typefile
{
"creativity": 0.75,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/LgkVvTO1QLOHtETm0VwlFPEPFTnGGJHO5UpSdFXnjpBwNN3N/upload_2024-9-24_16-24-55.jpg",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 50,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>normal hands with 5 fingers",
"resemblance": 3,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Exponential",
"sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
"seed": 1337,
"sharpen": 0,
"tiling_height": 144,
"tiling_width": 112
}npm install replicate
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=r8_LUb**********************************
This is your API token. Keep it to yourself.
import Replicate from "replicate";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run philz1337x/clarity-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"philz1337x/clarity-upscaler:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
{
input: {
creativity: 0.75,
custom_sd_model: "",
downscaling: false,
downscaling_resolution: 768,
dynamic: 6,
handfix: "disabled",
image: "https://replicate.delivery/pbxt/LgkVvTO1QLOHtETm0VwlFPEPFTnGGJHO5UpSdFXnjpBwNN3N/upload_2024-9-24_16-24-55.jpg",
lora_links: "",
negative_prompt: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
num_inference_steps: 50,
output_format: "png",
pattern: false,
prompt: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>normal hands with 5 fingers",
resemblance: 3,
scale_factor: 4,
scheduler: "DPM++ 3M SDE Exponential",
sd_model: "juggernaut_reborn.safetensors [338b85bc4f]",
seed: 1337,
sharpen: 0,
tiling_height: 144,
tiling_width: 112
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=r8_LUb**********************************
This is your API token. Keep it to yourself.
import replicate
Run philz1337x/clarity-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"philz1337x/clarity-upscaler:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
input={
"creativity": 0.75,
"custom_sd_model": "",
"downscaling": False,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/LgkVvTO1QLOHtETm0VwlFPEPFTnGGJHO5UpSdFXnjpBwNN3N/upload_2024-9-24_16-24-55.jpg",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 50,
"output_format": "png",
"pattern": False,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>normal hands with 5 fingers",
"resemblance": 3,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Exponential",
"sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
"seed": 1337,
"sharpen": 0,
"tiling_height": 144,
"tiling_width": 112
}
)
# To access the file URL:
print(output[0].url())
#=> "http://example.com"
# To write the file to disk:
with open("my-image.png", "wb") as file:
file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=r8_LUb**********************************
This is your API token. Keep it to yourself.
Run philz1337x/clarity-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "philz1337x/clarity-upscaler:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
"input": {
"creativity": 0.75,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/LgkVvTO1QLOHtETm0VwlFPEPFTnGGJHO5UpSdFXnjpBwNN3N/upload_2024-9-24_16-24-55.jpg",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 50,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>normal hands with 5 fingers",
"resemblance": 3,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Exponential",
"sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
"seed": 1337,
"sharpen": 0,
"tiling_height": 144,
"tiling_width": 112
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Loading...
{
"id": "8fv8xgwmthrj40cj5jka6p9q7w",
"model": "philz1337x/clarity-upscaler",
"version": "dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
"input": {
"creativity": 0.75,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/LgkVvTO1QLOHtETm0VwlFPEPFTnGGJHO5UpSdFXnjpBwNN3N/upload_2024-9-24_16-24-55.jpg",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 50,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>normal hands with 5 fingers",
"resemblance": 3,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Exponential",
"sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
"seed": 1337,
"sharpen": 0,
"tiling_height": 144,
"tiling_width": 112
},
"logs": "Running prediction\nUpscale your image 2 times\nUpscaling with scale_factor: 2\n[Tiled Diffusion] upscaling image with 4x-UltraSharp...\n[Tiled Diffusion] ControlNet found, support is enabled.\n2024-09-26 04:46:10,702 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2024-09-26 04:46:10,702 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model from cache: control_v11f1e_sd15_tile\n2024-09-26 04:46:10,713 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2024-09-26 04:46:10,713 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 2048\n2024-09-26 04:46:10,820 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 0.12308573722839355\nMultiDiffusion hooked into 'DPM++ 3M SDE Exponential' sampler, Tile size: 144x112, Tile count: 6, Batch size: 6, Tile batches: 1 (ext: ContrlNet)\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\nMultiDiffusion Sampling: 0%| | 0/5 [00:00<?, ?it/s]\n 0%| | 0/38 [00:00<?, ?it/s]\u001b[A\u001b[A\nTotal progress: 0%| | 0/38 [00:00<?, ?it/s]\u001b[A\n 3%|▎ | 1/38 [00:00<00:27, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 5%|▌ | 2/38 [00:00<00:13, 2.71it/s]\u001b[A\n 5%|▌ | 2/38 [00:01<00:26, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 8%|▊ | 3/38 [00:01<00:18, 1.91it/s]\u001b[A\n 8%|▊ | 3/38 [00:02<00:25, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 11%|█ | 4/38 [00:02<00:20, 1.66it/s]\u001b[A\n 11%|█ | 4/38 [00:02<00:25, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 13%|█▎ | 5/38 [00:02<00:21, 1.54it/s]\u001b[A\n 13%|█▎ | 5/38 [00:03<00:24, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 16%|█▌ | 6/38 [00:03<00:21, 1.47it/s]\u001b[A\n 16%|█▌ | 6/38 [00:04<00:23, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 18%|█▊ | 7/38 [00:04<00:21, 1.43it/s]\u001b[A\n 18%|█▊ | 7/38 [00:05<00:22, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 21%|██ | 8/38 [00:05<00:21, 1.41it/s]\u001b[A\n 21%|██ | 8/38 [00:05<00:22, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 24%|██▎ | 9/38 [00:05<00:20, 1.39it/s]\u001b[A\n 24%|██▎ | 9/38 [00:06<00:21, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 26%|██▋ | 10/38 [00:06<00:20, 1.38it/s]\u001b[A\n 26%|██▋ | 10/38 [00:07<00:20, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 29%|██▉ | 11/38 [00:07<00:19, 1.37it/s]\u001b[A\n 29%|██▉ | 11/38 [00:08<00:19, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 32%|███▏ | 12/38 [00:08<00:19, 1.37it/s]\u001b[A\n 32%|███▏ | 12/38 [00:08<00:19, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 34%|███▍ | 13/38 [00:08<00:18, 1.36it/s]\u001b[A\n 34%|███▍ | 13/38 [00:09<00:18, 1.36it/s]\u001b[A\u001b[A\nTotal progress: 37%|███▋ | 14/38 [00:09<00:17, 1.36it/s]\u001b[A\n 37%|███▋ | 14/38 [00:10<00:17, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 39%|███▉ | 15/38 [00:10<00:16, 1.36it/s]\u001b[A\n 39%|███▉ | 15/38 [00:11<00:16, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 42%|████▏ | 16/38 [00:11<00:16, 1.36it/s]\u001b[A\n 42%|████▏ | 16/38 [00:11<00:16, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 45%|████▍ | 17/38 [00:11<00:15, 1.35it/s]\u001b[A\n 45%|████▍ | 17/38 [00:12<00:15, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 47%|████▋ | 18/38 [00:12<00:14, 1.35it/s]\u001b[A\n 47%|████▋ | 18/38 [00:13<00:14, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 50%|█████ | 19/38 [00:13<00:14, 1.35it/s]\u001b[A\n 50%|█████ | 19/38 [00:14<00:14, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 53%|█████▎ | 20/38 [00:14<00:13, 1.35it/s]\u001b[A\n 53%|█████▎ | 20/38 [00:14<00:13, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 55%|█████▌ | 21/38 [00:14<00:12, 1.35it/s]\u001b[A\n 55%|█████▌ | 21/38 [00:15<00:12, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 58%|█████▊ | 22/38 [00:15<00:11, 1.35it/s]\u001b[A\n 58%|█████▊ | 22/38 [00:16<00:11, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 61%|██████ | 23/38 [00:16<00:11, 1.35it/s]\u001b[A\n 61%|██████ | 23/38 [00:16<00:11, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 63%|██████▎ | 24/38 [00:16<00:10, 1.35it/s]\u001b[A\n 63%|██████▎ | 24/38 [00:17<00:10, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 66%|██████▌ | 25/38 [00:17<00:09, 1.35it/s]\u001b[A\n 66%|██████▌ | 25/38 [00:18<00:09, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 68%|██████▊ | 26/38 [00:18<00:08, 1.35it/s]\u001b[A\n 68%|██████▊ | 26/38 [00:19<00:08, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 71%|███████ | 27/38 [00:19<00:08, 1.35it/s]\u001b[A\n 71%|███████ | 27/38 [00:19<00:08, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 74%|███████▎ | 28/38 [00:19<00:07, 1.35it/s]\u001b[A\n 74%|███████▎ | 28/38 [00:20<00:07, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 76%|███████▋ | 29/38 [00:20<00:06, 1.35it/s]\u001b[A\n 76%|███████▋ | 29/38 [00:21<00:06, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 79%|███████▉ | 30/38 [00:21<00:05, 1.35it/s]\u001b[A\n 79%|███████▉ | 30/38 [00:22<00:05, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 82%|████████▏ | 31/38 [00:22<00:05, 1.35it/s]\u001b[A\n 82%|████████▏ | 31/38 [00:22<00:05, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 84%|████████▍ | 32/38 [00:22<00:04, 1.35it/s]\u001b[A\n 84%|████████▍ | 32/38 [00:23<00:04, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 87%|████████▋ | 33/38 [00:23<00:03, 1.35it/s]\u001b[A\n 87%|████████▋ | 33/38 [00:24<00:03, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 89%|████████▉ | 34/38 [00:24<00:02, 1.35it/s]\u001b[A\n 89%|████████▉ | 34/38 [00:25<00:02, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 92%|█████████▏| 35/38 [00:25<00:02, 1.35it/s]\u001b[A\n 92%|█████████▏| 35/38 [00:25<00:02, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 95%|█████████▍| 36/38 [00:25<00:01, 1.35it/s]\u001b[A\n 95%|█████████▍| 36/38 [00:26<00:01, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 97%|█████████▋| 37/38 [00:26<00:00, 1.35it/s]\u001b[A\n 97%|█████████▋| 37/38 [00:27<00:00, 1.35it/s]\u001b[A\u001b[A\n100%|██████████| 38/38 [00:28<00:00, 1.35it/s]\u001b[A\u001b[A\n100%|██████████| 38/38 [00:28<00:00, 1.35it/s]\nMultiDiffusion Sampling: 50%|█████ | 12/24 [02:23<02:23, 11.96s/it]\nTotal progress: 100%|██████████| 38/38 [00:27<00:00, 1.35it/s]\u001b[A[Tiled VAE]: input_size: torch.Size([1, 4, 256, 256]), tile_size: 128, padding: 11\n[Tiled VAE]: split to 2x2 = 4 tiles. Optimal tile size 128x128, original tile size 128x128\n[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 128 x 128 image\n[Tiled VAE]: Executing Decoder Task Queue: 0%| | 0/492 [00:00<?, ?it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 25%|██▌ | 124/492 [00:00<00:00, 550.79it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 247/492 [00:00<00:00, 604.52it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 75%|███████▌ | 370/492 [00:00<00:00, 623.96it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 492/492 [00:00<00:00, 644.77it/s]\n[Tiled VAE]: Done in 1.385s, max VRAM alloc 6208.339 MB\nTotal progress: 100%|██████████| 38/38 [00:29<00:00, 1.35it/s]\u001b[A\nTotal progress: 100%|██████████| 38/38 [00:29<00:00, 1.31it/s]\nUpscaling with scale_factor: 2\n[Tiled Diffusion] upscaling image with 4x-UltraSharp...\n[Tiled Diffusion] ControlNet found, support is enabled.\n2024-09-26 04:46:52,849 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2024-09-26 04:46:52,849 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model from cache: control_v11f1e_sd15_tile\n2024-09-26 04:46:53,008 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2024-09-26 04:46:53,008 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 4096\n2024-09-26 04:46:53,426 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 0.5819051265716553\nMultiDiffusion hooked into 'DPM++ 3M SDE Exponential' sampler, Tile size: 144x112, Tile count: 20, Batch size: 7, Tile batches: 3 (ext: ContrlNet)\nMultiDiffusion Sampling: 0%| | 0/114 [00:00<?, ?it/s]\u001b[A\nMultiDiffusion Sampling: 0%| | 0/5 [00:43<?, ?it/s]\n[Tiled VAE]: input_size: torch.Size([1, 3, 4096, 4096]), tile_size: 2048, padding: 32\n[Tiled VAE]: split to 2x2 = 4 tiles. Optimal tile size 2016x2016, original tile size 2048x2048\n[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 2048 x 2048 image\n[Tiled VAE]: Executing Encoder Task Queue: 0%| | 0/364 [00:00<?, ?it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 5%|▌ | 19/364 [00:00<00:08, 42.78it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 7%|▋ | 24/364 [00:00<00:08, 40.55it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 10%|█ | 38/364 [00:01<00:09, 35.53it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 12%|█▏ | 42/364 [00:01<00:09, 34.06it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 16%|█▌ | 57/364 [00:01<00:08, 34.23it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 17%|█▋ | 61/364 [00:01<00:09, 33.16it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 21%|██ | 76/364 [00:02<00:08, 33.70it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 22%|██▏ | 80/364 [00:02<00:10, 27.18it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 23%|██▎ | 83/364 [00:02<00:13, 21.44it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 24%|██▎ | 86/364 [00:03<00:15, 17.64it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 25%|██▌ | 92/364 [00:03<00:12, 21.96it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 26%|██▌ | 95/364 [00:03<00:20, 13.45it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 27%|██▋ | 97/364 [00:03<00:18, 14.14it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 27%|██▋ | 99/364 [00:04<00:30, 8.82it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 28%|██▊ | 103/364 [00:04<00:27, 9.39it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 29%|██▉ | 105/364 [00:05<00:31, 8.33it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 29%|██▉ | 107/364 [00:05<00:26, 9.54it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 30%|██▉ | 109/364 [00:05<00:29, 8.66it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 31%|███ | 112/364 [00:06<00:29, 8.65it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 115/364 [00:06<00:29, 8.44it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 118/364 [00:06<00:29, 8.32it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 34%|███▍ | 124/364 [00:06<00:18, 13.32it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 35%|███▍ | 126/364 [00:07<00:17, 13.41it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 36%|███▌ | 130/364 [00:07<00:14, 15.90it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 36%|███▋ | 132/364 [00:07<00:15, 15.46it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 134/364 [00:07<00:15, 14.95it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 136/364 [00:07<00:14, 15.91it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 138/364 [00:07<00:14, 15.39it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 140/364 [00:07<00:15, 14.84it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 39%|███▉ | 142/364 [00:08<00:13, 15.96it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 40%|███▉ | 144/364 [00:08<00:14, 15.37it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 41%|████ | 148/364 [00:08<00:12, 17.67it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 41%|████▏ | 151/364 [00:08<00:11, 17.85it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 42%|████▏ | 154/364 [00:08<00:11, 18.03it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 44%|████▍ | 161/364 [00:08<00:08, 23.92it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 45%|████▌ | 164/364 [00:09<00:08, 22.22it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 46%|████▌ | 167/364 [00:09<00:12, 15.45it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 47%|████▋ | 171/364 [00:09<00:11, 16.96it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 48%|████▊ | 173/364 [00:09<00:12, 15.36it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 48%|████▊ | 176/364 [00:10<00:12, 15.35it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 49%|████▉ | 180/364 [00:10<00:10, 16.96it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 50%|█████ | 183/364 [00:10<00:10, 16.60it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 51%|█████ | 186/364 [00:10<00:10, 16.37it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 54%|█████▎ | 195/364 [00:10<00:05, 28.61it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 55%|█████▌ | 201/364 [00:10<00:04, 34.54it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 57%|█████▋ | 207/364 [00:10<00:03, 39.77it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 59%|█████▉ | 216/364 [00:11<00:02, 49.40it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 63%|██████▎ | 228/364 [00:11<00:02, 66.20it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 66%|██████▌ | 240/364 [00:11<00:01, 73.39it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 69%|██████▉ | 251/364 [00:11<00:01, 80.27it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 72%|███████▏ | 262/364 [00:11<00:01, 87.24it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 75%|███████▍ | 272/364 [00:11<00:01, 85.56it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 78%|███████▊ | 283/364 [00:11<00:00, 89.40it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 82%|████████▏ | 298/364 [00:11<00:00, 99.25it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 85%|████████▍ | 309/364 [00:12<00:00, 83.80it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 87%|████████▋ | 318/364 [00:12<00:01, 44.97it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 89%|████████▉ | 325/364 [00:13<00:01, 29.65it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 92%|█████████▏| 334/364 [00:13<00:00, 36.29it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 98%|█████████▊| 356/364 [00:13<00:00, 62.00it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 100%|██████████| 364/364 [00:13<00:00, 27.45it/s]\n[Tiled VAE]: Done in 13.946s, max VRAM alloc 8676.637 MB\n 0%| | 0/31 [00:00<?, ?it/s]\nMultiDiffusion Sampling: 1%| | 1/114 [00:14<27:43, 14.72s/it]\u001b[A\nMultiDiffusion Sampling: 2%|▏ | 2/114 [00:15<12:14, 6.56s/it]\u001b[A\nTotal progress: 0%| | 0/31 [00:00<?, ?it/s]\u001b[A\n 3%|▎ | 1/31 [00:02<01:13, 2.44s/it]\n 6%|▋ | 2/31 [00:04<01:10, 2.45s/it]\nMultiDiffusion Sampling: 3%|▎ | 3/114 [00:20<10:44, 5.80s/it]\u001b[A\nTotal progress: 6%|▋ | 2/31 [00:02<00:35, 1.23s/it]\u001b[A\nMultiDiffusion Sampling: 4%|▎ | 4/114 [00:21<07:00, 3.82s/it]\u001b[A\n 10%|▉ | 3/31 [00:07<01:08, 2.45s/it]\nMultiDiffusion Sampling: 4%|▍ | 5/114 [00:22<05:31, 3.04s/it]\u001b[A\nTotal progress: 10%|▉ | 3/31 [00:04<00:48, 1.74s/it]\u001b[A\nMultiDiffusion Sampling: 5%|▌ | 6/114 [00:23<04:06, 2.28s/it]\u001b[A\n 13%|█▎ | 4/31 [00:09<01:06, 2.45s/it]\nMultiDiffusion Sampling: 6%|▌ | 7/114 [00:25<03:42, 2.08s/it]\u001b[A\nTotal progress: 13%|█▎ | 4/31 [00:07<00:54, 2.01s/it]\u001b[A\nMultiDiffusion Sampling: 7%|▋ | 8/114 [00:26<02:56, 1.67s/it]\u001b[A\n 16%|█▌ | 5/31 [00:12<01:03, 2.45s/it]\nMultiDiffusion Sampling: 8%|▊ | 9/114 [00:27<02:55, 1.67s/it]\u001b[A\nTotal progress: 16%|█▌ | 5/31 [00:09<00:56, 2.16s/it]\u001b[A\nMultiDiffusion Sampling: 9%|▉ | 10/114 [00:28<02:25, 1.40s/it]\u001b[A\n 19%|█▉ | 6/31 [00:14<01:01, 2.46s/it]\nMultiDiffusion Sampling: 10%|▉ | 11/114 [00:30<02:32, 1.48s/it]\u001b[A\nTotal progress: 19%|█▉ | 6/31 [00:12<00:56, 2.26s/it]\u001b[A\nMultiDiffusion Sampling: 11%|█ | 12/114 [00:31<02:09, 1.27s/it]\u001b[A\n 23%|██▎ | 7/31 [00:17<00:59, 2.46s/it]\nMultiDiffusion Sampling: 11%|█▏ | 13/114 [00:32<02:20, 1.39s/it]\u001b[A\nTotal progress: 23%|██▎ | 7/31 [00:14<00:55, 2.33s/it]\u001b[A\nMultiDiffusion Sampling: 12%|█▏ | 14/114 [00:33<02:01, 1.21s/it]\u001b[A\n 26%|██▌ | 8/31 [00:19<00:56, 2.46s/it]\nMultiDiffusion Sampling: 13%|█▎ | 15/114 [00:35<02:13, 1.35s/it]\u001b[A\nTotal progress: 26%|██▌ | 8/31 [00:17<00:54, 2.37s/it]\u001b[A\nMultiDiffusion Sampling: 14%|█▍ | 16/114 [00:36<01:55, 1.18s/it]\u001b[A\n 29%|██▉ | 9/31 [00:22<00:54, 2.46s/it]\nMultiDiffusion Sampling: 15%|█▍ | 17/114 [00:37<02:08, 1.33s/it]\u001b[A\nTotal progress: 29%|██▉ | 9/31 [00:19<00:52, 2.40s/it]\u001b[A\nMultiDiffusion Sampling: 16%|█▌ | 18/114 [00:38<01:52, 1.17s/it]\u001b[A\n 32%|███▏ | 10/31 [00:24<00:51, 2.46s/it]\nMultiDiffusion Sampling: 17%|█▋ | 19/114 [00:40<02:05, 1.32s/it]\u001b[A\nTotal progress: 32%|███▏ | 10/31 [00:22<00:50, 2.42s/it]\u001b[A\nMultiDiffusion Sampling: 18%|█▊ | 20/114 [00:40<01:49, 1.16s/it]\u001b[A\n 35%|███▌ | 11/31 [00:27<00:49, 2.46s/it]\nMultiDiffusion Sampling: 18%|█▊ | 21/114 [00:42<02:02, 1.31s/it]\u001b[A\nTotal progress: 35%|███▌ | 11/31 [00:24<00:48, 2.43s/it]\u001b[A\nMultiDiffusion Sampling: 19%|█▉ | 22/114 [00:43<01:46, 1.16s/it]\u001b[A\n 39%|███▊ | 12/31 [00:29<00:46, 2.46s/it]\nMultiDiffusion Sampling: 20%|██ | 23/114 [00:45<01:59, 1.31s/it]\u001b[A\nTotal progress: 39%|███▊ | 12/31 [00:27<00:46, 2.44s/it]\u001b[A\nMultiDiffusion Sampling: 21%|██ | 24/114 [00:45<01:44, 1.16s/it]\u001b[A\n 42%|████▏ | 13/31 [00:31<00:44, 2.46s/it]\nMultiDiffusion Sampling: 22%|██▏ | 25/114 [00:47<01:56, 1.31s/it]\u001b[A\nTotal progress: 42%|████▏ | 13/31 [00:29<00:44, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 23%|██▎ | 26/114 [00:48<01:41, 1.16s/it]\u001b[A\n 45%|████▌ | 14/31 [00:34<00:41, 2.46s/it]\nMultiDiffusion Sampling: 24%|██▎ | 27/114 [00:50<01:54, 1.31s/it]\u001b[A\nTotal progress: 45%|████▌ | 14/31 [00:31<00:41, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 25%|██▍ | 28/114 [00:50<01:39, 1.16s/it]\u001b[A\n 48%|████▊ | 15/31 [00:36<00:39, 2.46s/it]\nMultiDiffusion Sampling: 25%|██▌ | 29/114 [00:52<01:51, 1.31s/it]\u001b[A\nTotal progress: 48%|████▊ | 15/31 [00:34<00:39, 2.46s/it]\u001b[A\nMultiDiffusion Sampling: 26%|██▋ | 30/114 [00:53<01:37, 1.16s/it]\u001b[A\n 52%|█████▏ | 16/31 [00:39<00:36, 2.46s/it]\nMultiDiffusion Sampling: 27%|██▋ | 31/114 [00:54<01:48, 1.31s/it]\u001b[A\nTotal progress: 52%|█████▏ | 16/31 [00:36<00:36, 2.46s/it]\u001b[A\nMultiDiffusion Sampling: 28%|██▊ | 32/114 [00:55<01:34, 1.15s/it]\u001b[A\n 55%|█████▍ | 17/31 [00:41<00:34, 2.46s/it]\nMultiDiffusion Sampling: 29%|██▉ | 33/114 [00:57<01:46, 1.31s/it]\u001b[A\nTotal progress: 55%|█████▍ | 17/31 [00:39<00:34, 2.46s/it]\u001b[A\nMultiDiffusion Sampling: 30%|██▉ | 34/114 [00:58<01:32, 1.16s/it]\u001b[A\n 58%|█████▊ | 18/31 [00:44<00:32, 2.46s/it]\nMultiDiffusion Sampling: 31%|███ | 35/114 [00:59<01:43, 1.31s/it]\u001b[A\nTotal progress: 58%|█████▊ | 18/31 [00:41<00:32, 2.46s/it]\u001b[A\nMultiDiffusion Sampling: 32%|███▏ | 36/114 [01:00<01:30, 1.16s/it]\u001b[A\n 61%|██████▏ | 19/31 [00:46<00:29, 2.47s/it]\nMultiDiffusion Sampling: 32%|███▏ | 37/114 [01:02<01:40, 1.31s/it]\u001b[A\nTotal progress: 61%|██████▏ | 19/31 [00:44<00:29, 2.46s/it]\u001b[A\nMultiDiffusion Sampling: 33%|███▎ | 38/114 [01:03<01:27, 1.16s/it]\u001b[A\n 65%|██████▍ | 20/31 [00:49<00:27, 2.47s/it]\nMultiDiffusion Sampling: 34%|███▍ | 39/114 [01:04<01:38, 1.31s/it]\u001b[A\nTotal progress: 65%|██████▍ | 20/31 [00:46<00:27, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 35%|███▌ | 40/114 [01:05<01:25, 1.16s/it]\u001b[A\n 68%|██████▊ | 21/31 [00:51<00:24, 2.47s/it]\nMultiDiffusion Sampling: 36%|███▌ | 41/114 [01:07<01:35, 1.31s/it]\u001b[A\nTotal progress: 68%|██████▊ | 21/31 [00:49<00:24, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 37%|███▋ | 42/114 [01:08<01:23, 1.16s/it]\u001b[A\n 71%|███████ | 22/31 [00:54<00:22, 2.47s/it]\nMultiDiffusion Sampling: 38%|███▊ | 43/114 [01:09<01:33, 1.31s/it]\u001b[A\nTotal progress: 71%|███████ | 22/31 [00:51<00:22, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 39%|███▊ | 44/114 [01:10<01:20, 1.16s/it]\u001b[A\n 74%|███████▍ | 23/31 [00:56<00:19, 2.47s/it]\nMultiDiffusion Sampling: 39%|███▉ | 45/114 [01:12<01:30, 1.31s/it]\u001b[A\nTotal progress: 74%|███████▍ | 23/31 [00:54<00:19, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 40%|████ | 46/114 [01:13<01:18, 1.16s/it]\u001b[A\n 77%|███████▋ | 24/31 [00:59<00:17, 2.47s/it]\nMultiDiffusion Sampling: 41%|████ | 47/114 [01:14<01:27, 1.31s/it]\u001b[A\nTotal progress: 77%|███████▋ | 24/31 [00:56<00:17, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 42%|████▏ | 48/114 [01:15<01:16, 1.16s/it]\u001b[A\n 81%|████████ | 25/31 [01:01<00:14, 2.47s/it]\nMultiDiffusion Sampling: 43%|████▎ | 49/114 [01:17<01:25, 1.31s/it]\u001b[A\nTotal progress: 81%|████████ | 25/31 [00:59<00:14, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 44%|████▍ | 50/114 [01:17<01:14, 1.16s/it]\u001b[A\n 84%|████████▍ | 26/31 [01:04<00:12, 2.47s/it]\nMultiDiffusion Sampling: 45%|████▍ | 51/114 [01:19<01:22, 1.31s/it]\u001b[A\nTotal progress: 84%|████████▍ | 26/31 [01:01<00:12, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 46%|████▌ | 52/114 [01:20<01:11, 1.16s/it]\u001b[A\n 87%|████████▋ | 27/31 [01:06<00:09, 2.47s/it]\nMultiDiffusion Sampling: 46%|████▋ | 53/114 [01:22<01:20, 1.31s/it]\u001b[A\nTotal progress: 87%|████████▋ | 27/31 [01:04<00:09, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 47%|████▋ | 54/114 [01:22<01:09, 1.16s/it]\u001b[A\n 90%|█████████ | 28/31 [01:08<00:07, 2.47s/it]\nMultiDiffusion Sampling: 48%|████▊ | 55/114 [01:24<01:17, 1.31s/it]\u001b[A\nTotal progress: 90%|█████████ | 28/31 [01:06<00:07, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 49%|████▉ | 56/114 [01:25<01:07, 1.16s/it]\u001b[A\n 94%|█████████▎| 29/31 [01:11<00:04, 2.47s/it]\nMultiDiffusion Sampling: 50%|█████ | 57/114 [01:27<01:14, 1.31s/it]\u001b[A\nTotal progress: 94%|█████████▎| 29/31 [01:09<00:04, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 51%|█████ | 58/114 [01:27<01:04, 1.16s/it]\u001b[A\n 97%|█████████▋| 30/31 [01:13<00:02, 2.47s/it]\nMultiDiffusion Sampling: 52%|█████▏ | 59/114 [01:29<01:12, 1.31s/it]\u001b[A\nTotal progress: 97%|█████████▋| 30/31 [01:11<00:02, 2.47s/it]\u001b[A\nMultiDiffusion Sampling: 53%|█████▎ | 60/114 [01:30<01:02, 1.16s/it]\u001b[A\n100%|██████████| 31/31 [01:16<00:00, 2.47s/it]\n100%|██████████| 31/31 [01:16<00:00, 2.46s/it]\nTotal progress: 100%|██████████| 31/31 [01:13<00:00, 2.47s/it]\u001b[A[Tiled VAE]: input_size: torch.Size([1, 4, 512, 512]), tile_size: 128, padding: 11\n[Tiled VAE]: split to 4x4 = 16 tiles. Optimal tile size 128x128, original tile size 128x128\n[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 128 x 128 image\n[Tiled VAE]: Executing Decoder Task Queue: 0%| | 0/1968 [00:00<?, ?it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 6%|▋ | 124/1968 [00:00<00:03, 549.87it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 13%|█▎ | 247/1968 [00:00<00:03, 548.17it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 19%|█▉ | 370/1968 [00:00<00:02, 546.76it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 25%|██▌ | 493/1968 [00:00<00:02, 582.75it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 31%|███▏ | 616/1968 [00:01<00:02, 568.75it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 38%|███▊ | 739/1968 [00:01<00:02, 560.74it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 44%|████▍ | 862/1968 [00:01<00:01, 556.13it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 985/1968 [00:01<00:01, 583.20it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 56%|█████▋ | 1108/1968 [00:01<00:01, 570.79it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 63%|██████▎ | 1231/1968 [00:02<00:01, 562.86it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 69%|██████▉ | 1354/1968 [00:02<00:01, 557.37it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 75%|███████▌ | 1477/1968 [00:02<00:00, 582.12it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 81%|████████▏ | 1600/1968 [00:02<00:00, 600.64it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 88%|████████▊ | 1723/1968 [00:02<00:00, 614.77it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 94%|█████████▍| 1846/1968 [00:03<00:00, 624.46it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 1968/1968 [00:03<00:00, 591.83it/s]\n[Tiled VAE]: Done in 4.005s, max VRAM alloc 6731.147 MB\nTotal progress: 100%|██████████| 31/31 [01:18<00:00, 2.47s/it]\u001b[A\nTotal progress: 100%|██████████| 31/31 [01:18<00:00, 2.54s/it]\nPrediction took 149.03 seconds",
"output": [
"https://replicate.delivery/yhqm/gly0vP85KWr5Ftjww8zeK4JMO1ESUCmea4J1x3N1lZ0kmpgTA/1338-950c2c80-7bc2-11ef-a324-a6fddc8e9df2.png"
],
"data_removed": false,
"error": null,
"source": "web",
"status": "succeeded",
"created_at": "2024-09-26T04:46:07.572Z",
"started_at": "2024-09-26T04:46:07.584529Z",
"completed_at": "2024-09-26T04:48:37.487469Z",
"urls": {
"cancel": "https://api.replicate.com/v1/predictions/8fv8xgwmthrj40cj5jka6p9q7w/cancel",
"get": "https://api.replicate.com/v1/predictions/8fv8xgwmthrj40cj5jka6p9q7w",
"web": "https://replicate.com/p/8fv8xgwmthrj40cj5jka6p9q7w"
},
"metrics": {
"predict_time": 149.902939911,
"total_time": 149.915469
}
}