SeedVR2 Video Upscaler

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "seed-vr-upscale-video",
  "prompt": "A torch-lit dungeon corridor, slow dolly forward",
  "batch_size": 1
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/bytedance-seedvr-upscale-video/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "guidance_file_init_video": [
          {
            "url": "https://example.com/input.png"
          }
        ]
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

quality

enumdefault XHIGH4 options

Higher levels render more detail, and can take longer and cost more.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

upscale_factor

enumdefault 22, 4, 8

How many times larger the output is than the source.

creativity

number0–1

How much new detail the model may invent. Higher can drift from the source.

guidance_file_init_video

file[]required

The video to modify