import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kimi000/mist-cedar-94", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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_diffusionnft_dvreward_version_base_alphagrpo39_claude_opus5_100pct_16prompts_group14_7train_1dvreward_tp1_2node_512px_20step_cfg4_cw
Source checkpoint: step_1000.pt
Training profile: 512px, 20 rollout steps, CFG 4, AlphaGRPO DVReward.
python demo.py --prompt "A red cube beside a blue glass sphere."
- Downloads last month
- 14
Model tree for kimi000/mist-cedar-94
Base model
black-forest-labs/FLUX.2-klein-base-4B