cjwbw/supir 🔢🖼️📝✓❓ → 🖼️
About
Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This version uses LLaVA-13b for captioning.

Example Output
Output

Performance Metrics
18.57s
Prediction Time
859.90s
Total Time
All Input Parameters
{ "image": "https://replicate.delivery/pbxt/KSFJ6sJWyEiPWysywNsAr2enzigJA3NZpG4YMrxrSFEIEShi/05.png", "s_cfg": 7.5, "s_churn": 5, "s_noise": 1.003, "upscale": 1, "a_prompt": "Cinematic, High Contrast, highly detailed, taken using a Canon EOS R camera, hyper detailed photo - realistic maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect without deformations.", "min_size": 1024, "n_prompt": "painting, oil painting, illustration, drawing, art, sketch, oil painting, cartoon, CG Style, 3D render, unreal engine, blurring, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth", "s_stage1": -1, "s_stage2": 1, "edm_steps": 50, "use_llava": true, "linear_CFG": false, "model_name": "SUPIR-v0Q", "color_fix_type": "Wavelet", "spt_linear_CFG": 1, "linear_s_stage2": false, "spt_linear_s_stage2": 0 }
Input Parameters
- seed
- Random seed. Leave blank to randomize the seed
- image (required)
- Low quality input image.
- s_cfg
- Classifier-free guidance scale for prompts.
- s_churn
- Original churn hy-param of EDM.
- s_noise
- Original noise hy-param of EDM.
- upscale
- Upsampling ratio of given inputs.
- a_prompt
- Additive positive prompt for the inputs.
- min_size
- Minimum resolution of output images.
- n_prompt
- Negative prompt for the inputs.
- s_stage1
- Control Strength of Stage1 (negative means invalid).
- s_stage2
- Control Strength of Stage2.
- edm_steps
- Number of steps for EDM Sampling Schedule.
- use_llava
- Use LLaVA model to get captions.
- linear_CFG
- Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg.
- model_name
- Choose a model. SUPIR-v0Q is the default training settings with paper. SUPIR-v0F is high generalization and high image quality in most cases. Training with light degradation settings. Stage1 encoder of SUPIR-v0F remains more details when facing light degradations.
- color_fix_type
- Color Fixing Type..
- spt_linear_CFG
- Start point of linearly increasing CFG.
- linear_s_stage2
- Linearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2.
- spt_linear_s_stage2
- Start point of linearly increasing s_stage2.
Output Schema
Output
Example Execution Logs
Using seed: 12774 Captions from LLaVA: ['The image features a beautiful bird perched on a thin, dry branch in a field. The bird is colorful and stands out against the brown background of the field. The branch is located in the middle of the scene, with the bird sitting on it, drawing attention to itself. The field is filled with a variety of flowers, adding a vibrant touch to the scene. The overall style of the image is artistic, with a focus on the bird and its natural surroundings.'] Seed set to 12774
Version Details
- Version ID
1302b550b4f7681da87ed0e405016d443fe1fafd64dabce6673401855a5039b5
- Version Created
- February 23, 2024