Downloads · 30 days
3
7% of all-time downloads
thedinaiym/judge-in-the-loop-flux-lora
judge-in-the-loop-flux-lora is a text-to-image model from thedinaiym. Use it when you need an image from a text prompt. It is set up for peft. The card lists the license as other.
Rank-64 LoRA adapter for FLUX.1-dev, trained with critic-free GRPO using a frozen Q-Judger (Qwen-Image-Bench) as an online, multi-dimensional reward oracle.
Downloads · 30 days
3
7% of all-time downloads
All-time downloads
41
Public
Repo size
299 MB
Likes
0
Public
Click a slice to open those files.
.safetensors299 MB · 100%
From the Hugging Face model README
Rank-64 LoRA adapter for FLUX.1-dev, trained with critic-free GRPO using a frozen Q-Judger (Qwen-Image-Bench) as an online, multi-dimensional reward oracle.
⚠️ Preliminary research artifact. This adapter is the output of a 10-step exploratory run. It is released for reproducibility, not as a quality-improving adapter. No baseline comparison has been established — see Limitations.
black-forest-labs/FLUX.1-devto_q, to_k, to_v, to_out.0 · rank 64, alpha 64| Setting | Value |
|---|---|
| GRPO steps | 10 |
| Prompts / step | 1 |
| Samples / prompt (G) | 3 |
| Resolution | 512×512, 6 denoising steps |
| Optimizer | AdamW, lr 1e-4 |
| Clip ε / KL β | 0.2 / 0.04 |
| SDE noise σ | 0.15 |
| Prompts | Qwen-Image-Bench test split (1,000 prompts, dims_en) |
| Hardware | 1× A100 80GB · 670 s/step · 1.86 h |
Policy (12B) and judge (27B) do not co-reside in 80GB, so the phases are sequenced: each model is moved to CPU while the other occupies the GPU.
| Metric | Value |
|---|---|
| Q-Judger parse rate | 1.000 (30/30 prompt–image pairs) |
| Gradient norm | 332 – 764 |
| Policy–reference KL | 0 → 256 |
| Mean reward | 32.11 ± 11.62 |
| OLS slope | +1.34/step (r² = 0.12, not significant) |
The per-step reward is confounded by prompt difficulty (one prompt per step), so it must not be read as a learning curve.
from diffusers import FluxPipeline
import torch
pipe = FluxPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("thedinaiym/judge-in-the-loop-flux-lora")
image = pipe("a robot walking in Tokyo", num_inference_steps=20).images[0]
PEFT 0.19.1 · diffusers 0.39.0 · transformers 5.13.0 · torch 2.12.0+cu130