Sign In

Large Rank LoRA - Experiments towards full finetuning

90
469
383
26
Updated: Aug 25, 2024
conceptanimemonster girl
Verified:
SafeTensor
Type
LoRA
Stats
260
194
Reviews
Published
Aug 25, 2024
Base Model
Pony
Training
Steps: 10,410
Epochs: 30
Usage Tips
Clip Skip: 2
Strength: 1
Hash
AutoV2
C9D032C59B
Supporter Badge March 2024
motimalu's Avatar
motimalu

Large Rank LoRA - Experiments towards full finetuning

What is this?

This is a collection of large rank (dimension), large dataset LoRA's which are mostly for testing full-finetuning settings with combined datasets which have been used for individual LoRA's. (see each version notes for lists)

Goal is to land on a single dataset and training settings that can

  • Express all the concepts well in a single checkpoint/lora

  • Improve the base output quality aesthetics and anatomy

Then I will use that dataset and training settings for new full-finetune models.

Who is this for?

If you enjoy any of the LoRA's datasets included, you might enjoy the combined results of these as well - in testing the individual concepts/characters are also still fairly well respresented so far. (See this post for comparisons)

These might also be useful to other creators for use in model mixing/finetuning, I've trained on base Pony for compatibility with the largest amount of merge mixes.

Datasets

Datasets included have:

  • Manual curating of quality and aesthetic tags:

    • masterpiece, best quality, low quality, very aesthetic, aesthetic

  • Around ~1000 images each

e.g. Fantasy Anime v.1 [Pony] version includes 3374 images from LoRA datasets:

Recommended prompt structure:

Positive prompt:

{{tags}}
score_9, score_8_up, score_7_up, score_6_up, absurdres, masterpiece, best quality, very aesthetic

Negative prompt:

(worst quality, low quality:1.1), score_4, score_3, score_2, score_1, error, bad anatomy, bad hands, watermark, ugly, distorted, signature