https://github.com/lucataco/cog-flux-dev-multi-lora

LoRA Explorer model to run with multiple LoRAs using Flux.1[Dev] as the base model
https://github.com/lucataco/cog-flux-dev-multi-lora

cog

Last synced: 12 months ago
JSON representation

LoRA Explorer model to run with multiple LoRAs using Flux.1[Dev] as the base model

• Host: GitHub
• URL: https://github.com/lucataco/cog-flux-dev-multi-lora
• Owner: lucataco
• License: apache-2.0
• Created: 2024-08-19T02:10:21.000Z (almost 2 years ago)
• Default Branch: master
• Last Pushed: 2024-10-06T04:01:23.000Z (almost 2 years ago)
• Last Synced: 2024-11-26T16:44:27.023Z (over 1 year ago)
• Topics: cog
• Language: Python
• Homepage: https://replicate.com/lucataco/flux-dev-multi-lora
• Size: 1.65 MB
• Stars: 9
• Watchers: 1
• Forks: 6
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# FLUX.1-dev multi-LoRA Explorer Cog Model

This is an implementation of [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) as a [Cog](https://github.com/replicate/cog) model.

Named multi-LoRA Explorer, to explore the model with different LoRA weights.

## Development

Follow the [model pushing guide](https://replicate.com/docs/guides/push-a-model) to push your own model to [Replicate](https://replicate.com).

## How to use

Make sure you have [cog](https://github.com/replicate/cog) installed.

To run a prediction:

    cog predict -i prompt="a photo of TOK, sftsrv style" -i extra_loras=["lucataco/flux-queso","https://huggingface.co/alvdansen/softserve_anime/resolve/main/flux_dev_softstyle_araminta_k.safetensors"]

![Output](output.0.png)

## License

The code in this repository is licensed under the [Apache-2.0 License](LICENSE).

Flux Dev falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).

`FLUX.1 [dev]` fine-tuned weights and their outputs are non-commercial by default, but can be used commercially when running on Replicate.