README.md

---
base_model: black-forest-labs/FLUX.1-dev
library_name: peft
license: other
pipeline_tag: text-to-image
tags:
- text-to-image
- flux
- lora
- peft
- flow-grpo
- solace
- reinforcement-learning
---

# FLUX.1-dev-SOLACE

LoRA adapter from **SOLACE** (**S**elf-c**O**nfidence reward for a**L**igning text-to-im**A**ge models via **C**onfidenc**E** optimization), CVPR 2026.

SOLACE applied to **FLUX.1-dev**, using the model's own denoising confidence as an intrinsic reward (no external reward model at training time).

- **Base model:** [`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev)
- **Method:** SOLACE intrinsic self-confidence reward (built on Flow-GRPO)
- **Code:** https://github.com/wookiekim/SOLACE
- **Adapter type:** PEFT LoRA (rank 64) on the Flux transformer

## Usage

```python
import torch
from diffusers import FluxPipeline
from peft import PeftModel

model_id = "black-forest-labs/FLUX.1-dev"
lora_ckpt_path = "wookiekim/FLUX.1-dev-SOLACE"
device = "cuda"

pipe = FluxPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

image = pipe(
    "a photo of a cat wearing a small red hat",
    height=512, width=512,
    num_inference_steps=28, guidance_scale=3.5,
).images[0]
image.save("solace_flux.png")
```

## Citation

```bibtex
@inproceedings{kim2026solace,
    title={Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards},
    author={Kim, Wookyoung and others},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2026}
}
```

## Acknowledgments

This work builds upon [Flow-GRPO](https://github.com/yifan123/flow_grpo) by Jie Liu et al.