replicatemodel/swinir_t4 ❓🖼️🔢 → 🖼️

▶️ 931 runs 📅 Jan 2024 ⚙️ Cog 0.8.5 🔗 GitHub 📄 Paper ⚖️ License
image-restoration image-upscaling jpeg-artifact-reduction

About

Cheaper model SwinIR: Image Restoration Using Swin Transformer (analogue of the popular model: jingyunliang/swinir)

Example Output

Output

Example output

Performance Metrics

8.70s Prediction Time
181.72s Total Time
All Input Parameters 
{
  "jpeg": 40,
  "image": "https://replicate.delivery/pbxt/KBiA0eZ0VxcpajZa3dhqcbB9Kgr7ZzgEeZPCXt9uuogmW72P/chip.png",
  "noise": 15,
  "task_type": "Real-World Image Super-Resolution-Large"
}
Input Parameters
jpeg Default: 40
Scale factor, activated for JPEG Compression Artifact Reduction. Leave it as default or arbitrary if other tasks are selected
image (required) Type: string
Input image
noise Default: 15
Noise level, activated for Grayscale Image Denoising and Color Image Denoising. Leave it as default or arbitrary if other tasks are selected
task_type Default: Real-World Image Super-Resolution-Large
Image restoration task type
out_format Default: png
Output image format
out_jpg_quality Type: integerDefault: 95Range: 40 - 100
If the output format is jpg, specify the quality (40...100%)
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
6f3a0035cfa43e83811421021d3360750250d6f527fa06f306d870721edc4447
Version Created
January 9, 2024
Run on Replicate →