kimi000/silver-brook-46

FLUX.2 Klein Base 4B AlphaGRPO checkpoint

This is a complete native Diffusers Flux2KleinPipeline. The EMA LoRA is already merged into the transformer, so FAR and PEFT are not required for inference.

Source experiment: flux2_klein_base_4b_native_grpo_dvreward_version_base_v0_1_seasonal_39family_100pct_16prompts_group14_7train_1dvreward_tp1_2node_512px_20step_10sde_cfg4_cw

Source checkpoint: step_500.pt

Training profile: 512px, 20 rollout steps, CFG 4, AlphaGRPO DVReward.

python demo.py --prompt "A red cube beside a blue glass sphere."