{
  "schema_version": 1,
  "id": "p-h3-image",
  "name": "P-H3-Image",
  "size_multiple": 32,
  "description": "Supports text-to-image and reference-image editing with the fixed 8-step schedule. Use the P-H3 single-frame VAE and Qwen3-VL-4B with its vision tower. Supply the P-H3 text connector separately unless it is included in the text encoder.",
  "model_url": "https://huggingface.co/PrunaAI/P-H3-Image",
  "slots": [
    {
      "id": "diffusion_model",
      "required": true
    },
    {
      "id": "llm",
      "required": true,
      "label": "Qwen 3 VL 4B Text Encoder"
    },
    {
      "id": "llm_vision",
      "required": false,
      "label": "Vision projector (required when not included in the text encoder)"
    },
    {
      "id": "embeddings_connectors",
      "required": false,
      "label": "P-H3 Text Connector (required when not included in the text encoder)"
    },
    {
      "id": "vae",
      "required": true,
      "label": "P-H3 Image VAE"
    }
  ],
  "defaults": {
    "sampling_method": "euler",
    "cfg_scale": 1,
    "steps": 8,
    "width": 1024,
    "height": 1024,
    "custom_sigmas": [
      1.0,
      0.984753,
      0.967905,
      0.951688,
      0.925372,
      0.881923,
      0.810083,
      0.528718,
      0.0
    ]
  },
  "features": [
    "ref_images"
  ]
}