Catalog/Video/fal

Cosmos Predict 2.5 2B Distilled

Makes a video from a description

Liveby NVIDIA

Generate video from text and videos using NVIDIA's 2B Cosmos Distilled Model

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Make a 5-second video with Cosmos Predict 2.5 2B Distilled of a drone flying over Florianópolis at sunrise.

Make a short video of waves rolling onto a beach at sunset.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Video generation API by NVIDIA, callable through Superpowers. It costs $0.086 per video, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.cosmos-predict-2.5-distilled-text-to-video", or over MCP with run_tool. 89 other providers in this category take the same input and can be compared side by side.

Tool id
Price per call: $0.086 / video

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.cosmos-predict-2.5-distilled-text-to-video","input":{"prompt":""},"idempotency_key":"example-request-1"}'

Input

8 fields · 1 required

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "sync_mode": {
      "type": "boolean",
      "description": "If `True`, the media will be returned as a data URI and the output data won't be available in the request history.",
      "default": false
    },
    "seed": {
      "type": "integer",
      "description": "Random seed for reproducible generation."
    },
    "video_quality": {
      "type": "string",
      "description": "The quality of the output video.",
      "default": "high",
      "enum": [
        "low",
        "medium",
        "high",
        "maximum"
      ]
    },
    "video_output_type": {
      "type": "string",
      "description": "The format of the output video.",
      "default": "X264 (.mp4)",
      "enum": [
        "X264 (.mp4)",
        "VP9 (.webm)",
        "PRORES4444 (.mov)",
        "GIF (.gif)"
      ]
    },
    "num_inference_steps": {
      "type": "integer",
      "description": "Number of denoising steps. Distilled model works well with fewer steps.",
      "default": 10
    },
    "negative_prompt": {
      "type": "string",
      "description": "A negative prompt to guide generation away from undesired content.",
      "default": "The video captures a series of frames showing ugly scenes, 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, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality."
    },
    "prompt": {
      "type": "string",
      "description": "The text prompt describing the video to generate."
    },
    "num_frames": {
      "type": "integer",
      "description": "Number of frames to generate. Must be between 9 and 93.",
      "default": 93
    }
  }
}