dribnet / pixray-tiler-future
- Public
- 1.7K runs
-
T4
Prediction
dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edbIDeatiaigjora6zkh7xn6eskuw3uStatusSucceededSourceWebHardware–Total durationCreatedInput
- mirror
- prompts
- fluffy clouds trending on artstation
- pixelart
{ "mirror": false, "prompts": "fluffy clouds trending on artstation", "pixelart": false }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-tiler-future using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", { input: { mirror: false, prompts: "fluffy clouds trending on artstation", pixelart: false } } ); 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-tiler-future using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", input={ "mirror": False, "prompts": "fluffy clouds trending on artstation", "pixelart": False } ) # The dribnet/pixray-tiler-future 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-tiler-future/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run dribnet/pixray-tiler-future 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-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", "input": { "mirror": false, "prompts": "fluffy clouds trending on artstation", "pixelart": false } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2021-12-07T11:36:52.158649Z", "created_at": "2021-12-07T11:31:03.718076Z", "data_removed": false, "error": null, "id": "eatiaigjora6zkh7xn6eskuw3u", "input": { "mirror": false, "prompts": "fluffy clouds trending on artstation", "pixelart": false }, "logs": "---> BasePixrayPredictor Predict\nUsing seed:\n10592767272366765512\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['fluffy clouds trending on artstation']\nusing custom losses: smoothness:0.5\n\n0it [00:00, ?it/s]\niter: 0, loss: 3.14, losses: 0.0281, 1.02, 0.0765, 0.898, 0.0466, 0.932, 0.0492, 0.0833 (-0=>3.136)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 10, loss: 2.66, losses: 0.00604, 0.869, 0.0849, 0.766, 0.0461, 0.784, 0.0461, 0.0596 (-0=>2.661)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 20, loss: 2.57, losses: 0.00396, 0.84, 0.0871, 0.737, 0.0462, 0.754, 0.0457, 0.0542 (-1=>2.567)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 30, loss: 2.48, losses: 0.00268, 0.806, 0.0863, 0.706, 0.0453, 0.735, 0.046, 0.0493 (-0=>2.477)\n\n0it [00:01, ?it/s]\n\n0it [00:11, ?it/s]\n\n0it [00:00, ?it/s]\niter: 40, loss: 2.48, losses: 0.00353, 0.816, 0.0846, 0.707, 0.0459, 0.725, 0.0459, 0.0486 (-4=>2.468)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 50, loss: 2.49, losses: 0.0024, 0.819, 0.0837, 0.708, 0.0459, 0.73, 0.0461, 0.0555 (-7=>2.426)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 60, loss: 2.42, losses: 0.00243, 0.785, 0.0856, 0.696, 0.047, 0.712, 0.0492, 0.0477 (-4=>2.396)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 70, loss: 2.39, losses: 0.00226, 0.78, 0.0859, 0.679, 0.0479, 0.697, 0.0483, 0.049 (-0=>2.39)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 80, loss: 2.45, losses: 0.00215, 0.801, 0.0852, 0.701, 0.0456, 0.716, 0.0468, 0.0509 (-1=>2.38)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 90, loss: 2.42, losses: 0.00272, 0.797, 0.0848, 0.683, 0.0469, 0.707, 0.0473, 0.0515 (-2=>2.363)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 100, loss: 2.41, losses: 0.00253, 0.794, 0.0833, 0.683, 0.0479, 0.694, 0.0481, 0.0545 (-12=>2.363)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 110, loss: 2.41, losses: 0.00292, 0.772, 0.0847, 0.686, 0.0463, 0.706, 0.0485, 0.0593 (-22=>2.363)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 120, loss: 2.41, losses: 0.0025, 0.787, 0.0854, 0.684, 0.0469, 0.704, 0.0482, 0.0498 (-4=>2.33)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 130, loss: 2.42, losses: 0.00256, 0.803, 0.0852, 0.675, 0.051, 0.695, 0.0493, 0.0638 (-14=>2.33)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 140, loss: 2.4, losses: 0.00194, 0.79, 0.0838, 0.682, 0.0477, 0.697, 0.0481, 0.0532 (-24=>2.33)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 150, loss: 2.36, losses: 0.00247, 0.77, 0.0846, 0.662, 0.0481, 0.691, 0.049, 0.0499 (-34=>2.33)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 160, loss: 2.36, losses: 0.00224, 0.77, 0.0849, 0.668, 0.0489, 0.683, 0.051, 0.0562 (-44=>2.33)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 170, loss: 2.37, losses: 0.0025, 0.766, 0.0854, 0.668, 0.0491, 0.688, 0.0502, 0.0578 (-8=>2.322)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 180, loss: 2.32, losses: 0.00292, 0.758, 0.0869, 0.649, 0.0505, 0.672, 0.0511, 0.0548 (-18=>2.322)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 190, loss: 2.35, losses: 0.00286, 0.776, 0.0858, 0.657, 0.0485, 0.672, 0.0511, 0.0546 (-28=>2.322)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 200, loss: 2.35, losses: 0.00241, 0.765, 0.0848, 0.672, 0.0471, 0.675, 0.0498, 0.0548 (-38=>2.322)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 210, loss: 2.37, losses: 0.00281, 0.778, 0.0851, 0.664, 0.0493, 0.69, 0.0496, 0.0516 (-2=>2.309)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 220, loss: 2.36, losses: 0.00255, 0.771, 0.0864, 0.659, 0.0484, 0.684, 0.049, 0.0634 (-12=>2.309)\n\n0it [00:00, ?it/s]\nDropping learning rate\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 230, loss: 2.36, losses: 0.00148, 0.777, 0.0857, 0.666, 0.0506, 0.676, 0.0511, 0.0522 (-4=>2.343)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 240, loss: 2.38, losses: 0.0021, 0.791, 0.0852, 0.668, 0.0482, 0.684, 0.0499, 0.0546 (-9=>2.324)\n\n0it [00:01, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 250, loss: 2.34, losses: 0.00199, 0.75, 0.0863, 0.663, 0.0486, 0.67, 0.0515, 0.0644 (-1=>2.305)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 260, loss: 2.37, losses: 0.00144, 0.785, 0.0862, 0.659, 0.0503, 0.68, 0.0506, 0.0572 (-11=>2.305)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 270, loss: 2.32, losses: 0.00178, 0.763, 0.0862, 0.649, 0.0511, 0.667, 0.0514, 0.0498 (-21=>2.305)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 280, loss: 2.36, losses: 0.00186, 0.772, 0.0865, 0.661, 0.0495, 0.68, 0.0502, 0.0566 (-9=>2.299)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 290, loss: 2.31, losses: 0.0022, 0.745, 0.0862, 0.655, 0.0495, 0.663, 0.0528, 0.0583 (-19=>2.299)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 300, finished (-5=>2.285)\n\n0it [00:00, ?it/s]\n\n0it [00:00, ?it/s]", "metrics": { "predict_time": 348.059373, "total_time": 348.440573 }, "output": [ { "file": "https://replicate.delivery/mgxm/c8cbee01-2fbc-4eb1-a970-88350160a56c/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f5a4bfa9-daec-42ad-a9d2-f5e2539270c6/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/d351e32f-077e-4bbc-a80a-d72ddf362755/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/c0f3e69e-7224-4e63-9c93-58f4f2ee26da/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/82029d88-6704-4028-9053-01584e56ecdc/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/f8211625-b7fb-484a-8c68-0d511b320b44/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5cd5734e-efbe-40dc-9c8a-d3e10bf46358/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/6ce16ff3-3aea-4922-9726-6a830f249151/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/cb099110-9f4d-49b4-a110-6e756e3c1e63/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/218bbf61-6a23-42cd-9a96-0aecd076886a/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/b0756424-4020-4cf1-b47a-2ab8dcc8e226/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5ddce4a5-f0f1-4403-ba43-83e94b954dab/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/93d88130-76a5-4f9b-abf4-ea0e566fc0c7/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/29f01a24-883b-45ea-ae81-47f9eb182875/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/dafd35a4-1fdf-484f-ad99-5c783f46f3e4/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/994f6854-526c-40ed-93da-8391ee563696/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/5860ad9b-3a3e-4e94-918f-2fc45c0c47f8/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/b8f9d599-ae67-4300-b2e3-11b99ca60cee/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/13627506-ba53-426d-9c9e-70ebea0dc632/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/7c067651-a128-4b69-b298-41304d48018d/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/35fa295c-7d8e-42c5-8ac5-7230b33b4f39/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/d0b06314-1973-4158-b50b-b393bae082a8/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/0baf8c4c-662b-4e9e-889a-a98d7af1b8f4/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/73f65641-52d2-48c1-93f6-9e6465c6e622/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/dc196e9d-13a8-4459-bc18-965a4bcfc2ae/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/8fe7742c-f279-4268-9343-022603a99e87/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/931008a9-5fc3-4f2c-b328-bfe91591e44c/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/a07e1444-3d81-48be-91d8-0dca1e5dd8c8/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/8f772bd4-e028-4753-a263-2c1f34504557/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/fe8fca90-dc1b-46f1-9187-22983d6062a4/tempfile.png" } ], "started_at": "2021-12-07T11:31:04.099276Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/eatiaigjora6zkh7xn6eskuw3u", "cancel": "https://api.replicate.com/v1/predictions/eatiaigjora6zkh7xn6eskuw3u/cancel" }, "version": "056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb" }Generated in---> BasePixrayPredictor Predict Using seed: 10592767272366765512 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: ['fluffy clouds trending on artstation'] using custom losses: smoothness:0.5 0it [00:00, ?it/s] iter: 0, loss: 3.14, losses: 0.0281, 1.02, 0.0765, 0.898, 0.0466, 0.932, 0.0492, 0.0833 (-0=>3.136) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 10, loss: 2.66, losses: 0.00604, 0.869, 0.0849, 0.766, 0.0461, 0.784, 0.0461, 0.0596 (-0=>2.661) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 20, loss: 2.57, losses: 0.00396, 0.84, 0.0871, 0.737, 0.0462, 0.754, 0.0457, 0.0542 (-1=>2.567) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 30, loss: 2.48, losses: 0.00268, 0.806, 0.0863, 0.706, 0.0453, 0.735, 0.046, 0.0493 (-0=>2.477) 0it [00:01, ?it/s] 0it [00:11, ?it/s] 0it [00:00, ?it/s] iter: 40, loss: 2.48, losses: 0.00353, 0.816, 0.0846, 0.707, 0.0459, 0.725, 0.0459, 0.0486 (-4=>2.468) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 50, loss: 2.49, losses: 0.0024, 0.819, 0.0837, 0.708, 0.0459, 0.73, 0.0461, 0.0555 (-7=>2.426) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 60, loss: 2.42, losses: 0.00243, 0.785, 0.0856, 0.696, 0.047, 0.712, 0.0492, 0.0477 (-4=>2.396) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 70, loss: 2.39, losses: 0.00226, 0.78, 0.0859, 0.679, 0.0479, 0.697, 0.0483, 0.049 (-0=>2.39) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 80, loss: 2.45, losses: 0.00215, 0.801, 0.0852, 0.701, 0.0456, 0.716, 0.0468, 0.0509 (-1=>2.38) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 90, loss: 2.42, losses: 0.00272, 0.797, 0.0848, 0.683, 0.0469, 0.707, 0.0473, 0.0515 (-2=>2.363) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 100, loss: 2.41, losses: 0.00253, 0.794, 0.0833, 0.683, 0.0479, 0.694, 0.0481, 0.0545 (-12=>2.363) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 110, loss: 2.41, losses: 0.00292, 0.772, 0.0847, 0.686, 0.0463, 0.706, 0.0485, 0.0593 (-22=>2.363) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 120, loss: 2.41, losses: 0.0025, 0.787, 0.0854, 0.684, 0.0469, 0.704, 0.0482, 0.0498 (-4=>2.33) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 130, loss: 2.42, losses: 0.00256, 0.803, 0.0852, 0.675, 0.051, 0.695, 0.0493, 0.0638 (-14=>2.33) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 140, loss: 2.4, losses: 0.00194, 0.79, 0.0838, 0.682, 0.0477, 0.697, 0.0481, 0.0532 (-24=>2.33) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 150, loss: 2.36, losses: 0.00247, 0.77, 0.0846, 0.662, 0.0481, 0.691, 0.049, 0.0499 (-34=>2.33) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 160, loss: 2.36, losses: 0.00224, 0.77, 0.0849, 0.668, 0.0489, 0.683, 0.051, 0.0562 (-44=>2.33) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 170, loss: 2.37, losses: 0.0025, 0.766, 0.0854, 0.668, 0.0491, 0.688, 0.0502, 0.0578 (-8=>2.322) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 180, loss: 2.32, losses: 0.00292, 0.758, 0.0869, 0.649, 0.0505, 0.672, 0.0511, 0.0548 (-18=>2.322) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 190, loss: 2.35, losses: 0.00286, 0.776, 0.0858, 0.657, 0.0485, 0.672, 0.0511, 0.0546 (-28=>2.322) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 200, loss: 2.35, losses: 0.00241, 0.765, 0.0848, 0.672, 0.0471, 0.675, 0.0498, 0.0548 (-38=>2.322) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 210, loss: 2.37, losses: 0.00281, 0.778, 0.0851, 0.664, 0.0493, 0.69, 0.0496, 0.0516 (-2=>2.309) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 220, loss: 2.36, losses: 0.00255, 0.771, 0.0864, 0.659, 0.0484, 0.684, 0.049, 0.0634 (-12=>2.309) 0it [00:00, ?it/s] Dropping learning rate 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 230, loss: 2.36, losses: 0.00148, 0.777, 0.0857, 0.666, 0.0506, 0.676, 0.0511, 0.0522 (-4=>2.343) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 240, loss: 2.38, losses: 0.0021, 0.791, 0.0852, 0.668, 0.0482, 0.684, 0.0499, 0.0546 (-9=>2.324) 0it [00:01, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 250, loss: 2.34, losses: 0.00199, 0.75, 0.0863, 0.663, 0.0486, 0.67, 0.0515, 0.0644 (-1=>2.305) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 260, loss: 2.37, losses: 0.00144, 0.785, 0.0862, 0.659, 0.0503, 0.68, 0.0506, 0.0572 (-11=>2.305) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 270, loss: 2.32, losses: 0.00178, 0.763, 0.0862, 0.649, 0.0511, 0.667, 0.0514, 0.0498 (-21=>2.305) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 280, loss: 2.36, losses: 0.00186, 0.772, 0.0865, 0.661, 0.0495, 0.68, 0.0502, 0.0566 (-9=>2.299) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 290, loss: 2.31, losses: 0.0022, 0.745, 0.0862, 0.655, 0.0495, 0.663, 0.0528, 0.0583 (-19=>2.299) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 300, finished (-5=>2.285) 0it [00:00, ?it/s] 0it [00:00, ?it/s]Prediction
dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edbInput
- mirror
- prompts
- colorful granite texture
- pixelart
- settings
- iterations: 50
{ "mirror": false, "prompts": "colorful granite texture", "pixelart": false, "settings": "iterations: 50\n" }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-tiler-future using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", { input: { mirror: false, prompts: "colorful granite texture", pixelart: false, settings: "iterations: 50\n" } } ); 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-tiler-future using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "dribnet/pixray-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", input={ "mirror": False, "prompts": "colorful granite texture", "pixelart": False, "settings": "iterations: 50\n" } ) # The dribnet/pixray-tiler-future 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-tiler-future/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run dribnet/pixray-tiler-future 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-tiler-future:056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb", "input": { "mirror": false, "prompts": "colorful granite texture", "pixelart": false, "settings": "iterations: 50\\n" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2021-12-07T11:11:24.236108Z", "created_at": "2021-12-07T11:09:59.175341Z", "data_removed": false, "error": null, "id": "az7dptbervdxxcuk24ygvrvbtm", "input": { "mirror": false, "prompts": "colorful granite texture", "pixelart": false, "settings": "iterations: 50\n" }, "logs": "---> BasePixrayPredictor Predict\nUsing seed:\n13156875299438480323\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['colorful granite texture']\nusing custom losses: smoothness:0.5\n\n0it [00:00, ?it/s]\niter: 0, loss: 2.91, losses: 0.0295, 0.914, 0.0763, 0.868, 0.047, 0.83, 0.0494, 0.0932 (-0=>2.908)\n\n0it [00:00, ?it/s]\n\n0it [00:09, ?it/s]\n\n0it [00:00, ?it/s]\niter: 10, loss: 2.52, losses: 0.00824, 0.809, 0.075, 0.74, 0.0533, 0.717, 0.0575, 0.0577 (-0=>2.518)\n\n0it [00:00, ?it/s]\n\n0it [00:09, ?it/s]\n\n0it [00:00, ?it/s]\niter: 20, loss: 2.48, losses: 0.00845, 0.798, 0.0751, 0.727, 0.0548, 0.702, 0.0578, 0.0589 (-0=>2.482)\n\n0it [00:00, ?it/s]\n\n0it [00:09, ?it/s]\n\n0it [00:00, ?it/s]\niter: 30, loss: 2.45, losses: 0.00705, 0.792, 0.0739, 0.722, 0.0529, 0.685, 0.0572, 0.0595 (-0=>2.45)\n\n0it [00:00, ?it/s]\nDropping learning rate\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 40, loss: 2.44, losses: 0.00601, 0.79, 0.0756, 0.721, 0.0533, 0.683, 0.0584, 0.057 (-0=>2.444)\n\n0it [00:00, ?it/s]\n\n0it [00:10, ?it/s]\n\n0it [00:00, ?it/s]\niter: 50, finished (-6=>2.425)\n\n0it [00:00, ?it/s]\n\n0it [00:00, ?it/s]", "metrics": { "predict_time": 81.362716, "total_time": 85.060767 }, "output": [ { "file": "https://replicate.delivery/mgxm/a926a55f-fea2-459b-a5f1-f5a0f501e5b0/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/79ef3ddc-e709-4199-b236-deefcd83b2f1/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/e1e55177-7471-45e6-bae0-fc6a055d62bc/tempfile.png" }, { "file": "https://replicate.delivery/mgxm/9f97b4ea-0769-483f-a575-51a9d68fc52c/tempfile.png" } ], "started_at": "2021-12-07T11:10:02.873392Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/az7dptbervdxxcuk24ygvrvbtm", "cancel": "https://api.replicate.com/v1/predictions/az7dptbervdxxcuk24ygvrvbtm/cancel" }, "version": "056a948009a9e98f7dcabdb29e2477238433b7e8c0c78420c1bb7b53ce960edb" }Generated in---> BasePixrayPredictor Predict Using seed: 13156875299438480323 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: ['colorful granite texture'] using custom losses: smoothness:0.5 0it [00:00, ?it/s] iter: 0, loss: 2.91, losses: 0.0295, 0.914, 0.0763, 0.868, 0.047, 0.83, 0.0494, 0.0932 (-0=>2.908) 0it [00:00, ?it/s] 0it [00:09, ?it/s] 0it [00:00, ?it/s] iter: 10, loss: 2.52, losses: 0.00824, 0.809, 0.075, 0.74, 0.0533, 0.717, 0.0575, 0.0577 (-0=>2.518) 0it [00:00, ?it/s] 0it [00:09, ?it/s] 0it [00:00, ?it/s] iter: 20, loss: 2.48, losses: 0.00845, 0.798, 0.0751, 0.727, 0.0548, 0.702, 0.0578, 0.0589 (-0=>2.482) 0it [00:00, ?it/s] 0it [00:09, ?it/s] 0it [00:00, ?it/s] iter: 30, loss: 2.45, losses: 0.00705, 0.792, 0.0739, 0.722, 0.0529, 0.685, 0.0572, 0.0595 (-0=>2.45) 0it [00:00, ?it/s] Dropping learning rate 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 40, loss: 2.44, losses: 0.00601, 0.79, 0.0756, 0.721, 0.0533, 0.683, 0.0584, 0.057 (-0=>2.444) 0it [00:00, ?it/s] 0it [00:10, ?it/s] 0it [00:00, ?it/s] iter: 50, finished (-6=>2.425) 0it [00:00, ?it/s] 0it [00:00, ?it/s]
Want to make some of these yourself?
Run this model
