dribnet/pixray-vqgan
/
pixray-vqgan
Select a model
View profile
dribnet/pixray-vqgan
dribnet/clipit
Image generation with CLIP + VQGAN / PixelDraw
dribnet/pixray-pixel
dribnet/pixray-text2image
Uses pixray to generate an image from text prompt
dribnet/pixray-text2pixel
Turn any description into pixel art
dribnet/pixray
Pixray with custom settings
dribnet/pixray-genesis
dribnet/pixray-api
Uses pixray with raw settings.
dribnet/pixray-tiler
Turn any description into wallpaper tiles
dribnet/bex-research-portfolio-code
dribnet/pixray-tiler-future
dribnet/pixray-text2pixel-0x42
Uses pixray to generate an image from text prompt
dribnet/8bidoug
A pixray tool for 24x24 pixelart
dribnet/homage1
Homage to the Pixel: text prompt to 6 color squares
Prediction
dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1Input
- aspect
- widescreen
- prompts
- Squid Game by Hwang Dong-hyuk
- quality
- better
{ "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "better" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run dribnet/pixray-vqgan using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", { input: { aspect: "widescreen", prompts: "Squid Game by Hwang Dong-hyuk", quality: "better" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun dribnet/pixray-vqgan using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", input={ "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "better" } ) # The dribnet/pixray-vqgan model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/dribnet/pixray-vqgan/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run dribnet/pixray-vqgan 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": "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", "input": { "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "better" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2021-10-10T14:31:33.967755Z", "created_at": "2021-10-10T14:23:35.238245Z", "data_removed": false, "error": null, "id": "m3ricclf55bgvh5elbxq4oh2aa", "input": { "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "better" }, "logs": "---> BasePixrayPredictor Predict\nUsing seed:\n11092165953890664426\nWorking with z of shape (1, 256, 16, 16) = 65536 dimensions.\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['Squid Game by Hwang Dong-hyuk']\n\n0it [00:00, ?it/s]\n/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.\n warnings.warn(\niter: 0, loss: 3.03, losses: 0.997, 0.0773, 0.924, 0.0466, 0.943, 0.047 (-0=>3.034)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 10, loss: 2.9, losses: 0.954, 0.0795, 0.884, 0.0474, 0.885, 0.0473 (-0=>2.897)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 20, loss: 2.86, losses: 0.943, 0.0803, 0.874, 0.0464, 0.864, 0.0476 (-2=>2.8)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 30, loss: 2.76, losses: 0.913, 0.0803, 0.847, 0.0468, 0.823, 0.047 (-0=>2.758)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 40, loss: 2.71, losses: 0.9, 0.0828, 0.826, 0.0488, 0.805, 0.0491 (-4=>2.674)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 50, loss: 2.66, losses: 0.882, 0.0817, 0.811, 0.0498, 0.786, 0.0496 (-3=>2.603)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 60, loss: 2.53, losses: 0.835, 0.0817, 0.78, 0.0497, 0.736, 0.0514 (-5=>2.53)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 70, loss: 2.59, losses: 0.863, 0.0827, 0.788, 0.0506, 0.759, 0.0509 (-1=>2.498)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 80, loss: 2.55, losses: 0.845, 0.0813, 0.777, 0.0517, 0.74, 0.0507 (-2=>2.458)\n\n0it [00:00, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 90, loss: 2.52, losses: 0.826, 0.0818, 0.774, 0.0525, 0.738, 0.0511 (-7=>2.434)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 100, loss: 2.41, losses: 0.786, 0.0817, 0.745, 0.0558, 0.689, 0.0543 (-3=>2.4)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 110, loss: 2.5, losses: 0.824, 0.0847, 0.762, 0.0541, 0.721, 0.0536 (-7=>2.381)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 120, loss: 2.49, losses: 0.826, 0.0828, 0.75, 0.0542, 0.723, 0.0526 (-7=>2.371)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 130, loss: 2.45, losses: 0.8, 0.0835, 0.752, 0.0553, 0.708, 0.0542 (-9=>2.363)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 140, loss: 2.48, losses: 0.82, 0.0836, 0.752, 0.0553, 0.715, 0.0531 (-3=>2.328)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 150, loss: 2.44, losses: 0.81, 0.0828, 0.739, 0.0559, 0.703, 0.0527 (-13=>2.328)\n\n0it [00:00, ?it/s]\nCaught SIGTERM, exiting...\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 160, loss: 2.46, losses: 0.812, 0.0827, 0.753, 0.0546, 0.705, 0.0534 (-7=>2.313)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 170, loss: 2.32, losses: 0.747, 0.0855, 0.712, 0.0596, 0.659, 0.0564 (-1=>2.292)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 180, loss: 2.42, losses: 0.8, 0.0828, 0.737, 0.0559, 0.689, 0.0546 (-11=>2.292)\n\n0it [00:00, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 190, loss: 2.42, losses: 0.799, 0.0843, 0.739, 0.0549, 0.688, 0.0542 (-21=>2.292)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 200, loss: 2.39, losses: 0.795, 0.0851, 0.731, 0.0558, 0.666, 0.0545 (-4=>2.281)\n\n0it [00:00, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 210, loss: 2.4, losses: 0.786, 0.0847, 0.735, 0.0565, 0.683, 0.0557 (-14=>2.281)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 220, loss: 2.27, losses: 0.743, 0.0863, 0.698, 0.06, 0.627, 0.0593 (-5=>2.254)\n\n0it [00:01, ?it/s]\nDropping learning rate\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 230, loss: 2.33, losses: 0.765, 0.0865, 0.712, 0.0588, 0.652, 0.0568 (-1=>2.221)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 240, loss: 2.35, losses: 0.774, 0.0837, 0.725, 0.0571, 0.66, 0.0548 (-11=>2.221)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 250, loss: 2.32, losses: 0.765, 0.0853, 0.706, 0.0591, 0.651, 0.0567 (-3=>2.203)\n\n0it [00:00, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 260, loss: 2.34, losses: 0.765, 0.0862, 0.713, 0.059, 0.66, 0.057 (-9=>2.2)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 270, loss: 2.39, losses: 0.788, 0.0844, 0.729, 0.0561, 0.674, 0.056 (-4=>2.197)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 280, loss: 2.22, losses: 0.711, 0.086, 0.688, 0.0611, 0.609, 0.0604 (-9=>2.188)\n\n0it [00:00, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 290, loss: 2.33, losses: 0.773, 0.0856, 0.708, 0.0592, 0.648, 0.0574 (-5=>2.186)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 300, finished (-15=>2.186)\n\n0it [00:00, ?it/s]\n\n0it [00:00, ?it/s]", "metrics": { "total_time": 478.72951 }, "output": [ { "file": "https://replicate.delivery/mgxm/3a1a5e2b-e186-449a-b187-b36b5a3d6da7/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/6b6b18fb-e10d-47d2-afb3-ad82338e5d4f/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/6779a224-ce75-4c35-af76-09bc185e2505/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/dfbbdaa6-fa29-4a31-a741-64a668749552/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/9b3c9d7b-928a-4811-8de9-e9c2ff173745/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/1da9e5f9-4271-4b9f-b4c1-f243f4646878/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f544b51c-8926-45ee-bde3-80c9647002e9/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/b88a8f84-6c65-4b3b-845f-75f4649442d9/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/84c93c1d-1cfc-4332-938c-ed854bff2d6d/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/d481b0a4-db74-44ac-a8ec-fdee21bc6917/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/ca72e701-1d15-4dd9-911c-568287b86787/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/719fc94b-419e-4a88-8f85-22a7ea4edd32/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/3a62418b-c421-4d40-8ac1-4ec37cad0de1/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/697db609-7169-456e-aa3c-71d4787c4171/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/ac400a01-8bf3-445a-877d-db230e38b6b4/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5c61aaef-0464-456b-ae32-c223fc85525a/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/57a8cf9a-6f53-4e14-ba37-ce8eb5034869/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/164081d4-3f06-49b1-a157-7d257957dffa/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5632a58e-8363-4e58-89a9-7a5c9e5b2525/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5b529431-710e-400b-a796-c16214b20582/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/9e8993e0-4499-4005-a9f8-5643cb70ece5/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/1a1a5f11-95a0-4e4f-ac7a-89fcda9bef1e/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/7158faea-5566-4f28-b829-89a29aa54c68/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/d2b55162-5d86-49a2-b7ee-7012a961148a/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/c4c4969a-e81e-413f-9689-23b67d5e8422/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/24853e57-65a1-4ed0-8087-4c3b3e15cdbf/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5919083d-744a-4120-8150-a13e3b91978f/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/c7f6c0c3-d5e3-4759-9ae6-b9767e086326/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/bf1a4d4e-179e-4753-aefe-b3d6b14c03c5/tempfile.png" } ], "started_at": "2021-11-30T16:34:32.094803Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/m3ricclf55bgvh5elbxq4oh2aa", "cancel": "https://api.replicate.com/v1/predictions/m3ricclf55bgvh5elbxq4oh2aa/cancel" }, "version": "012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1" }---> BasePixrayPredictor Predict Using seed: 11092165953890664426 Working with z of shape (1, 256, 16, 16) = 65536 dimensions. loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth VQLPIPSWithDiscriminator running with hinge loss. Restored from models/vqgan_imagenet_f16_16384.ckpt Using device: cuda:0 Optimising using: Adam Using text prompts: ['Squid Game by Hwang Dong-hyuk'] 0it [00:00, ?it/s] /root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. warnings.warn( iter: 0, loss: 3.03, losses: 0.997, 0.0773, 0.924, 0.0466, 0.943, 0.047 (-0=>3.034) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 10, loss: 2.9, losses: 0.954, 0.0795, 0.884, 0.0474, 0.885, 0.0473 (-0=>2.897) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 20, loss: 2.86, losses: 0.943, 0.0803, 0.874, 0.0464, 0.864, 0.0476 (-2=>2.8) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 30, loss: 2.76, losses: 0.913, 0.0803, 0.847, 0.0468, 0.823, 0.047 (-0=>2.758) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 40, loss: 2.71, losses: 0.9, 0.0828, 0.826, 0.0488, 0.805, 0.0491 (-4=>2.674) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 50, loss: 2.66, losses: 0.882, 0.0817, 0.811, 0.0498, 0.786, 0.0496 (-3=>2.603) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 60, loss: 2.53, losses: 0.835, 0.0817, 0.78, 0.0497, 0.736, 0.0514 (-5=>2.53) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 70, loss: 2.59, losses: 0.863, 0.0827, 0.788, 0.0506, 0.759, 0.0509 (-1=>2.498) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 80, loss: 2.55, losses: 0.845, 0.0813, 0.777, 0.0517, 0.74, 0.0507 (-2=>2.458) 0it [00:00, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 90, loss: 2.52, losses: 0.826, 0.0818, 0.774, 0.0525, 0.738, 0.0511 (-7=>2.434) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 100, loss: 2.41, losses: 0.786, 0.0817, 0.745, 0.0558, 0.689, 0.0543 (-3=>2.4) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 110, loss: 2.5, losses: 0.824, 0.0847, 0.762, 0.0541, 0.721, 0.0536 (-7=>2.381) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 120, loss: 2.49, losses: 0.826, 0.0828, 0.75, 0.0542, 0.723, 0.0526 (-7=>2.371) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 130, loss: 2.45, losses: 0.8, 0.0835, 0.752, 0.0553, 0.708, 0.0542 (-9=>2.363) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 140, loss: 2.48, losses: 0.82, 0.0836, 0.752, 0.0553, 0.715, 0.0531 (-3=>2.328) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 150, loss: 2.44, losses: 0.81, 0.0828, 0.739, 0.0559, 0.703, 0.0527 (-13=>2.328) 0it [00:00, ?it/s] Caught SIGTERM, exiting... 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 160, loss: 2.46, losses: 0.812, 0.0827, 0.753, 0.0546, 0.705, 0.0534 (-7=>2.313) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 170, loss: 2.32, losses: 0.747, 0.0855, 0.712, 0.0596, 0.659, 0.0564 (-1=>2.292) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 180, loss: 2.42, losses: 0.8, 0.0828, 0.737, 0.0559, 0.689, 0.0546 (-11=>2.292) 0it [00:00, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 190, loss: 2.42, losses: 0.799, 0.0843, 0.739, 0.0549, 0.688, 0.0542 (-21=>2.292) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 200, loss: 2.39, losses: 0.795, 0.0851, 0.731, 0.0558, 0.666, 0.0545 (-4=>2.281) 0it [00:00, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 210, loss: 2.4, losses: 0.786, 0.0847, 0.735, 0.0565, 0.683, 0.0557 (-14=>2.281) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 220, loss: 2.27, losses: 0.743, 0.0863, 0.698, 0.06, 0.627, 0.0593 (-5=>2.254) 0it [00:01, ?it/s] Dropping learning rate 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 230, loss: 2.33, losses: 0.765, 0.0865, 0.712, 0.0588, 0.652, 0.0568 (-1=>2.221) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 240, loss: 2.35, losses: 0.774, 0.0837, 0.725, 0.0571, 0.66, 0.0548 (-11=>2.221) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 250, loss: 2.32, losses: 0.765, 0.0853, 0.706, 0.0591, 0.651, 0.0567 (-3=>2.203) 0it [00:00, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 260, loss: 2.34, losses: 0.765, 0.0862, 0.713, 0.059, 0.66, 0.057 (-9=>2.2) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 270, loss: 2.39, losses: 0.788, 0.0844, 0.729, 0.0561, 0.674, 0.056 (-4=>2.197) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 280, loss: 2.22, losses: 0.711, 0.086, 0.688, 0.0611, 0.609, 0.0604 (-9=>2.188) 0it [00:00, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 290, loss: 2.33, losses: 0.773, 0.0856, 0.708, 0.0592, 0.648, 0.0574 (-5=>2.186) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 300, finished (-15=>2.186) 0it [00:00, ?it/s] 0it [00:00, ?it/s]Prediction
dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1IDeb6fedelznagbcaqhcoh6g4vp4StatusSucceededSourceWebHardware–Total duration–CreatedInput
- aspect
- widescreen
- prompts
- Squid Game by Hwang Dong-hyuk
- quality
- best
{ "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "best" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run dribnet/pixray-vqgan using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", { input: { aspect: "widescreen", prompts: "Squid Game by Hwang Dong-hyuk", quality: "best" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun dribnet/pixray-vqgan using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", input={ "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "best" } ) # The dribnet/pixray-vqgan model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/dribnet/pixray-vqgan/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run dribnet/pixray-vqgan 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": "dribnet/pixray-vqgan:012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1", "input": { "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "best" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2021-10-10T14:38:37.412470Z", "created_at": "2021-10-10T14:30:19.038380Z", "data_removed": false, "error": null, "id": "eb6fedelznagbcaqhcoh6g4vp4", "input": { "aspect": "widescreen", "prompts": "Squid Game by Hwang Dong-hyuk", "quality": "best" }, "logs": "---> BasePixrayPredictor Predict\nUsing seed:\n16988199606273389535\nreusing cached copy of model\nmodels/vqgan_imagenet_f16_16384.ckpt\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['Squid Game by Hwang Dong-hyuk']\n\n0it [00:00, ?it/s]\niter: 0, loss: 2.8, losses: 0.774, 0.07, 0.925, 0.0457, 0.941, 0.0479 (-0=>2.804)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 10, loss: 2.68, losses: 0.725, 0.0743, 0.894, 0.0485, 0.888, 0.0492 (-0=>2.679)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 20, loss: 2.6, losses: 0.717, 0.075, 0.869, 0.0487, 0.841, 0.048 (-1=>2.583)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 30, loss: 2.51, losses: 0.671, 0.077, 0.851, 0.0488, 0.814, 0.0488 (-1=>2.504)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 40, loss: 2.43, losses: 0.642, 0.0758, 0.822, 0.0489, 0.792, 0.0505 (-0=>2.431)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 50, loss: 2.37, losses: 0.625, 0.0774, 0.805, 0.0499, 0.767, 0.0495 (-1=>2.362)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 60, loss: 2.39, losses: 0.632, 0.0795, 0.804, 0.0509, 0.771, 0.0507 (-4=>2.354)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 70, loss: 2.32, losses: 0.631, 0.079, 0.766, 0.0507, 0.739, 0.0513 (-6=>2.29)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 80, loss: 2.35, losses: 0.631, 0.0802, 0.784, 0.0515, 0.756, 0.0519 (-1=>2.26)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 90, loss: 2.29, losses: 0.593, 0.0822, 0.767, 0.0524, 0.739, 0.053 (-6=>2.245)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 100, loss: 2.23, losses: 0.602, 0.0817, 0.739, 0.053, 0.699, 0.0535 (-2=>2.227)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 110, loss: 2.22, losses: 0.593, 0.079, 0.738, 0.0547, 0.7, 0.0557 (-2=>2.181)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 120, loss: 2.24, losses: 0.573, 0.0807, 0.757, 0.0541, 0.724, 0.0535 (-7=>2.167)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 130, loss: 2.22, losses: 0.581, 0.0825, 0.742, 0.0555, 0.705, 0.0544 (-4=>2.164)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 140, loss: 2.23, losses: 0.586, 0.0808, 0.752, 0.0509, 0.708, 0.0536 (-14=>2.164)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 150, loss: 2.2, losses: 0.583, 0.0833, 0.734, 0.0548, 0.695, 0.0546 (-3=>2.124)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 160, loss: 2.19, losses: 0.557, 0.0825, 0.739, 0.056, 0.7, 0.0578 (-13=>2.124)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 170, loss: 2.16, losses: 0.573, 0.0834, 0.719, 0.0556, 0.671, 0.0572 (-23=>2.124)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 180, loss: 2.11, losses: 0.542, 0.084, 0.711, 0.0548, 0.658, 0.0577 (-0=>2.109)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 190, loss: 2.1, losses: 0.538, 0.0847, 0.709, 0.0567, 0.655, 0.0599 (-0=>2.102)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 200, loss: 2.18, losses: 0.56, 0.0845, 0.729, 0.0574, 0.688, 0.0574 (-8=>2.093)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 210, loss: 2.07, losses: 0.547, 0.0833, 0.689, 0.0604, 0.634, 0.062 (-0=>2.075)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 220, loss: 2.15, losses: 0.53, 0.0854, 0.728, 0.0555, 0.689, 0.0573 (-10=>2.075)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 230, loss: 2.11, losses: 0.558, 0.0845, 0.697, 0.0619, 0.649, 0.0593 (-3=>2.07)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 240, loss: 2.1, losses: 0.548, 0.0833, 0.701, 0.0564, 0.652, 0.0595 (-13=>2.07)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 250, loss: 2.05, losses: 0.522, 0.0855, 0.695, 0.0599, 0.632, 0.0603 (-0=>2.055)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 260, loss: 2.14, losses: 0.55, 0.084, 0.717, 0.0572, 0.673, 0.0564 (-10=>2.055)\n\n0it [00:01, ?it/s]\nDropping learning rate\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 270, loss: 2.09, losses: 0.573, 0.083, 0.683, 0.0601, 0.63, 0.06 (-8=>2.068)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 280, loss: 2.13, losses: 0.535, 0.0866, 0.718, 0.057, 0.674, 0.0566 (-1=>2.045)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 290, loss: 2.08, losses: 0.562, 0.0828, 0.683, 0.0607, 0.627, 0.0606 (-11=>2.045)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 300, loss: 2.05, losses: 0.512, 0.0836, 0.694, 0.0599, 0.636, 0.0607 (-9=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 310, loss: 2.04, losses: 0.525, 0.0838, 0.686, 0.0601, 0.627, 0.0587 (-19=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 320, loss: 2.11, losses: 0.548, 0.0836, 0.709, 0.0594, 0.651, 0.06 (-29=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 330, loss: 2.02, losses: 0.53, 0.0842, 0.674, 0.061, 0.61, 0.0624 (-39=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 340, loss: 2.1, losses: 0.515, 0.0843, 0.718, 0.0572, 0.661, 0.0602 (-49=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:13, ?it/s]\n\n0it [00:00, ?it/s]\niter: 350, finished (-59=>1.993)\n\n0it [00:01, ?it/s]\n\n0it [00:01, ?it/s]", "metrics": { "total_time": 498.37409 }, "output": [ { "file": "https://replicate.delivery/mgxm/66137d16-f830-47e3-a581-f2dcf9b78171/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/0c71707e-ba86-463f-b0f3-89904a33b097/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/bb0bf905-79c3-47d9-a904-d477dd68faf7/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/23e8dec8-62f5-48e9-90a6-25f80674f828/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/85c2a684-f388-47b9-bfd7-308ebb4900e4/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/b84a645f-66b8-4b9c-a4c9-82627d77f88f/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/69f59cc9-18cb-4588-a990-7a2bbba44392/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/111d8b7e-e459-4247-8340-91814aa88ace/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f06c4c11-981c-4cd8-b341-39c80da2397c/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f0cd840f-32fa-4f79-9267-b1bdf873e2f8/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/4a9d3c32-f874-4e91-b586-1e7a56ef4bba/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/df0bde8f-8db3-4127-8ea3-373562b735cf/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/181b93ba-d279-4421-a76c-b344ee7837c5/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/fe70a502-8f3d-4b44-b649-f12ae4051a1f/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f09b48ab-abc5-4004-9587-3bc5c5152573/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/51557333-affb-427d-948f-90d7221a3343/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/afc95098-0fa7-432b-bdb5-7fd75b16a8c0/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/a8618223-6576-4dd7-bd4b-9b6236607025/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/37169718-8e35-4ee6-99ad-5dde6d63e984/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/e038cb48-ba07-42a4-b8ac-5af91c11b746/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/d2f52342-6b7a-43b5-9f0c-5571ed241570/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/8f30d59c-47bc-418b-a5b5-69fd3a6db960/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/e2646a8d-2487-4983-805b-d8b49213b539/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/11c9bdde-3aee-4abe-96e5-fd3bd39923f3/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/47bb1901-05d3-4be5-abad-84886cd860a0/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/c7bd7d07-0e38-4827-ac95-b2ead8e70a99/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/50dc4228-58f6-4fc8-9ecd-67295d622a33/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/bee33afa-48af-4530-8c83-20e32b980753/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/05a05774-7550-4915-97f3-beb44150ec86/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f9d403a9-6cab-4652-9d10-7c97835c8b39/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/72462e75-f58b-48e7-a31d-55db5ec11f3c/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/798780a8-1968-4d44-9b7b-fcd12ed28bcf/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/21761d0f-4709-4a82-ab75-a096e14bbd49/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/e0d5cfb4-b171-4c71-9067-8bcca0274d42/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/ee4e9d84-f448-4dee-9e2f-a639c110eec3/tempfile.png" } ], "started_at": "2021-12-04T04:20:36.260363Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/eb6fedelznagbcaqhcoh6g4vp4", "cancel": "https://api.replicate.com/v1/predictions/eb6fedelznagbcaqhcoh6g4vp4/cancel" }, "version": "012b0d7aa8fdeff191f2be675c2b81bf950450973bf644d763d46e39654e20e1" }---> BasePixrayPredictor Predict Using seed: 16988199606273389535 reusing cached copy of model models/vqgan_imagenet_f16_16384.ckpt Using device: cuda:0 Optimising using: Adam Using text prompts: ['Squid Game by Hwang Dong-hyuk'] 0it [00:00, ?it/s] iter: 0, loss: 2.8, losses: 0.774, 0.07, 0.925, 0.0457, 0.941, 0.0479 (-0=>2.804) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 10, loss: 2.68, losses: 0.725, 0.0743, 0.894, 0.0485, 0.888, 0.0492 (-0=>2.679) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 20, loss: 2.6, losses: 0.717, 0.075, 0.869, 0.0487, 0.841, 0.048 (-1=>2.583) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 30, loss: 2.51, losses: 0.671, 0.077, 0.851, 0.0488, 0.814, 0.0488 (-1=>2.504) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 40, loss: 2.43, losses: 0.642, 0.0758, 0.822, 0.0489, 0.792, 0.0505 (-0=>2.431) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 50, loss: 2.37, losses: 0.625, 0.0774, 0.805, 0.0499, 0.767, 0.0495 (-1=>2.362) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 60, loss: 2.39, losses: 0.632, 0.0795, 0.804, 0.0509, 0.771, 0.0507 (-4=>2.354) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 70, loss: 2.32, losses: 0.631, 0.079, 0.766, 0.0507, 0.739, 0.0513 (-6=>2.29) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 80, loss: 2.35, losses: 0.631, 0.0802, 0.784, 0.0515, 0.756, 0.0519 (-1=>2.26) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 90, loss: 2.29, losses: 0.593, 0.0822, 0.767, 0.0524, 0.739, 0.053 (-6=>2.245) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 100, loss: 2.23, losses: 0.602, 0.0817, 0.739, 0.053, 0.699, 0.0535 (-2=>2.227) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 110, loss: 2.22, losses: 0.593, 0.079, 0.738, 0.0547, 0.7, 0.0557 (-2=>2.181) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 120, loss: 2.24, losses: 0.573, 0.0807, 0.757, 0.0541, 0.724, 0.0535 (-7=>2.167) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 130, loss: 2.22, losses: 0.581, 0.0825, 0.742, 0.0555, 0.705, 0.0544 (-4=>2.164) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 140, loss: 2.23, losses: 0.586, 0.0808, 0.752, 0.0509, 0.708, 0.0536 (-14=>2.164) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 150, loss: 2.2, losses: 0.583, 0.0833, 0.734, 0.0548, 0.695, 0.0546 (-3=>2.124) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 160, loss: 2.19, losses: 0.557, 0.0825, 0.739, 0.056, 0.7, 0.0578 (-13=>2.124) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 170, loss: 2.16, losses: 0.573, 0.0834, 0.719, 0.0556, 0.671, 0.0572 (-23=>2.124) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 180, loss: 2.11, losses: 0.542, 0.084, 0.711, 0.0548, 0.658, 0.0577 (-0=>2.109) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 190, loss: 2.1, losses: 0.538, 0.0847, 0.709, 0.0567, 0.655, 0.0599 (-0=>2.102) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 200, loss: 2.18, losses: 0.56, 0.0845, 0.729, 0.0574, 0.688, 0.0574 (-8=>2.093) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 210, loss: 2.07, losses: 0.547, 0.0833, 0.689, 0.0604, 0.634, 0.062 (-0=>2.075) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 220, loss: 2.15, losses: 0.53, 0.0854, 0.728, 0.0555, 0.689, 0.0573 (-10=>2.075) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 230, loss: 2.11, losses: 0.558, 0.0845, 0.697, 0.0619, 0.649, 0.0593 (-3=>2.07) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 240, loss: 2.1, losses: 0.548, 0.0833, 0.701, 0.0564, 0.652, 0.0595 (-13=>2.07) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 250, loss: 2.05, losses: 0.522, 0.0855, 0.695, 0.0599, 0.632, 0.0603 (-0=>2.055) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 260, loss: 2.14, losses: 0.55, 0.084, 0.717, 0.0572, 0.673, 0.0564 (-10=>2.055) 0it [00:01, ?it/s] Dropping learning rate 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 270, loss: 2.09, losses: 0.573, 0.083, 0.683, 0.0601, 0.63, 0.06 (-8=>2.068) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 280, loss: 2.13, losses: 0.535, 0.0866, 0.718, 0.057, 0.674, 0.0566 (-1=>2.045) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 290, loss: 2.08, losses: 0.562, 0.0828, 0.683, 0.0607, 0.627, 0.0606 (-11=>2.045) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 300, loss: 2.05, losses: 0.512, 0.0836, 0.694, 0.0599, 0.636, 0.0607 (-9=>1.993) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 310, loss: 2.04, losses: 0.525, 0.0838, 0.686, 0.0601, 0.627, 0.0587 (-19=>1.993) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 320, loss: 2.11, losses: 0.548, 0.0836, 0.709, 0.0594, 0.651, 0.06 (-29=>1.993) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 330, loss: 2.02, losses: 0.53, 0.0842, 0.674, 0.061, 0.61, 0.0624 (-39=>1.993) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 340, loss: 2.1, losses: 0.515, 0.0843, 0.718, 0.0572, 0.661, 0.0602 (-49=>1.993) 0it [00:01, ?it/s] 0it [00:13, ?it/s] 0it [00:00, ?it/s] iter: 350, finished (-59=>1.993) 0it [00:01, ?it/s] 0it [00:01, ?it/s]
Want to make some of these yourself?
Run this model