You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Second successful LoRA trained on FLUX.1 [dev] for 4000 steps

Trigger word: sanna marin

Trained using SimpleTuner with code from pull request #622: https://github.com/bghira/SimpleTuner/pull/622

The quantization code is included in the latest release of SimpleTuner.

The base model and text encoders were fp8 quantized. This version works better with weight_dtype = fp8_e4m3fn in ComfyUI than earlier v0.1 that was int8 quantized.

Downloads last month: 3

Inference API

Unable to determine this model’s pipeline type. Check the docs .

Model tree for mikaelh/flux-sanna-marin-lora-v0.2-fp8

Base model

black-forest-labs/FLUX.1-dev

Adapter

(8997)

this model