Cosmos 3 Super Image to Video

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.nvidia-cosmos-3-super-image-to-video","input":{"image_url":"","prompt":""},"idempotency_key":"example-request-1"}'

{
  "type": "object",
  "required": [
    "prompt",
    "image_url"
  ],
  "properties": {
    "num_inference_steps": {
      "type": "integer",
      "description": "Number of denoising steps. More steps yield higher quality but take longer.",
      "default": 28
    },
    "agentic_samples_per_iteration": {
      "type": "integer",
      "description": "Candidate videos to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage.",
      "default": 2
    },
    "image_size": {
      "type": "string",
      "description": "The size of the generated video. The request is clamped and snapped to the nearest supported NVIDIA tier (256p/480p/720p) and aspect ratio.",
      "default": {
        "height": 480,
        "width": 832
      },
      "enum": [
        "square_hd",
        "square",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9"
      ]
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Enable content moderation for the input prompt and image. Disabling it requires account authorization; unauthorized requests are always checked.",
      "default": true
    },
    "guidance_scale": {
      "type": "number",
      "description": "Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity.",
      "default": 6
    },
    "enable_prompt_expansion": {
      "type": "boolean",
      "description": "If true, the Cosmos3-Nano Reasoner (a VLM that sees the first frame) rewrites the prompt into the dense caption Cosmos3 was trained on. The app starts a local Reasoner by default, or uses COSMOS_PROMPT_UPSAMPLER_BASE_URL when configured. Falls back to the raw prompt if expansion fails.",
      "default": true
    },
    "agentic_max_iterations": {
      "type": "integer",
      "description": "Maximum agentic prompt stages when agentic generation is enabled.",
      "default": 2
    },
    "seed": {
      "type": "integer",
      "description": "The same seed and prompt given to the same model version will produce the same video every time."
    },
    "num_frames": {
      "type": "integer",
      "description": "Number of frames to generate. More frames yield a longer video.",
      "default": 189
    },
    "enable_agentic_generation": {
      "type": "boolean",
      "description": "Enable the iterative Cosmos agentic loop: prompt upsampling, candidate video generation, VLM critique of sampled frames, and prompt rewrite. Each candidate is a full render, so this is substantially slower and costlier than a single generation.",
      "default": false
    },
    "image_url": {
      "type": "string",
      "description": "URL of the conditioning first-frame image for the video."
    },
    "agentic_early_stop": {
      "type": "boolean",
      "description": "Stop the agentic loop early when the critic score clears the strict quality threshold.",
      "default": true
    },
    "frames_per_second": {
      "type": "integer",
      "description": "Frames per second of the output video.",
      "default": 24
    },
    "prompt": {
      "type": "string",
      "description": "Text prompt describing the motion and scene of the video to generate."
    },
    "sync_mode": {
      "type": "boolean",
      "description": "If `True`, the video is returned as a data URI and the output data won't be available in the request history.",
      "default": false
    },
    "negative_prompt": {
      "type": "string",
      "description": "Content to steer the generation away from (artifacts, unwanted motion). Defaults to NVIDIA's recommended i2v negative prompt; pass an empty string to disable.",
      "default": "The video captures a series of frames showing macroblocking artifacts, chromatic aberration, high-frequency noise, and rolling shutter distortion. It includes static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, bit-depth compression artifacts, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, hard cut, visual noise, and flickering. It features moiré patterns, edge halos, and temporal aliasing. Furthermore, the content defies common sense, generating illogical scenarios, nonsensical entities, absurd character behaviors, and conceptual paradoxes that violate basic human reasoning and everyday reality. The video looks like a surreal or glitchy hallucination. Overall, the video is of poor quality."
    }
  }
}