{
  "model_name": "FlashRender",
  "description": "Few-step generative rendering via camera-controlled video MeanFlow.",
  "task": "video-to-video",
  "license": "apache-2.0",
  "code_repository": "https://github.com/byeongjun-park/FlashRender",
  "base_model": "alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera",
  "torch_dtype": "bfloat16",
  "height": 480,
  "width": 832,
  "num_frames": 81,
  "state_dict_format": "partial (trainable subset only); load with strict=False onto the base Wan DiT patched by flashrender_utils.model_utils.adjust_to_FlashRender",
  "checkpoints": {
    "epoch_20.safetensors": {
      "stage": 1,
      "training": "multi-step flow matching (t = r) with RETA feature alignment",
      "num_inference_steps": 50,
      "inference_mode": "mul"
    },
    "meanflow_epoch_20.safetensors": {
      "stage": 2,
      "training": "few-step MeanFlow distillation, resumed from stage 1",
      "num_inference_steps": 4,
      "inference_mode": "any"
    },
    "onpolicy_epoch_5.safetensors": {
      "stage": 3,
      "training": "on-policy flow-map distillation (DMD/VSD + GAN) of the stage-2 student",
      "num_inference_steps": 4,
      "inference_mode": "any"
    }
  }
}