prakharsaxena24/masked-upscaler 🖼️🔢📝 → 🖼️

▶️ 4.8K runs 📅 May 2024 ⚙️ Cog 0.9.8

image-editing image-upscaling

About

Upscaler and detailer for a selected area

Example Output

Prompt:

"masterpiece, best quality, highres, lora:more_details:0.5 lora:SDXLrender_v2.0:1"

Output

Performance Metrics

9.20s Prediction Time

132.45s Total Time

All Input Parameters

{
  "mask": "https://replicate.delivery/pbxt/L293tY1UNaSlq01zA1VCCkNyv49jD4Ab3QrMau376xUON56q/inverse_image_mask.png",
  "seed": 42,
  "image": "https://replicate.delivery/pbxt/L293tzfx8WiFQQrLRxPMwRwMZHzi9Bs5a1mUOgwySqf77men/img5a21b4bd1c924b0ba6d04f1c75ced25d.png",
  "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
  "scale_factor": 2,
  "num_inference_steps": 20
}

Input Parameters

mask Type: string: Mask image areas to not upscale
seed Type: integerDefault: 42: seed
image (required) Type: string: Input image
prompt Type: stringDefault: masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>: Prompt
scale_factor Type: numberDefault: 2: Scale by factor
num_inference_steps Type: integerDefault: 20Range: 1 - 100: Num of steps

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Running prediction
Upscaling with scale_factor:  2.0
[Tiled Diffusion] upscaling image with 4x-UltraSharp...
[Tiled Diffusion] ControlNet found, support is enabled.
2024-06-03 19:24:07,997 - ControlNet - [0;32mINFO[0m - unit_separate = False, style_align = False
2024-06-03 19:24:07,997 - ControlNet - [0;32mINFO[0m - Loading model from cache: control_v11f1e_sd15_tile
2024-06-03 19:24:08,011 - ControlNet - [0;32mINFO[0m - Using preprocessor: tile_resample
2024-06-03 19:24:08,011 - ControlNet - [0;32mINFO[0m - preprocessor resolution = 950
2024-06-03 19:24:08,092 - ControlNet - [0;32mINFO[0m - ControlNet Hooked - Time = 0.1022803783416748
MultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 118x112, Tile count: 3, Batch size: 3, Tile batches: 1 (ext: ContrlNet)
[Tiled VAE]: the input size is tiny and unnecessary to tile.
MultiDiffusion Sampling:   0%|          | 0/1 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s][A
Total progress:   0%|          | 0/8 [00:00<?, ?it/s][A
 12%|█▎        | 1/8 [00:01<00:07,  1.01s/it][A
Total progress:  25%|██▌       | 2/8 [00:00<00:00,  6.32it/s][A
 25%|██▌       | 2/8 [00:01<00:03,  1.66it/s][A
Total progress:  38%|███▊      | 3/8 [00:00<00:01,  4.51it/s][A
 38%|███▊      | 3/8 [00:01<00:02,  2.13it/s][A
Total progress:  50%|█████     | 4/8 [00:00<00:01,  3.91it/s][A
 50%|█████     | 4/8 [00:01<00:01,  2.45it/s][A
Total progress:  62%|██████▎   | 5/8 [00:01<00:00,  3.63it/s][A
 62%|██████▎   | 5/8 [00:02<00:01,  2.68it/s][A
Total progress:  75%|███████▌  | 6/8 [00:01<00:00,  3.48it/s][A
 75%|███████▌  | 6/8 [00:02<00:00,  2.84it/s][A
Total progress:  88%|████████▊ | 7/8 [00:01<00:00,  3.38it/s][A
 88%|████████▊ | 7/8 [00:02<00:00,  2.96it/s][A
100%|██████████| 8/8 [00:03<00:00,  3.05it/s][A
100%|██████████| 8/8 [00:03<00:00,  2.51it/s]
Total progress: 100%|██████████| 8/8 [00:02<00:00,  3.33it/s][A[Tiled VAE]: input_size: torch.Size([1, 4, 118, 250]), tile_size: 128, padding: 11
[Tiled VAE]: split to 1x2 = 2 tiles. Optimal tile size 128x96, original tile size 128x128
[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 128 x 60 image
[Tiled VAE]: Executing Decoder Task Queue:   0%|          | 0/246 [00:00<?, ?it/s][A[A
[Tiled VAE]: Executing Decoder Task Queue:  50%|█████     | 124/246 [00:00<00:00, 672.41it/s][A[A
[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 246/246 [00:00<00:00, 744.19it/s]
[Tiled VAE]: Done in 0.965s, max VRAM alloc 5375.187 MB
Total progress: 100%|██████████| 8/8 [00:03<00:00,  3.33it/s][A
Total progress: 100%|██████████| 8/8 [00:03<00:00,  2.30it/s]
Prediction took 8.56 seconds

Version Details

Version ID: 0e864cd4844ac63d862efd3468e4c55219066351009db73833ad67f98c5eaefb
Version Created: June 3, 2024

Run on Replicate →