typefile
{
"creativity": 0.35,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/NFCN3AMb0EBCJDJSnIZsnF6w8GZrnKumiydYrrCQG6Vcwmm2/placeholder_transparent.png",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 18,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
"resemblance": 0.6,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Karras",
"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_A3G**********************************
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: 0.35,
custom_sd_model: "",
downscaling: false,
downscaling_resolution: 768,
dynamic: 6,
handfix: "disabled",
image: "https://replicate.delivery/pbxt/NFCN3AMb0EBCJDJSnIZsnF6w8GZrnKumiydYrrCQG6Vcwmm2/placeholder_transparent.png",
lora_links: "",
negative_prompt: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
num_inference_steps: 18,
output_format: "png",
pattern: false,
prompt: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
resemblance: 0.6,
scale_factor: 4,
scheduler: "DPM++ 3M SDE Karras",
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_A3G**********************************
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": 0.35,
"custom_sd_model": "",
"downscaling": False,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/NFCN3AMb0EBCJDJSnIZsnF6w8GZrnKumiydYrrCQG6Vcwmm2/placeholder_transparent.png",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 18,
"output_format": "png",
"pattern": False,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
"resemblance": 0.6,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Karras",
"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_A3G**********************************
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": 0.35,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/NFCN3AMb0EBCJDJSnIZsnF6w8GZrnKumiydYrrCQG6Vcwmm2/placeholder_transparent.png",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 18,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
"resemblance": 0.6,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Karras",
"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": "dsestetcxnrj40cqmfwvaeqg7c",
"model": "philz1337x/clarity-upscaler",
"version": "dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
"input": {
"creativity": 0.35,
"custom_sd_model": "",
"downscaling": false,
"downscaling_resolution": 768,
"dynamic": 6,
"handfix": "disabled",
"image": "https://replicate.delivery/pbxt/NFCN3AMb0EBCJDJSnIZsnF6w8GZrnKumiydYrrCQG6Vcwmm2/placeholder_transparent.png",
"lora_links": "",
"negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
"num_inference_steps": 18,
"output_format": "png",
"pattern": false,
"prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
"resemblance": 0.6,
"scale_factor": 4,
"scheduler": "DPM++ 3M SDE Karras",
"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.\n2025-06-24 22:05:17,386 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2025-06-24 22:05:17,386 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model from cache: control_v11f1e_sd15_tile\n2025-06-24 22:05:17,415 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2025-06-24 22:05:17,415 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 2048\n2025-06-24 22:05:17,511 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 0.13015222549438477\nMultiDiffusion hooked into 'DPM++ 3M SDE Karras' 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%| | 0/2 [00:00<?, ?it/s]\u001b[A\n 0%| | 0/7 [00:00<?, ?it/s]\u001b[A\u001b[A\nTotal progress: 0%| | 0/7 [00:00<?, ?it/s]\u001b[A\n 14%|█▍ | 1/7 [00:00<00:04, 1.31it/s]\u001b[A\u001b[A\nTotal progress: 29%|██▊ | 2/7 [00:00<00:01, 2.63it/s]\u001b[A\n 29%|██▊ | 2/7 [00:01<00:03, 1.34it/s]\u001b[A\u001b[A\nTotal progress: 43%|████▎ | 3/7 [00:01<00:02, 1.89it/s]\u001b[A\n 43%|████▎ | 3/7 [00:02<00:02, 1.34it/s]\u001b[A\u001b[A\nTotal progress: 57%|█████▋ | 4/7 [00:02<00:01, 1.65it/s]\u001b[A\n 57%|█████▋ | 4/7 [00:02<00:02, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 71%|███████▏ | 5/7 [00:02<00:01, 1.53it/s]\u001b[A\n 71%|███████▏ | 5/7 [00:03<00:01, 1.35it/s]\u001b[A\u001b[A\nTotal progress: 86%|████████▌ | 6/7 [00:03<00:00, 1.47it/s]\u001b[A\n 86%|████████▌ | 6/7 [00:04<00:00, 1.35it/s]\u001b[A\u001b[A\n100%|██████████| 7/7 [00:05<00:00, 1.36it/s]\u001b[A\u001b[A\n100%|██████████| 7/7 [00:05<00:00, 1.35it/s]\nMultiDiffusion Sampling: 0%| | 0/7 [00:19<?, ?it/s]\nTotal progress: 100%|██████████| 7/7 [00:04<00:00, 1.43it/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]\n[Tiled VAE]: Executing Decoder Task Queue: 25%|██▌ | 124/492 [00:00<00:00, 548.01it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 247/492 [00:00<00:00, 601.97it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 75%|███████▌ | 370/492 [00:00<00:00, 621.50it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 492/492 [00:00<00:00, 642.19it/s]\n[Tiled VAE]: Done in 1.446s, max VRAM alloc 6209.335 MB\nTotal progress: 100%|██████████| 7/7 [00:06<00:00, 1.43it/s]\u001b[A\nTotal progress: 100%|██████████| 7/7 [00:06<00:00, 1.13it/s]\nUpscaling with scale_factor: 2\n[Tiled Diffusion] upscaling image with 4x-UltraSharp...\n[Tiled Diffusion] ControlNet found, support is enabled.\n2025-06-24 22:05:36,887 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2025-06-24 22:05:36,888 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model from cache: control_v11f1e_sd15_tile\n2025-06-24 22:05:36,959 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2025-06-24 22:05:36,959 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 4096\n2025-06-24 22:05:37,276 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 0.39351892471313477\nMultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 144x112, Tile count: 20, Batch size: 7, Tile batches: 3 (ext: ContrlNet)\nMultiDiffusion Sampling: 0%| | 0/21 [00:00<?, ?it/s]\nMultiDiffusion Sampling: 0%| | 0/2 [00:20<?, ?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]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 5%|▌ | 19/364 [00:00<00:08, 40.47it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 7%|▋ | 24/364 [00:00<00:08, 37.95it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 10%|█ | 38/364 [00:01<00:09, 34.04it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 12%|█▏ | 42/364 [00:01<00:09, 32.53it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 16%|█▌ | 57/364 [00:01<00:09, 32.90it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 17%|█▋ | 61/364 [00:01<00:09, 31.93it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 21%|██ | 76/364 [00:02<00:08, 32.64it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 22%|██▏ | 80/364 [00:02<00:10, 26.31it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 23%|██▎ | 83/364 [00:02<00:13, 20.83it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 24%|██▎ | 86/364 [00:03<00:16, 17.11it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 25%|██▌ | 92/364 [00:03<00:12, 21.06it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 26%|██▌ | 95/364 [00:04<00:21, 12.77it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 27%|██▋ | 97/364 [00:04<00:19, 13.40it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 27%|██▋ | 99/364 [00:04<00:31, 8.45it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 28%|██▊ | 102/364 [00:04<00:24, 10.50it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 29%|██▊ | 104/364 [00:05<00:36, 7.06it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 29%|██▉ | 107/364 [00:05<00:27, 9.22it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 30%|██▉ | 109/364 [00:05<00:30, 8.43it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 31%|███ | 112/364 [00:06<00:29, 8.45it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 115/364 [00:06<00:30, 8.28it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 118/364 [00:07<00:30, 8.19it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 34%|███▍ | 124/364 [00:07<00:18, 12.84it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 35%|███▍ | 126/364 [00:07<00:18, 12.89it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 36%|███▌ | 130/364 [00:07<00:15, 14.74it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 36%|███▋ | 132/364 [00:07<00:16, 14.33it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 134/364 [00:07<00:16, 14.05it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 136/364 [00:07<00:15, 15.05it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 138/364 [00:08<00:15, 14.48it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 140/364 [00:08<00:15, 14.19it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 39%|███▉ | 142/364 [00:08<00:14, 15.41it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 40%|███▉ | 144/364 [00:08<00:14, 14.77it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 41%|████ | 148/364 [00:08<00:12, 16.89it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 41%|████▏ | 151/364 [00:08<00:12, 17.04it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 42%|████▏ | 154/364 [00:09<00:12, 17.17it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 44%|████▍ | 161/364 [00:09<00:09, 22.53it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 45%|████▌ | 164/364 [00:09<00:09, 21.10it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 46%|████▌ | 167/364 [00:09<00:13, 14.62it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 47%|████▋ | 171/364 [00:10<00:12, 15.95it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 48%|████▊ | 173/364 [00:10<00:13, 14.63it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 48%|████▊ | 176/364 [00:10<00:12, 14.73it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 49%|████▉ | 180/364 [00:10<00:11, 16.18it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 50%|█████ | 183/364 [00:10<00:11, 15.88it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 51%|█████ | 186/364 [00:11<00:11, 15.76it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 53%|█████▎ | 194/364 [00:11<00:06, 26.99it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 55%|█████▌ | 201/364 [00:11<00:04, 32.63it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 57%|█████▋ | 207/364 [00:11<00:04, 37.39it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 59%|█████▊ | 213/364 [00:11<00:03, 41.23it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 61%|██████ | 222/364 [00:11<00:02, 51.53it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 66%|██████▌ | 239/364 [00:11<00:01, 80.52it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 68%|██████▊ | 248/364 [00:11<00:01, 72.36it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 72%|███████▏ | 262/364 [00:12<00:01, 82.41it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 74%|███████▍ | 271/364 [00:12<00:01, 75.85it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 77%|███████▋ | 280/364 [00:12<00:01, 70.84it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 79%|███████▉ | 288/364 [00:12<00:01, 72.24it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 82%|████████▏ | 297/364 [00:12<00:00, 73.88it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 84%|████████▍ | 305/364 [00:12<00:00, 61.65it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 86%|████████▌ | 312/364 [00:13<00:01, 43.34it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 87%|████████▋ | 318/364 [00:13<00:01, 32.13it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 89%|████████▊ | 323/364 [00:13<00:01, 21.52it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 91%|█████████ | 331/364 [00:14<00:01, 27.08it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 95%|█████████▍| 344/364 [00:14<00:00, 41.18it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 96%|█████████▋| 351/364 [00:14<00:00, 44.80it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 100%|██████████| 364/364 [00:14<00:00, 25.50it/s]\n[Tiled VAE]: Done in 14.970s, max VRAM alloc 8676.574 MB\n 0%| | 0/6 [00:00<?, ?it/s]\u001b[A\nMultiDiffusion Sampling: 5%|▍ | 1/21 [00:15<05:14, 15.73s/it]\nMultiDiffusion Sampling: 10%|▉ | 2/21 [00:16<02:12, 6.98s/it]\nTotal progress: 0%| | 0/6 [00:00<?, ?it/s]\u001b[A\n 17%|█▋ | 1/6 [00:02<00:12, 2.45s/it]\u001b[A\n 33%|███▎ | 2/6 [00:04<00:09, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 14%|█▍ | 3/21 [00:21<01:48, 6.03s/it]\nTotal progress: 33%|███▎ | 2/6 [00:02<00:04, 1.22s/it]\u001b[A\nMultiDiffusion Sampling: 19%|█▉ | 4/21 [00:22<01:07, 3.96s/it]\n 50%|█████ | 3/6 [00:07<00:07, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 24%|██▍ | 5/21 [00:23<00:50, 3.13s/it]\nTotal progress: 50%|█████ | 3/6 [00:04<00:05, 1.74s/it]\u001b[A\nMultiDiffusion Sampling: 29%|██▊ | 6/21 [00:24<00:35, 2.34s/it]\n 67%|██████▋ | 4/6 [00:09<00:04, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 33%|███▎ | 7/21 [00:26<00:29, 2.12s/it]\nTotal progress: 67%|██████▋ | 4/6 [00:07<00:04, 2.00s/it]\u001b[A\nMultiDiffusion Sampling: 38%|███▊ | 8/21 [00:27<00:22, 1.69s/it]\n 83%|████████▎ | 5/6 [00:12<00:02, 2.45s/it]\u001b[A\nMultiDiffusion Sampling: 43%|████▎ | 9/21 [00:28<00:20, 1.68s/it]\nTotal progress: 83%|████████▎ | 5/6 [00:09<00:02, 2.16s/it]\u001b[A\nMultiDiffusion Sampling: 48%|████▊ | 10/21 [00:29<00:15, 1.41s/it]\n100%|██████████| 6/6 [00:14<00:00, 2.45s/it]\u001b[A\n100%|██████████| 6/6 [00:14<00:00, 2.45s/it]\nTotal progress: 100%|██████████| 6/6 [00:12<00:00, 2.26s/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]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 6%|▋ | 124/1968 [00:00<00:03, 548.74it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 13%|█▎ | 247/1968 [00:00<00:03, 545.40it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 19%|█▉ | 370/1968 [00:00<00:02, 545.05it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 25%|██▌ | 493/1968 [00:00<00:02, 581.54it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 31%|███▏ | 616/1968 [00:01<00:02, 567.47it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 38%|███▊ | 739/1968 [00:01<00:02, 559.06it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 44%|████▍ | 862/1968 [00:01<00:01, 554.22it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 985/1968 [00:01<00:01, 580.69it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 56%|█████▋ | 1108/1968 [00:01<00:01, 568.19it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 63%|██████▎ | 1231/1968 [00:02<00:01, 560.62it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 69%|██████▉ | 1354/1968 [00:02<00:01, 554.75it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 75%|███████▌ | 1477/1968 [00:02<00:00, 579.67it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 81%|████████▏ | 1600/1968 [00:02<00:00, 597.85it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 88%|████████▊ | 1723/1968 [00:02<00:00, 611.17it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 94%|█████████▍| 1846/1968 [00:03<00:00, 621.45it/s]\u001b[A\u001b[A\n[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 1968/1968 [00:03<00:00, 589.53it/s]\n[Tiled VAE]: Done in 3.993s, max VRAM alloc 6730.210 MB\nTotal progress: 100%|██████████| 6/6 [00:16<00:00, 2.26s/it]\u001b[A\nTotal progress: 100%|██████████| 6/6 [00:16<00:00, 2.81s/it]\nPrediction took 65.24 seconds",
"output": [
"https://replicate.delivery/yhqm/zphqr5xF5aJhIFg3uLhMmAJP9sfmwuWlxwYNi9P4m5ltmGdKA/1338-72ab9986-5147-11f0-af34-36d41c341aaa.png"
],
"data_removed": false,
"error": null,
"source": "web",
"status": "succeeded",
"created_at": "2025-06-24T22:05:13.837Z",
"started_at": "2025-06-24T22:05:13.846832Z",
"completed_at": "2025-06-24T22:06:19.77518Z",
"urls": {
"cancel": "https://api.replicate.com/v1/predictions/dsestetcxnrj40cqmfwvaeqg7c/cancel",
"get": "https://api.replicate.com/v1/predictions/dsestetcxnrj40cqmfwvaeqg7c",
"stream": "https://stream.replicate.com/v1/files/qoxq-xuvrdxplopso45tnq6erbh2upaavufvnzy4t6jokqc6b4oqfouma",
"web": "https://replicate.com/p/dsestetcxnrj40cqmfwvaeqg7c"
},
"metrics": {
"predict_time": 65.928348097,
"total_time": 65.93818
}
}