ENPTEntrarGanhe US$ 5

FlashVSR+

Edits a video you give it

Liveby OpenImagingLab

FlashVSR+ upscales video by up to 4x with a one-step diffusion model, offering a fast Turbo mode and a higher-quality Base mode.

Output reaches about 4K, and the input audio track is preserved by default.

Ask your agent

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

CodexClaude CodeAny agent with a terminal

Use FlashVSR+ to make this clip look like it was shot at night.

More examples

Change the background of this video to a beach.

Reviews

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

How it works

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

Video API by OpenImagingLab, callable through Superpowers. It costs $0.00054 per megapixel, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.openimaginglab-flashvsr-plus", or over MCP with run_tool.

Tool id
Price per call
$0.00054 / megapixel

Call it

Also over MCP as run_tool
curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.openimaginglab-flashvsr-plus","input":{"video_url":""},"idempotency_key":"example-request-1"}'

Input

12 fields · 1 required
{
  "type": "object",
  "required": [
    "video_url"
  ],
  "properties": {
    "preserve_audio": {
      "type": "boolean",
      "description": "Copy the input audio track into the output.",
      "default": true
    },
    "upscale_factor": {
      "type": "number",
      "description": "Spatial upscaling factor. Output is capped at about 4K.",
      "default": 2
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Authorized callers may set false to request relaxed screening.",
      "default": true
    },
    "seed": {
      "type": "integer",
      "description": "The random seed used for the generation process."
    },
    "sync_mode": {
      "type": "boolean",
      "description": "If `True`, the media will be returned inline and not stored in history.",
      "default": false
    },
    "video_write_mode": {
      "type": "string",
      "description": "Output write mode.",
      "default": "balanced",
      "enum": [
        "fast",
        "balanced",
        "small"
      ]
    },
    "video_quality": {
      "type": "string",
      "description": "Output encoding quality.",
      "default": "high",
      "enum": [
        "low",
        "medium",
        "high",
        "maximum"
      ]
    },
    "temporal_compression": {
      "type": "integer",
      "description": "Input frames per latent frame. Use 2 or 1 for large motion; inference cost rises about 2x or 4x.",
      "default": 4,
      "enum": [
        1,
        2,
        4
      ]
    },
    "video_url": {
      "type": "string",
      "description": "The input video to upscale."
    },
    "video_output_type": {
      "type": "string",
      "description": "Output container/codec.",
      "default": "X264 (.mp4)",
      "enum": [
        "X264 (.mp4)",
        "VP9 (.webm)",
        "PRORES4444 (.mov)",
        "GIF (.gif)"
      ]
    },
    "model": {
      "type": "string",
      "description": "turbo: fastest (hybrid sliding attention). base: highest quality. v1: FlashVSR v1.1 weights with the base configuration.",
      "default": "turbo",
      "enum": [
        "turbo",
        "base",
        "v1"
      ]
    },
    "color_fix": {
      "type": "boolean",
      "description": "Apply low-frequency wavelet color correction.",
      "default": false
    }
  }
}