lucataco / stable-diffusion-3.5-large-lora-trainer

Fine-tune StableDiffusion3.5-Large with Hugging Face Diffusers

  • Public
  • 315 runs
  • GitHub
  • Weights
  • Paper
  • License
Run with an API
Playground API Examples README Versions

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Huggingface Diffusers Dreambooth LoRA Trainer for StableDiffusion3.5-Large

About

Cog implementation of the Diffusers LoRA Trainer for StableDiffusion3.5-Large

Follow me on Twitter/X @lucataco93

How to use

Upload images as a zip file, and hit run to train a LoRA. At this time, it is advised that you also add a HF_token that has write access to Huggingface to upload your trained LoRA.

An example of a trained LoRA style: lucataco/SD3.5-Large-yarn

An example of a trained LoRA object: lucataco/SD3.5-Large-queso

Run your LoRA

Once your LoRA is in Huggingface, go to the model and grab the full URL to the LoRA

An example of a prediction run with a LoRA can be found here: frog

Licensing and commercial use

If you generate images on Replicate with StableDiffusion3.5-Large models and their fine-tunes, then you can use the images commercially.

If you download the weights off Replicate and generate images on your own computer, you can’t use the images commercially.