model_index.json

{
  "_class_name": "Cosmos3OmniDiffusersPipeline",
  "_diffusers_version": "0.37.1",
  "scheduler": [
    "diffusers",
    "UniPCMultistepScheduler"
  ],
  "text_tokenizer": [
    "transformers",
    "Qwen2TokenizerFast"
  ],
  "transformer": [
    "diffusers",
    "Cosmos3OmniTransformer"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKLWan"
  ],
  "vision_encoder": [
    "transformers",
    "Qwen3VLVisionModel"
  ],
  "sound_tokenizer": [
    "diffusers",
    "Cosmos3AVAEAudioTokenizer"
  ]
}