iceclear / stablesr

Exploiting Diffusion Prior for Real-World Image Super-Resolution

  • Public
  • 5.1K runs
  • A100 (80GB)
  • GitHub
  • Paper
  • License
Iterate in playground
  • Prediction

    iceclear/stablesr:01e431cbcf30e2307c61dadca4db988411bc297d35f9bcad8b84ec1462cfe51b
    ID
    vwqsxtrbx64uwtd2aetfzir55a
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (40GB)
    Total duration
    Created

    Input

    seed
    42
    upscale
    4
    ddpm_steps
    200
    input_image
    input_image
    tile_overlap
    32
    colorfix_type
    adain
    fidelity_weight
    0.5

    Output

    output
    Generated in
  • Prediction

    iceclear/stablesr:01e431cbcf30e2307c61dadca4db988411bc297d35f9bcad8b84ec1462cfe51b
    ID
    csrc6njbe6n7dtsgg7szvumlpm
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (40GB)
    Total duration
    Created

    Input

    seed
    42
    upscale
    4
    ddpm_steps
    200
    input_image
    input_image
    tile_overlap
    32
    colorfix_type
    adain
    fidelity_weight
    0.5

    Output

    output
    Generated in
  • Prediction

    iceclear/stablesr:01e431cbcf30e2307c61dadca4db988411bc297d35f9bcad8b84ec1462cfe51b
    ID
    3qdszwbbcnet72dzpozws6zx2i
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (40GB)
    Total duration
    Created

    Input

    seed
    42
    upscale
    4
    ddpm_steps
    200
    input_image
    input_image
    tile_overlap
    32
    colorfix_type
    adain
    fidelity_weight
    0.5

    Output

    output
    Generated in

Want to make some of these yourself?

Run this model