Seedvr2 Image
Playground
Try it on WavespeedAI!The SeedVR2 image upscaler is a powerful tool designed to enhance the resolution and quality of image. Our model allows users to choose different levels of enhancement by adjusting the value of creativity.
Features
WaveSpeedAI — SeedVR2 Image Upscaler
The SeedVR2 Image Upscaler boosts image resolution while preserving real-world texture, edge sharpness, and fine detail. It uses deep-learning super-resolution to reduce blur and compression artifacts, producing clean outputs for design, photography, and AI artwork.
✨ Key Features
- Multi-step super-resolution — upscale to 2K, 4K, or 8K.
- Detail preservation — keeps textures/edges natural without ringing or halo artifacts.
- Adaptive enhancement — a creativity control lets you balance faithful restoration vs. assertive enhancement.
- Flexible exports — output as JPEG, PNG, or WEBP.
- Fast & efficient — optimized inference for high-res workflows.
🧩 Parameters
- 
image* (required) Source image (URL or upload). 
- 
creativity (slider / integer) Controls how strongly the upscaler tries to improve quality. Lower = faithful, Higher = more reconstruction and texture synthesis. 
- 
target_resolution (dropdown) Upscale target: 2k, 4k, 8k. 
- 
output_format (dropdown) jpeg, png, or webp. 
🚀 How to Use
- 
Upload/Paste image (required) — start with the best available source. 
- 
Set target_resolution to 2k, 4k, or 8k based on delivery needs. 
- 
Adjust creativity: - Lower values for documentary/product fidelity.
- Higher values to recover textures in AI art or heavily compressed sources.
 
- 
Choose output_format (jpeg for web, png for lossless alpha-free work, webp for compact delivery). 
- 
Click Run to generate and download your upscaled image. 
💰 Pricing
- Per run: $0.01
💡 Recommended Use Cases
- Professional photo restoration and large-format prints
- AI artwork sharpening and artifact cleanup
- Product imagery & marketing assets
- Upscaling low-res screenshots and video stills
📝 Notes & Tips
- Garbage in, garbage out: very tiny sources upscale better to 2K first; evaluate, then jump to 4K/8K.
- For strict brand colors or typography, keep creativity lower to avoid over-synthesis.
- Use PNG when you plan to do further editing; use WEBP/JPEG for web delivery.
- For ultra quality, you can try Ultimate Image Upscaler.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/seedvr2/image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "creativity": 0,
    "target_resolution": "4k",
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description | 
|---|---|---|---|---|---|
| image | string | Yes | - | The URL of the image to generate an image from. | |
| creativity | number | No | - | -2 ~ 2 | Controls how strongly the upscaler will try to improve the image quality. | 
| target_resolution | string | No | 4k | 2k, 4k, 8k | The target resolution of the generated media. | 
| output_format | string | No | jpeg | jpeg, png, webp | The format of the output image. | 
| enable_base64_output | boolean | No | false | - | If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API. | 
| enable_sync_mode | boolean | No | false | - | If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API. | 
Response Parameters
| Parameter | Type | Description | 
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) | 
| message | string | Status message (e.g., “success”) | 
| data.id | string | Unique identifier for the prediction, Task Id | 
| data.model | string | Model ID used for the prediction | 
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) | 
| data.urls | object | Object containing related API endpoints | 
| data.urls.get | string | URL to retrieve the prediction result | 
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output | 
| data.status | string | Status of the task: created,processing,completed, orfailed | 
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) | 
| data.error | string | Error message (empty if no error occurred) | 
| data.timings | object | Object containing timing details | 
| data.timings.inference | integer | Inference time in milliseconds |