Creates detailed surface textures without shadows or hotspots.
For versions 5 and 6, the recommended “Weight,” “Strength,” or “LoRA Weight” (depending on the tool used) is between 50% and 150% when entered as a percentage or 0.5 to 1.5 when entered as a decimal. Some prompts performed significantly better at 150%, while others yielded better results at 100%. If you are dissatisfied with the outcomes, I suggest experimenting with a different weight. Weights closer to 1.0 generally resulted in more dynamic output, but they occasionally introduced undesirable elements. Conversely, weights closer to 1.5 produced more authentic diffuse map output, but they may sometimes appear too simplistic.
The recommended sampler is: DDIM
The Minimal Weight / Strength is: 0.5
The recommended Weight / Strength is: 0.5 - 1.5
The recommended Guidance Scale is: 3.5
The recommended number of steps are: 50-150
For best results, begin your prompt with "A diffuse map of a " or "diffusemapsurfaces, A diffuse map of "
Example Prompts:
A diffuse map of a wooden surface with a natural wood grain texture.
diffusemapsurfaces, A diffuse map of a brick wall.
Please be advised that the trigger word used in versions below version 5 was “DiffuseMapSurfaces,” although the trigger word was removed for version 5, has been reinstated in version 6 and functions effectively without it.
If you review the labels in the dataset, most of them begin with “A diffuse map of a” (a few omit the “a” at the end, so disregard it if it does not align grammatically with your prompt).
Comparison of output with and without the LORA using the same settings, seed, and prompt:
Dataset:
The dataset used is available for download from my huggingface account at:
https://huggingface.co/datasets/alastandy/Diffuse_Map_Surfaces
misc {andrew_smith_2025,
author = { {Andrew Smith} },
title = { Diffuse_Map_Surfaces (Revision 3ea7938) },
year = 2025,
url = { https://huggingface.co/datasets/alastandy/Diffuse_Map_Surfaces },
doi = { 10.57967/hf/4587 },
publisher = { Hugging Face }
}
Description
Version v5.0-Pinnacle:
Using 1.0 / (100%) weight/strength is once again working and recommended. In fact, in testing, using 1.0- 1.5 / ( 100% - 150%) produced some of the best version 5 results. Some prompts do better at 1.0 and some do better at 1.5.
Version 5.0-Pinnacle has a large and diverse set of training examples with labels. The dataset is 1.07 GB in size with hundreds of high-resolution images, and it took almost 24 hours to train 20 epochs on the civitai onsite trainer.
Start Time:
12/19/2024 03:14:17 a.m.
End Time:
12/20/2024 02:03:15 a.m.
I was honestly not sure if it would make it given the 24-hour time cutoff for failing a job. (Training processing for more than 24 hours is automatically failed by Civitai.)