide-brimmed hat and sunglasses, smoking a red pipe against a dark background.
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.

negative Images

Black and white zombie illustration with dark background and expressive pose.

stable diffusion Images

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.
Beautiful girl with black hair and goth dress in a sunlit cafe.

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.