GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
thedinaiym
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
thedinaiym
Model Tree
black-forest-labs/FLUX.1-dev
Input Modalities
Output Modalities
Supported Functionality
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.
python
from diffusers import FluxPipelineimport torchpipe = 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