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

8/10/2025

7:20:40 PM

| Discussion|

Related Keywords & Tags

A futuristic astronaut wearing a biomechanical, colorful suit with a large robotic helmet exploring a surreal planet filled with vibrant orange and pink alien flowers under a bright blue sky with clouds.

A calico cat sitting serenely among vibrant Japanese watercolor style flowers under a large red sun with elegant ink wash effects.

Pink two-story house with a blue door, colorful clothes hanging on lines, a cat on a washing machine, outdoor laundry setup on a sunny day

Fantasy portrait of a girl with angel wings and cat ears wearing a gothic dress, with curly hair and dangling earrings.

A woman in a white dress and straw hat walking barefoot on a sandy beach toward the ocean with waves and clear blue water.

Recommended Parameters

samplers

DPM++ 2M

steps

cfg

4.5

Tips

Use negative strength values when applying the LoRA.

LoRA strength can range from -0.01 to -2.00, with -0.45 as a good starting point.

Values beyond -0.75 may cause deterioration in results.

ComfyUI users can utilize the SnakeOil custom_node suite to automatically invert negative LoRAs and organize them in the models/nloras folder.

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

For ease of use, ComfyUI users can use the SnakeOil custom_node suite which supports automatic inversion of negative LoRAs and improved 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.