cjwbw / scalecrafter
Tuning-free Higher-Resolution Visual Generation with Diffusion Models
Prediction
cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96IDfqiw5sdby2zlxktr7bmp44x3yaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @chenxwhInput
- width
- 2048
- height
- 2048
- prompt
- a professional photograph of an astronaut riding a horse
- num_inference_steps
- 50
{ "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", { input: { width: 2048, height: 2048, prompt: "a professional photograph of an astronaut riding a horse", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", input={ "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", "input": { "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T18:10:32.714702Z", "created_at": "2023-10-18T18:08:41.380615Z", "data_removed": false, "error": null, "id": "fqiw5sdby2zlxktr7bmp44x3ya", "input": { "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 }, "logs": "Using seed: 45640\nReading dilation settings\ndown_blocks.2.resnets.0.conv1 : 3.0\ndown_blocks.2.resnets.0.conv2 : 3.0\ndown_blocks.2.resnets.1.conv1 : 3.0\ndown_blocks.2.resnets.1.conv2 : 3.0\ndown_blocks.2.downsamplers.0.conv : 3.0\ndown_blocks.3.resnets.0.conv1 : 4.0\ndown_blocks.3.resnets.0.conv2 : 4.0\ndown_blocks.3.resnets.1.conv1 : 4.0\ndown_blocks.3.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.0.conv1 : 4.0\nup_blocks.0.resnets.0.conv2 : 4.0\nup_blocks.0.resnets.1.conv1 : 4.0\nup_blocks.0.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.2.conv1 : 4.0\nup_blocks.0.resnets.2.conv2 : 4.0\nup_blocks.0.upsamplers.0.conv : 4.0\nup_blocks.1.resnets.0.conv1 : 3.0\nup_blocks.1.resnets.0.conv2 : 3.0\nup_blocks.1.resnets.1.conv1 : 3.0\nup_blocks.1.resnets.1.conv2 : 3.0\nup_blocks.1.resnets.2.conv1 : 3.0\nup_blocks.1.resnets.2.conv2 : 3.0\nup_blocks.1.upsamplers.0.conv : 3.0\nup_blocks.2.resnets.0.conv1 : 2.0\nup_blocks.2.resnets.0.conv2 : 2.0\nup_blocks.2.resnets.1.conv1 : 2.0\nup_blocks.2.resnets.1.conv2 : 2.0\nup_blocks.2.resnets.2.conv1 : 2.0\nup_blocks.2.resnets.2.conv2 : 2.0\nup_blocks.2.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 4.0\nmid_block.resnets.0.conv2 : 4.0\nmid_block.resnets.1.conv1 : 4.0\nmid_block.resnets.1.conv2 : 4.0\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:02<02:19, 2.84s/it]\n 4%|▍ | 2/50 [00:05<02:04, 2.59s/it]\n 6%|▌ | 3/50 [00:07<01:58, 2.52s/it]\n 8%|▊ | 4/50 [00:10<01:54, 2.49s/it]\n 10%|█ | 5/50 [00:12<01:51, 2.47s/it]\n 12%|█▏ | 6/50 [00:15<01:48, 2.46s/it]\n 14%|█▍ | 7/50 [00:17<01:45, 2.46s/it]\n 16%|█▌ | 8/50 [00:19<01:42, 2.45s/it]\n 18%|█▊ | 9/50 [00:22<01:40, 2.45s/it]\n 20%|██ | 10/50 [00:24<01:37, 2.45s/it]\n 22%|██▏ | 11/50 [00:27<01:35, 2.45s/it]\n 24%|██▍ | 12/50 [00:29<01:32, 2.45s/it]\n 26%|██▌ | 13/50 [00:32<01:30, 2.45s/it]\n 28%|██▊ | 14/50 [00:34<01:28, 2.45s/it]\n 30%|███ | 15/50 [00:37<01:25, 2.45s/it]\n 32%|███▏ | 16/50 [00:39<01:23, 2.45s/it]\n 34%|███▍ | 17/50 [00:41<01:20, 2.45s/it]\n 36%|███▌ | 18/50 [00:44<01:18, 2.45s/it]\n 38%|███▊ | 19/50 [00:46<01:15, 2.45s/it]\n 40%|████ | 20/50 [00:49<01:13, 2.45s/it]\n 42%|████▏ | 21/50 [00:51<01:11, 2.45s/it]\n 44%|████▍ | 22/50 [00:54<01:08, 2.45s/it]\n 46%|████▌ | 23/50 [00:56<01:06, 2.46s/it]\n 48%|████▊ | 24/50 [00:59<01:03, 2.46s/it]\n 50%|█████ | 25/50 [01:01<01:01, 2.46s/it]\n 52%|█████▏ | 26/50 [01:04<00:59, 2.46s/it]\n 54%|█████▍ | 27/50 [01:06<00:56, 2.46s/it]\n 56%|█████▌ | 28/50 [01:08<00:54, 2.46s/it]\n 58%|█████▊ | 29/50 [01:11<00:51, 2.46s/it]\n 60%|██████ | 30/50 [01:13<00:49, 2.46s/it]\n 62%|██████▏ | 31/50 [01:16<00:46, 2.46s/it]\n 64%|██████▍ | 32/50 [01:18<00:44, 2.46s/it]\n 66%|██████▌ | 33/50 [01:21<00:41, 2.46s/it]\n 68%|██████▊ | 34/50 [01:23<00:39, 2.47s/it]\n 70%|███████ | 35/50 [01:26<00:36, 2.47s/it]\n 72%|███████▏ | 36/50 [01:27<00:29, 2.10s/it]\n 74%|███████▍ | 37/50 [01:28<00:23, 1.84s/it]\n 76%|███████▌ | 38/50 [01:29<00:19, 1.65s/it]\n 78%|███████▊ | 39/50 [01:31<00:16, 1.53s/it]\n 80%|████████ | 40/50 [01:32<00:14, 1.44s/it]\n 82%|████████▏ | 41/50 [01:33<00:12, 1.38s/it]\n 84%|████████▍ | 42/50 [01:34<00:10, 1.33s/it]\n 86%|████████▌ | 43/50 [01:36<00:09, 1.30s/it]\n 88%|████████▊ | 44/50 [01:37<00:07, 1.28s/it]\n 90%|█████████ | 45/50 [01:38<00:06, 1.26s/it]\n 92%|█████████▏| 46/50 [01:39<00:05, 1.25s/it]\n 94%|█████████▍| 47/50 [01:40<00:03, 1.25s/it]\n 96%|█████████▌| 48/50 [01:42<00:02, 1.24s/it]\n 98%|█████████▊| 49/50 [01:43<00:01, 1.24s/it]\n100%|██████████| 50/50 [01:44<00:00, 1.24s/it]\n100%|██████████| 50/50 [01:44<00:00, 2.09s/it]", "metrics": { "predict_time": 109.942046, "total_time": 111.334087 }, "output": "https://pbxt.replicate.delivery/WffBxTIX99rs005ySfHwEiuhYhdLPEhbVgJbDri2dfTfyo7NC/out.png", "started_at": "2023-10-18T18:08:42.772656Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fqiw5sdby2zlxktr7bmp44x3ya", "cancel": "https://api.replicate.com/v1/predictions/fqiw5sdby2zlxktr7bmp44x3ya/cancel" }, "version": "8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96" }Generated inUsing seed: 45640 Reading dilation settings down_blocks.2.resnets.0.conv1 : 3.0 down_blocks.2.resnets.0.conv2 : 3.0 down_blocks.2.resnets.1.conv1 : 3.0 down_blocks.2.resnets.1.conv2 : 3.0 down_blocks.2.downsamplers.0.conv : 3.0 down_blocks.3.resnets.0.conv1 : 4.0 down_blocks.3.resnets.0.conv2 : 4.0 down_blocks.3.resnets.1.conv1 : 4.0 down_blocks.3.resnets.1.conv2 : 4.0 up_blocks.0.resnets.0.conv1 : 4.0 up_blocks.0.resnets.0.conv2 : 4.0 up_blocks.0.resnets.1.conv1 : 4.0 up_blocks.0.resnets.1.conv2 : 4.0 up_blocks.0.resnets.2.conv1 : 4.0 up_blocks.0.resnets.2.conv2 : 4.0 up_blocks.0.upsamplers.0.conv : 4.0 up_blocks.1.resnets.0.conv1 : 3.0 up_blocks.1.resnets.0.conv2 : 3.0 up_blocks.1.resnets.1.conv1 : 3.0 up_blocks.1.resnets.1.conv2 : 3.0 up_blocks.1.resnets.2.conv1 : 3.0 up_blocks.1.resnets.2.conv2 : 3.0 up_blocks.1.upsamplers.0.conv : 3.0 up_blocks.2.resnets.0.conv1 : 2.0 up_blocks.2.resnets.0.conv2 : 2.0 up_blocks.2.resnets.1.conv1 : 2.0 up_blocks.2.resnets.1.conv2 : 2.0 up_blocks.2.resnets.2.conv1 : 2.0 up_blocks.2.resnets.2.conv2 : 2.0 up_blocks.2.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 4.0 mid_block.resnets.0.conv2 : 4.0 mid_block.resnets.1.conv1 : 4.0 mid_block.resnets.1.conv2 : 4.0 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<02:19, 2.84s/it] 4%|▍ | 2/50 [00:05<02:04, 2.59s/it] 6%|▌ | 3/50 [00:07<01:58, 2.52s/it] 8%|▊ | 4/50 [00:10<01:54, 2.49s/it] 10%|█ | 5/50 [00:12<01:51, 2.47s/it] 12%|█▏ | 6/50 [00:15<01:48, 2.46s/it] 14%|█▍ | 7/50 [00:17<01:45, 2.46s/it] 16%|█▌ | 8/50 [00:19<01:42, 2.45s/it] 18%|█▊ | 9/50 [00:22<01:40, 2.45s/it] 20%|██ | 10/50 [00:24<01:37, 2.45s/it] 22%|██▏ | 11/50 [00:27<01:35, 2.45s/it] 24%|██▍ | 12/50 [00:29<01:32, 2.45s/it] 26%|██▌ | 13/50 [00:32<01:30, 2.45s/it] 28%|██▊ | 14/50 [00:34<01:28, 2.45s/it] 30%|███ | 15/50 [00:37<01:25, 2.45s/it] 32%|███▏ | 16/50 [00:39<01:23, 2.45s/it] 34%|███▍ | 17/50 [00:41<01:20, 2.45s/it] 36%|███▌ | 18/50 [00:44<01:18, 2.45s/it] 38%|███▊ | 19/50 [00:46<01:15, 2.45s/it] 40%|████ | 20/50 [00:49<01:13, 2.45s/it] 42%|████▏ | 21/50 [00:51<01:11, 2.45s/it] 44%|████▍ | 22/50 [00:54<01:08, 2.45s/it] 46%|████▌ | 23/50 [00:56<01:06, 2.46s/it] 48%|████▊ | 24/50 [00:59<01:03, 2.46s/it] 50%|█████ | 25/50 [01:01<01:01, 2.46s/it] 52%|█████▏ | 26/50 [01:04<00:59, 2.46s/it] 54%|█████▍ | 27/50 [01:06<00:56, 2.46s/it] 56%|█████▌ | 28/50 [01:08<00:54, 2.46s/it] 58%|█████▊ | 29/50 [01:11<00:51, 2.46s/it] 60%|██████ | 30/50 [01:13<00:49, 2.46s/it] 62%|██████▏ | 31/50 [01:16<00:46, 2.46s/it] 64%|██████▍ | 32/50 [01:18<00:44, 2.46s/it] 66%|██████▌ | 33/50 [01:21<00:41, 2.46s/it] 68%|██████▊ | 34/50 [01:23<00:39, 2.47s/it] 70%|███████ | 35/50 [01:26<00:36, 2.47s/it] 72%|███████▏ | 36/50 [01:27<00:29, 2.10s/it] 74%|███████▍ | 37/50 [01:28<00:23, 1.84s/it] 76%|███████▌ | 38/50 [01:29<00:19, 1.65s/it] 78%|███████▊ | 39/50 [01:31<00:16, 1.53s/it] 80%|████████ | 40/50 [01:32<00:14, 1.44s/it] 82%|████████▏ | 41/50 [01:33<00:12, 1.38s/it] 84%|████████▍ | 42/50 [01:34<00:10, 1.33s/it] 86%|████████▌ | 43/50 [01:36<00:09, 1.30s/it] 88%|████████▊ | 44/50 [01:37<00:07, 1.28s/it] 90%|█████████ | 45/50 [01:38<00:06, 1.26s/it] 92%|█████████▏| 46/50 [01:39<00:05, 1.25s/it] 94%|█████████▍| 47/50 [01:40<00:03, 1.25s/it] 96%|█████████▌| 48/50 [01:42<00:02, 1.24s/it] 98%|█████████▊| 49/50 [01:43<00:01, 1.24s/it] 100%|██████████| 50/50 [01:44<00:00, 1.24s/it] 100%|██████████| 50/50 [01:44<00:00, 2.09s/it]Prediction
cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96IDzo2kby3bf5axy2nkngnsyaueheStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 4096
- height
- 4096
- prompt
- Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail
- num_inference_steps
- 50
{ "width": 4096, "height": 4096, "prompt": "Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", { input: { width: 4096, height: 4096, prompt: "Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", input={ "width": 4096, "height": 4096, "prompt": "Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", "input": { "width": 4096, "height": 4096, "prompt": "Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T18:29:25.601308Z", "created_at": "2023-10-18T18:13:51.575500Z", "data_removed": false, "error": null, "id": "zo2kby3bf5axy2nkngnsyauehe", "input": { "width": 4096, "height": 4096, "prompt": "Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail", "num_inference_steps": 50 }, "logs": "Using seed: 21787\nReading dilation settings\ndown_blocks.2.resnets.0.conv1 : 3.0\ndown_blocks.2.resnets.0.conv2 : 3.0\ndown_blocks.2.resnets.1.conv1 : 3.0\ndown_blocks.2.resnets.1.conv2 : 3.0\ndown_blocks.2.downsamplers.0.conv : 3.0\ndown_blocks.3.resnets.0.conv1 : 4.0\ndown_blocks.3.resnets.0.conv2 : 4.0\ndown_blocks.3.resnets.1.conv1 : 4.0\ndown_blocks.3.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.0.conv1 : 4.0\nup_blocks.0.resnets.0.conv2 : 4.0\nup_blocks.0.resnets.1.conv1 : 4.0\nup_blocks.0.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.2.conv1 : 4.0\nup_blocks.0.resnets.2.conv2 : 4.0\nup_blocks.0.upsamplers.0.conv : 4.0\nup_blocks.1.resnets.0.conv1 : 3.0\nup_blocks.1.resnets.0.conv2 : 3.0\nup_blocks.1.resnets.1.conv1 : 3.0\nup_blocks.1.resnets.1.conv2 : 3.0\nup_blocks.1.resnets.2.conv1 : 3.0\nup_blocks.1.resnets.2.conv2 : 3.0\nup_blocks.1.upsamplers.0.conv : 3.0\nup_blocks.2.resnets.0.conv1 : 2.0\nup_blocks.2.resnets.0.conv2 : 2.0\nup_blocks.2.resnets.1.conv1 : 2.0\nup_blocks.2.resnets.1.conv2 : 2.0\nup_blocks.2.resnets.2.conv1 : 2.0\nup_blocks.2.resnets.2.conv2 : 2.0\nup_blocks.2.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 4.0\nmid_block.resnets.0.conv2 : 4.0\nmid_block.resnets.1.conv1 : 4.0\nmid_block.resnets.1.conv2 : 4.0\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:21<17:18, 21.19s/it]\n 4%|▍ | 2/50 [00:42<16:57, 21.20s/it]\n 6%|▌ | 3/50 [01:03<16:40, 21.28s/it]\n 8%|▊ | 4/50 [01:25<16:22, 21.35s/it]\n 10%|█ | 5/50 [01:46<16:03, 21.40s/it]\n 12%|█▏ | 6/50 [02:08<15:44, 21.46s/it]\n 14%|█▍ | 7/50 [02:29<15:24, 21.50s/it]\n 16%|█▌ | 8/50 [02:51<15:04, 21.53s/it]\n 18%|█▊ | 9/50 [03:13<14:43, 21.55s/it]\n 20%|██ | 10/50 [03:34<14:22, 21.57s/it]\n 22%|██▏ | 11/50 [03:56<14:02, 21.59s/it]\n 24%|██▍ | 12/50 [04:17<13:40, 21.60s/it]\n 26%|██▌ | 13/50 [04:39<13:19, 21.60s/it]\n 28%|██▊ | 14/50 [05:01<12:57, 21.61s/it]\n 30%|███ | 15/50 [05:22<12:36, 21.60s/it]\n 32%|███▏ | 16/50 [05:44<12:14, 21.61s/it]\n 34%|███▍ | 17/50 [06:05<11:53, 21.61s/it]\n 36%|███▌ | 18/50 [06:27<11:31, 21.61s/it]\n 38%|███▊ | 19/50 [06:49<11:10, 21.62s/it]\n 40%|████ | 20/50 [07:10<10:48, 21.61s/it]\n 42%|████▏ | 21/50 [07:32<10:26, 21.61s/it]\n 44%|████▍ | 22/50 [07:54<10:05, 21.61s/it]\n 46%|████▌ | 23/50 [08:15<09:43, 21.61s/it]\n 48%|████▊ | 24/50 [08:37<09:22, 21.62s/it]\n 50%|█████ | 25/50 [08:58<09:00, 21.61s/it]\n 52%|█████▏ | 26/50 [09:20<08:38, 21.61s/it]\n 54%|█████▍ | 27/50 [09:42<08:16, 21.61s/it]\n 56%|█████▌ | 28/50 [10:03<07:55, 21.60s/it]\n 58%|█████▊ | 29/50 [10:25<07:33, 21.61s/it]\n 60%|██████ | 30/50 [10:46<07:12, 21.61s/it]\n 62%|██████▏ | 31/50 [11:08<06:50, 21.60s/it]\n 64%|██████▍ | 32/50 [11:30<06:28, 21.61s/it]\n 66%|██████▌ | 33/50 [11:51<06:07, 21.61s/it]\n 68%|██████▊ | 34/50 [12:13<05:45, 21.60s/it]\n 70%|███████ | 35/50 [12:34<05:24, 21.61s/it]\n 72%|███████▏ | 36/50 [12:45<04:17, 18.36s/it]\n 74%|███████▍ | 37/50 [12:56<03:29, 16.08s/it]\n 76%|███████▌ | 38/50 [13:07<02:53, 14.49s/it]\n 78%|███████▊ | 39/50 [13:18<02:27, 13.39s/it]\n 80%|████████ | 40/50 [13:28<02:06, 12.61s/it]\n 82%|████████▏ | 41/50 [13:39<01:48, 12.06s/it]\n 84%|████████▍ | 42/50 [13:50<01:33, 11.67s/it]\n 86%|████████▌ | 43/50 [14:01<01:19, 11.40s/it]\n 88%|████████▊ | 44/50 [14:11<01:07, 11.22s/it]\n 90%|█████████ | 45/50 [14:22<00:55, 11.09s/it]\n 92%|█████████▏| 46/50 [14:33<00:43, 11.00s/it]\n 94%|█████████▍| 47/50 [14:44<00:32, 10.93s/it]\n 96%|█████████▌| 48/50 [14:55<00:21, 10.89s/it]\n 98%|█████████▊| 49/50 [15:05<00:10, 10.86s/it]\n100%|██████████| 50/50 [15:16<00:00, 10.84s/it]\n100%|██████████| 50/50 [15:16<00:00, 18.33s/it]", "metrics": { "predict_time": 934.048671, "total_time": 934.025808 }, "output": "https://pbxt.replicate.delivery/4YzejFfdl5mAu0fuVtcuW7t4SP7J7q5hZb6ldZzI6IiHw6eGB/out.png", "started_at": "2023-10-18T18:13:51.552637Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/zo2kby3bf5axy2nkngnsyauehe", "cancel": "https://api.replicate.com/v1/predictions/zo2kby3bf5axy2nkngnsyauehe/cancel" }, "version": "8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96" }Generated inUsing seed: 21787 Reading dilation settings down_blocks.2.resnets.0.conv1 : 3.0 down_blocks.2.resnets.0.conv2 : 3.0 down_blocks.2.resnets.1.conv1 : 3.0 down_blocks.2.resnets.1.conv2 : 3.0 down_blocks.2.downsamplers.0.conv : 3.0 down_blocks.3.resnets.0.conv1 : 4.0 down_blocks.3.resnets.0.conv2 : 4.0 down_blocks.3.resnets.1.conv1 : 4.0 down_blocks.3.resnets.1.conv2 : 4.0 up_blocks.0.resnets.0.conv1 : 4.0 up_blocks.0.resnets.0.conv2 : 4.0 up_blocks.0.resnets.1.conv1 : 4.0 up_blocks.0.resnets.1.conv2 : 4.0 up_blocks.0.resnets.2.conv1 : 4.0 up_blocks.0.resnets.2.conv2 : 4.0 up_blocks.0.upsamplers.0.conv : 4.0 up_blocks.1.resnets.0.conv1 : 3.0 up_blocks.1.resnets.0.conv2 : 3.0 up_blocks.1.resnets.1.conv1 : 3.0 up_blocks.1.resnets.1.conv2 : 3.0 up_blocks.1.resnets.2.conv1 : 3.0 up_blocks.1.resnets.2.conv2 : 3.0 up_blocks.1.upsamplers.0.conv : 3.0 up_blocks.2.resnets.0.conv1 : 2.0 up_blocks.2.resnets.0.conv2 : 2.0 up_blocks.2.resnets.1.conv1 : 2.0 up_blocks.2.resnets.1.conv2 : 2.0 up_blocks.2.resnets.2.conv1 : 2.0 up_blocks.2.resnets.2.conv2 : 2.0 up_blocks.2.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 4.0 mid_block.resnets.0.conv2 : 4.0 mid_block.resnets.1.conv1 : 4.0 mid_block.resnets.1.conv2 : 4.0 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:21<17:18, 21.19s/it] 4%|▍ | 2/50 [00:42<16:57, 21.20s/it] 6%|▌ | 3/50 [01:03<16:40, 21.28s/it] 8%|▊ | 4/50 [01:25<16:22, 21.35s/it] 10%|█ | 5/50 [01:46<16:03, 21.40s/it] 12%|█▏ | 6/50 [02:08<15:44, 21.46s/it] 14%|█▍ | 7/50 [02:29<15:24, 21.50s/it] 16%|█▌ | 8/50 [02:51<15:04, 21.53s/it] 18%|█▊ | 9/50 [03:13<14:43, 21.55s/it] 20%|██ | 10/50 [03:34<14:22, 21.57s/it] 22%|██▏ | 11/50 [03:56<14:02, 21.59s/it] 24%|██▍ | 12/50 [04:17<13:40, 21.60s/it] 26%|██▌ | 13/50 [04:39<13:19, 21.60s/it] 28%|██▊ | 14/50 [05:01<12:57, 21.61s/it] 30%|███ | 15/50 [05:22<12:36, 21.60s/it] 32%|███▏ | 16/50 [05:44<12:14, 21.61s/it] 34%|███▍ | 17/50 [06:05<11:53, 21.61s/it] 36%|███▌ | 18/50 [06:27<11:31, 21.61s/it] 38%|███▊ | 19/50 [06:49<11:10, 21.62s/it] 40%|████ | 20/50 [07:10<10:48, 21.61s/it] 42%|████▏ | 21/50 [07:32<10:26, 21.61s/it] 44%|████▍ | 22/50 [07:54<10:05, 21.61s/it] 46%|████▌ | 23/50 [08:15<09:43, 21.61s/it] 48%|████▊ | 24/50 [08:37<09:22, 21.62s/it] 50%|█████ | 25/50 [08:58<09:00, 21.61s/it] 52%|█████▏ | 26/50 [09:20<08:38, 21.61s/it] 54%|█████▍ | 27/50 [09:42<08:16, 21.61s/it] 56%|█████▌ | 28/50 [10:03<07:55, 21.60s/it] 58%|█████▊ | 29/50 [10:25<07:33, 21.61s/it] 60%|██████ | 30/50 [10:46<07:12, 21.61s/it] 62%|██████▏ | 31/50 [11:08<06:50, 21.60s/it] 64%|██████▍ | 32/50 [11:30<06:28, 21.61s/it] 66%|██████▌ | 33/50 [11:51<06:07, 21.61s/it] 68%|██████▊ | 34/50 [12:13<05:45, 21.60s/it] 70%|███████ | 35/50 [12:34<05:24, 21.61s/it] 72%|███████▏ | 36/50 [12:45<04:17, 18.36s/it] 74%|███████▍ | 37/50 [12:56<03:29, 16.08s/it] 76%|███████▌ | 38/50 [13:07<02:53, 14.49s/it] 78%|███████▊ | 39/50 [13:18<02:27, 13.39s/it] 80%|████████ | 40/50 [13:28<02:06, 12.61s/it] 82%|████████▏ | 41/50 [13:39<01:48, 12.06s/it] 84%|████████▍ | 42/50 [13:50<01:33, 11.67s/it] 86%|████████▌ | 43/50 [14:01<01:19, 11.40s/it] 88%|████████▊ | 44/50 [14:11<01:07, 11.22s/it] 90%|█████████ | 45/50 [14:22<00:55, 11.09s/it] 92%|█████████▏| 46/50 [14:33<00:43, 11.00s/it] 94%|█████████▍| 47/50 [14:44<00:32, 10.93s/it] 96%|█████████▌| 48/50 [14:55<00:21, 10.89s/it] 98%|█████████▊| 49/50 [15:05<00:10, 10.86s/it] 100%|██████████| 50/50 [15:16<00:00, 10.84s/it] 100%|██████████| 50/50 [15:16<00:00, 18.33s/it]Prediction
cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96IDtpz364dbrglqafarnkmdlxrj5eStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 4096
- height
- 2048
- prompt
- A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear
- num_inference_steps
- 50
{ "width": 4096, "height": 2048, "prompt": "A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", { input: { width: 4096, height: 2048, prompt: "A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", input={ "width": 4096, "height": 2048, "prompt": "A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", "input": { "width": 4096, "height": 2048, "prompt": "A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T18:36:41.160675Z", "created_at": "2023-10-18T18:33:40.535572Z", "data_removed": false, "error": null, "id": "tpz364dbrglqafarnkmdlxrj5e", "input": { "width": 4096, "height": 2048, "prompt": "A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear", "num_inference_steps": 50 }, "logs": "Using seed: 27061\nReading dilation settings\ndown_blocks.2.resnets.0.conv1 : 3.0\ndown_blocks.2.resnets.0.conv2 : 3.0\ndown_blocks.2.resnets.1.conv1 : 3.0\ndown_blocks.2.resnets.1.conv2 : 3.0\ndown_blocks.2.downsamplers.0.conv : 3.0\ndown_blocks.3.resnets.0.conv1 : 4.0\ndown_blocks.3.resnets.0.conv2 : 4.0\ndown_blocks.3.resnets.1.conv1 : 4.0\ndown_blocks.3.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.0.conv1 : 4.0\nup_blocks.0.resnets.0.conv2 : 4.0\nup_blocks.0.resnets.1.conv1 : 4.0\nup_blocks.0.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.2.conv1 : 4.0\nup_blocks.0.resnets.2.conv2 : 4.0\nup_blocks.0.upsamplers.0.conv : 4.0\nup_blocks.1.resnets.0.conv1 : 3.0\nup_blocks.1.resnets.0.conv2 : 3.0\nup_blocks.1.resnets.1.conv1 : 3.0\nup_blocks.1.resnets.1.conv2 : 3.0\nup_blocks.1.resnets.2.conv1 : 3.0\nup_blocks.1.resnets.2.conv2 : 3.0\nup_blocks.1.upsamplers.0.conv : 3.0\nup_blocks.2.resnets.0.conv1 : 2.0\nup_blocks.2.resnets.0.conv2 : 2.0\nup_blocks.2.resnets.1.conv1 : 2.0\nup_blocks.2.resnets.1.conv2 : 2.0\nup_blocks.2.resnets.2.conv1 : 2.0\nup_blocks.2.resnets.2.conv2 : 2.0\nup_blocks.2.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 4.0\nmid_block.resnets.0.conv2 : 4.0\nmid_block.resnets.1.conv1 : 4.0\nmid_block.resnets.1.conv2 : 4.0\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:04<03:18, 4.04s/it]\n 4%|▍ | 2/50 [00:08<03:14, 4.04s/it]\n 6%|▌ | 3/50 [00:12<03:10, 4.05s/it]\n 8%|▊ | 4/50 [00:16<03:06, 4.05s/it]\n 10%|█ | 5/50 [00:20<03:02, 4.06s/it]\n 12%|█▏ | 6/50 [00:24<02:58, 4.06s/it]\n 14%|█▍ | 7/50 [00:28<02:54, 4.06s/it]\n 16%|█▌ | 8/50 [00:32<02:50, 4.06s/it]\n 18%|█▊ | 9/50 [00:36<02:46, 4.07s/it]\n 20%|██ | 10/50 [00:40<02:42, 4.07s/it]\n 22%|██▏ | 11/50 [00:44<02:38, 4.07s/it]\n 24%|██▍ | 12/50 [00:48<02:34, 4.07s/it]\n 26%|██▌ | 13/50 [00:52<02:30, 4.07s/it]\n 28%|██▊ | 14/50 [00:56<02:26, 4.07s/it]\n 30%|███ | 15/50 [01:00<02:22, 4.07s/it]\n 32%|███▏ | 16/50 [01:05<02:18, 4.07s/it]\n 34%|███▍ | 17/50 [01:09<02:14, 4.07s/it]\n 36%|███▌ | 18/50 [01:13<02:10, 4.07s/it]\n 38%|███▊ | 19/50 [01:17<02:06, 4.08s/it]\n 40%|████ | 20/50 [01:21<02:02, 4.07s/it]\n 42%|████▏ | 21/50 [01:25<01:58, 4.07s/it]\n 44%|████▍ | 22/50 [01:29<01:54, 4.07s/it]\n 46%|████▌ | 23/50 [01:33<01:49, 4.07s/it]\n 48%|████▊ | 24/50 [01:37<01:45, 4.07s/it]\n 50%|█████ | 25/50 [01:41<01:41, 4.07s/it]\n 52%|█████▏ | 26/50 [01:45<01:37, 4.07s/it]\n 54%|█████▍ | 27/50 [01:49<01:33, 4.08s/it]\n 56%|█████▌ | 28/50 [01:53<01:29, 4.08s/it]\n 58%|█████▊ | 29/50 [01:58<01:25, 4.08s/it]\n 60%|██████ | 30/50 [02:02<01:21, 4.08s/it]\n 62%|██████▏ | 31/50 [02:06<01:17, 4.08s/it]\n 64%|██████▍ | 32/50 [02:10<01:13, 4.08s/it]\n 66%|██████▌ | 33/50 [02:14<01:09, 4.08s/it]\n 68%|██████▊ | 34/50 [02:18<01:05, 4.08s/it]\n 70%|███████ | 35/50 [02:22<01:01, 4.08s/it]\n 72%|███████▏ | 36/50 [02:24<00:48, 3.47s/it]\n 74%|███████▍ | 37/50 [02:26<00:39, 3.04s/it]\n 76%|███████▌ | 38/50 [02:28<00:32, 2.74s/it]\n 78%|███████▊ | 39/50 [02:30<00:27, 2.53s/it]\n 80%|████████ | 40/50 [02:32<00:23, 2.38s/it]\n 82%|████████▏ | 41/50 [02:34<00:20, 2.28s/it]\n 84%|████████▍ | 42/50 [02:36<00:17, 2.21s/it]\n 86%|████████▌ | 43/50 [02:38<00:15, 2.16s/it]\n 88%|████████▊ | 44/50 [02:40<00:12, 2.12s/it]\n 90%|█████████ | 45/50 [02:42<00:10, 2.10s/it]\n 92%|█████████▏| 46/50 [02:44<00:08, 2.08s/it]\n 94%|█████████▍| 47/50 [02:46<00:06, 2.07s/it]\n 96%|█████████▌| 48/50 [02:49<00:04, 2.06s/it]\n 98%|█████████▊| 49/50 [02:51<00:02, 2.05s/it]\n100%|██████████| 50/50 [02:53<00:00, 2.05s/it]\n100%|██████████| 50/50 [02:53<00:00, 3.46s/it]", "metrics": { "predict_time": 180.736966, "total_time": 180.625103 }, "output": "https://pbxt.replicate.delivery/CNKxnZeQBBR1HSS6A0jE943otgehgCcQ6qaTHEdxSmJ3e6eGB/out.png", "started_at": "2023-10-18T18:33:40.423709Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/tpz364dbrglqafarnkmdlxrj5e", "cancel": "https://api.replicate.com/v1/predictions/tpz364dbrglqafarnkmdlxrj5e/cancel" }, "version": "8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96" }Generated inUsing seed: 27061 Reading dilation settings down_blocks.2.resnets.0.conv1 : 3.0 down_blocks.2.resnets.0.conv2 : 3.0 down_blocks.2.resnets.1.conv1 : 3.0 down_blocks.2.resnets.1.conv2 : 3.0 down_blocks.2.downsamplers.0.conv : 3.0 down_blocks.3.resnets.0.conv1 : 4.0 down_blocks.3.resnets.0.conv2 : 4.0 down_blocks.3.resnets.1.conv1 : 4.0 down_blocks.3.resnets.1.conv2 : 4.0 up_blocks.0.resnets.0.conv1 : 4.0 up_blocks.0.resnets.0.conv2 : 4.0 up_blocks.0.resnets.1.conv1 : 4.0 up_blocks.0.resnets.1.conv2 : 4.0 up_blocks.0.resnets.2.conv1 : 4.0 up_blocks.0.resnets.2.conv2 : 4.0 up_blocks.0.upsamplers.0.conv : 4.0 up_blocks.1.resnets.0.conv1 : 3.0 up_blocks.1.resnets.0.conv2 : 3.0 up_blocks.1.resnets.1.conv1 : 3.0 up_blocks.1.resnets.1.conv2 : 3.0 up_blocks.1.resnets.2.conv1 : 3.0 up_blocks.1.resnets.2.conv2 : 3.0 up_blocks.1.upsamplers.0.conv : 3.0 up_blocks.2.resnets.0.conv1 : 2.0 up_blocks.2.resnets.0.conv2 : 2.0 up_blocks.2.resnets.1.conv1 : 2.0 up_blocks.2.resnets.1.conv2 : 2.0 up_blocks.2.resnets.2.conv1 : 2.0 up_blocks.2.resnets.2.conv2 : 2.0 up_blocks.2.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 4.0 mid_block.resnets.0.conv2 : 4.0 mid_block.resnets.1.conv1 : 4.0 mid_block.resnets.1.conv2 : 4.0 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:04<03:18, 4.04s/it] 4%|▍ | 2/50 [00:08<03:14, 4.04s/it] 6%|▌ | 3/50 [00:12<03:10, 4.05s/it] 8%|▊ | 4/50 [00:16<03:06, 4.05s/it] 10%|█ | 5/50 [00:20<03:02, 4.06s/it] 12%|█▏ | 6/50 [00:24<02:58, 4.06s/it] 14%|█▍ | 7/50 [00:28<02:54, 4.06s/it] 16%|█▌ | 8/50 [00:32<02:50, 4.06s/it] 18%|█▊ | 9/50 [00:36<02:46, 4.07s/it] 20%|██ | 10/50 [00:40<02:42, 4.07s/it] 22%|██▏ | 11/50 [00:44<02:38, 4.07s/it] 24%|██▍ | 12/50 [00:48<02:34, 4.07s/it] 26%|██▌ | 13/50 [00:52<02:30, 4.07s/it] 28%|██▊ | 14/50 [00:56<02:26, 4.07s/it] 30%|███ | 15/50 [01:00<02:22, 4.07s/it] 32%|███▏ | 16/50 [01:05<02:18, 4.07s/it] 34%|███▍ | 17/50 [01:09<02:14, 4.07s/it] 36%|███▌ | 18/50 [01:13<02:10, 4.07s/it] 38%|███▊ | 19/50 [01:17<02:06, 4.08s/it] 40%|████ | 20/50 [01:21<02:02, 4.07s/it] 42%|████▏ | 21/50 [01:25<01:58, 4.07s/it] 44%|████▍ | 22/50 [01:29<01:54, 4.07s/it] 46%|████▌ | 23/50 [01:33<01:49, 4.07s/it] 48%|████▊ | 24/50 [01:37<01:45, 4.07s/it] 50%|█████ | 25/50 [01:41<01:41, 4.07s/it] 52%|█████▏ | 26/50 [01:45<01:37, 4.07s/it] 54%|█████▍ | 27/50 [01:49<01:33, 4.08s/it] 56%|█████▌ | 28/50 [01:53<01:29, 4.08s/it] 58%|█████▊ | 29/50 [01:58<01:25, 4.08s/it] 60%|██████ | 30/50 [02:02<01:21, 4.08s/it] 62%|██████▏ | 31/50 [02:06<01:17, 4.08s/it] 64%|██████▍ | 32/50 [02:10<01:13, 4.08s/it] 66%|██████▌ | 33/50 [02:14<01:09, 4.08s/it] 68%|██████▊ | 34/50 [02:18<01:05, 4.08s/it] 70%|███████ | 35/50 [02:22<01:01, 4.08s/it] 72%|███████▏ | 36/50 [02:24<00:48, 3.47s/it] 74%|███████▍ | 37/50 [02:26<00:39, 3.04s/it] 76%|███████▌ | 38/50 [02:28<00:32, 2.74s/it] 78%|███████▊ | 39/50 [02:30<00:27, 2.53s/it] 80%|████████ | 40/50 [02:32<00:23, 2.38s/it] 82%|████████▏ | 41/50 [02:34<00:20, 2.28s/it] 84%|████████▍ | 42/50 [02:36<00:17, 2.21s/it] 86%|████████▌ | 43/50 [02:38<00:15, 2.16s/it] 88%|████████▊ | 44/50 [02:40<00:12, 2.12s/it] 90%|█████████ | 45/50 [02:42<00:10, 2.10s/it] 92%|█████████▏| 46/50 [02:44<00:08, 2.08s/it] 94%|█████████▍| 47/50 [02:46<00:06, 2.07s/it] 96%|█████████▌| 48/50 [02:49<00:04, 2.06s/it] 98%|█████████▊| 49/50 [02:51<00:02, 2.05s/it] 100%|██████████| 50/50 [02:53<00:00, 2.05s/it] 100%|██████████| 50/50 [02:53<00:00, 3.46s/it]Prediction
cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96IDjzpyg7tbbw2qgdwjxoagfpbwt4StatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 2560
- height
- 4096
- prompt
- A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details
- num_inference_steps
- 50
{ "width": 2560, "height": 4096, "prompt": "A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", { input: { width: 2560, height: 4096, prompt: "A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", input={ "width": 2560, "height": 4096, "prompt": "A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", "input": { "width": 2560, "height": 4096, "prompt": "A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T18:44:43.231645Z", "created_at": "2023-10-18T18:40:26.235841Z", "data_removed": false, "error": null, "id": "jzpyg7tbbw2qgdwjxoagfpbwt4", "input": { "width": 2560, "height": 4096, "prompt": "A corgi sits on a beach chair on a beautiful beach, with palm trees behind, high details", "num_inference_steps": 50 }, "logs": "Using seed: 38458\nReading dilation settings\ndown_blocks.2.resnets.0.conv1 : 3.0\ndown_blocks.2.resnets.0.conv2 : 3.0\ndown_blocks.2.resnets.1.conv1 : 3.0\ndown_blocks.2.resnets.1.conv2 : 3.0\ndown_blocks.2.downsamplers.0.conv : 3.0\ndown_blocks.3.resnets.0.conv1 : 4.0\ndown_blocks.3.resnets.0.conv2 : 4.0\ndown_blocks.3.resnets.1.conv1 : 4.0\ndown_blocks.3.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.0.conv1 : 4.0\nup_blocks.0.resnets.0.conv2 : 4.0\nup_blocks.0.resnets.1.conv1 : 4.0\nup_blocks.0.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.2.conv1 : 4.0\nup_blocks.0.resnets.2.conv2 : 4.0\nup_blocks.0.upsamplers.0.conv : 4.0\nup_blocks.1.resnets.0.conv1 : 3.0\nup_blocks.1.resnets.0.conv2 : 3.0\nup_blocks.1.resnets.1.conv1 : 3.0\nup_blocks.1.resnets.1.conv2 : 3.0\nup_blocks.1.resnets.2.conv1 : 3.0\nup_blocks.1.resnets.2.conv2 : 3.0\nup_blocks.1.upsamplers.0.conv : 3.0\nup_blocks.2.resnets.0.conv1 : 2.0\nup_blocks.2.resnets.0.conv2 : 2.0\nup_blocks.2.resnets.1.conv1 : 2.0\nup_blocks.2.resnets.1.conv2 : 2.0\nup_blocks.2.resnets.2.conv1 : 2.0\nup_blocks.2.resnets.2.conv2 : 2.0\nup_blocks.2.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 4.0\nmid_block.resnets.0.conv2 : 4.0\nmid_block.resnets.1.conv1 : 4.0\nmid_block.resnets.1.conv2 : 4.0\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:05<04:44, 5.81s/it]\n 4%|▍ | 2/50 [00:11<04:37, 5.79s/it]\n 6%|▌ | 3/50 [00:17<04:32, 5.79s/it]\n 8%|▊ | 4/50 [00:23<04:26, 5.79s/it]\n 10%|█ | 5/50 [00:28<04:20, 5.80s/it]\n 12%|█▏ | 6/50 [00:34<04:15, 5.80s/it]\n 14%|█▍ | 7/50 [00:40<04:09, 5.80s/it]\n 16%|█▌ | 8/50 [00:46<04:03, 5.80s/it]\n 18%|█▊ | 9/50 [00:52<03:58, 5.81s/it]\n 20%|██ | 10/50 [00:58<03:52, 5.81s/it]\n 22%|██▏ | 11/50 [01:03<03:46, 5.81s/it]\n 24%|██▍ | 12/50 [01:09<03:41, 5.82s/it]\n 26%|██▌ | 13/50 [01:15<03:35, 5.82s/it]\n 28%|██▊ | 14/50 [01:21<03:29, 5.82s/it]\n 30%|███ | 15/50 [01:27<03:23, 5.83s/it]\n 32%|███▏ | 16/50 [01:32<03:18, 5.82s/it]\n 34%|███▍ | 17/50 [01:38<03:12, 5.83s/it]\n 36%|███▌ | 18/50 [01:44<03:06, 5.83s/it]\n 38%|███▊ | 19/50 [01:50<03:00, 5.82s/it]\n 40%|████ | 20/50 [01:56<02:54, 5.82s/it]\n 42%|████▏ | 21/50 [02:02<02:48, 5.82s/it]\n 44%|████▍ | 22/50 [02:07<02:43, 5.83s/it]\n 46%|████▌ | 23/50 [02:13<02:37, 5.83s/it]\n 48%|████▊ | 24/50 [02:19<02:31, 5.83s/it]\n 50%|█████ | 25/50 [02:25<02:25, 5.83s/it]\n 52%|█████▏ | 26/50 [02:31<02:19, 5.83s/it]\n 54%|█████▍ | 27/50 [02:37<02:14, 5.83s/it]\n 56%|█████▌ | 28/50 [02:42<02:08, 5.83s/it]\n 58%|█████▊ | 29/50 [02:48<02:02, 5.83s/it]\n 60%|██████ | 30/50 [02:54<01:56, 5.83s/it]\n 62%|██████▏ | 31/50 [03:00<01:50, 5.83s/it]\n 64%|██████▍ | 32/50 [03:06<01:44, 5.83s/it]\n 66%|██████▌ | 33/50 [03:12<01:39, 5.84s/it]\n 68%|██████▊ | 34/50 [03:17<01:33, 5.84s/it]\n 70%|███████ | 35/50 [03:23<01:27, 5.83s/it]\n 72%|███████▏ | 36/50 [03:26<01:09, 4.96s/it]\n 74%|███████▍ | 37/50 [03:29<00:56, 4.34s/it]\n 76%|███████▌ | 38/50 [03:32<00:46, 3.91s/it]\n 78%|███████▊ | 39/50 [03:35<00:39, 3.61s/it]\n 80%|████████ | 40/50 [03:38<00:34, 3.40s/it]\n 82%|████████▏ | 41/50 [03:41<00:29, 3.25s/it]\n 84%|████████▍ | 42/50 [03:44<00:25, 3.15s/it]\n 86%|████████▌ | 43/50 [03:47<00:21, 3.08s/it]\n 88%|████████▊ | 44/50 [03:49<00:18, 3.03s/it]\n 90%|█████████ | 45/50 [03:52<00:14, 2.99s/it]\n 92%|█████████▏| 46/50 [03:55<00:11, 2.97s/it]\n 94%|█████████▍| 47/50 [03:58<00:08, 2.95s/it]\n 96%|█████████▌| 48/50 [04:01<00:05, 2.94s/it]\n 98%|█████████▊| 49/50 [04:04<00:02, 2.93s/it]\n100%|██████████| 50/50 [04:07<00:00, 2.94s/it]\n100%|██████████| 50/50 [04:07<00:00, 4.95s/it]", "metrics": { "predict_time": 256.994984, "total_time": 256.995804 }, "output": "https://pbxt.replicate.delivery/xjJqIFs4Ze1LZ6XylITeWfjRoHcm5fQv5p0te8vrFlYJzs7NC/out.png", "started_at": "2023-10-18T18:40:26.236661Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jzpyg7tbbw2qgdwjxoagfpbwt4", "cancel": "https://api.replicate.com/v1/predictions/jzpyg7tbbw2qgdwjxoagfpbwt4/cancel" }, "version": "8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96" }Generated inUsing seed: 38458 Reading dilation settings down_blocks.2.resnets.0.conv1 : 3.0 down_blocks.2.resnets.0.conv2 : 3.0 down_blocks.2.resnets.1.conv1 : 3.0 down_blocks.2.resnets.1.conv2 : 3.0 down_blocks.2.downsamplers.0.conv : 3.0 down_blocks.3.resnets.0.conv1 : 4.0 down_blocks.3.resnets.0.conv2 : 4.0 down_blocks.3.resnets.1.conv1 : 4.0 down_blocks.3.resnets.1.conv2 : 4.0 up_blocks.0.resnets.0.conv1 : 4.0 up_blocks.0.resnets.0.conv2 : 4.0 up_blocks.0.resnets.1.conv1 : 4.0 up_blocks.0.resnets.1.conv2 : 4.0 up_blocks.0.resnets.2.conv1 : 4.0 up_blocks.0.resnets.2.conv2 : 4.0 up_blocks.0.upsamplers.0.conv : 4.0 up_blocks.1.resnets.0.conv1 : 3.0 up_blocks.1.resnets.0.conv2 : 3.0 up_blocks.1.resnets.1.conv1 : 3.0 up_blocks.1.resnets.1.conv2 : 3.0 up_blocks.1.resnets.2.conv1 : 3.0 up_blocks.1.resnets.2.conv2 : 3.0 up_blocks.1.upsamplers.0.conv : 3.0 up_blocks.2.resnets.0.conv1 : 2.0 up_blocks.2.resnets.0.conv2 : 2.0 up_blocks.2.resnets.1.conv1 : 2.0 up_blocks.2.resnets.1.conv2 : 2.0 up_blocks.2.resnets.2.conv1 : 2.0 up_blocks.2.resnets.2.conv2 : 2.0 up_blocks.2.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 4.0 mid_block.resnets.0.conv2 : 4.0 mid_block.resnets.1.conv1 : 4.0 mid_block.resnets.1.conv2 : 4.0 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:05<04:44, 5.81s/it] 4%|▍ | 2/50 [00:11<04:37, 5.79s/it] 6%|▌ | 3/50 [00:17<04:32, 5.79s/it] 8%|▊ | 4/50 [00:23<04:26, 5.79s/it] 10%|█ | 5/50 [00:28<04:20, 5.80s/it] 12%|█▏ | 6/50 [00:34<04:15, 5.80s/it] 14%|█▍ | 7/50 [00:40<04:09, 5.80s/it] 16%|█▌ | 8/50 [00:46<04:03, 5.80s/it] 18%|█▊ | 9/50 [00:52<03:58, 5.81s/it] 20%|██ | 10/50 [00:58<03:52, 5.81s/it] 22%|██▏ | 11/50 [01:03<03:46, 5.81s/it] 24%|██▍ | 12/50 [01:09<03:41, 5.82s/it] 26%|██▌ | 13/50 [01:15<03:35, 5.82s/it] 28%|██▊ | 14/50 [01:21<03:29, 5.82s/it] 30%|███ | 15/50 [01:27<03:23, 5.83s/it] 32%|███▏ | 16/50 [01:32<03:18, 5.82s/it] 34%|███▍ | 17/50 [01:38<03:12, 5.83s/it] 36%|███▌ | 18/50 [01:44<03:06, 5.83s/it] 38%|███▊ | 19/50 [01:50<03:00, 5.82s/it] 40%|████ | 20/50 [01:56<02:54, 5.82s/it] 42%|████▏ | 21/50 [02:02<02:48, 5.82s/it] 44%|████▍ | 22/50 [02:07<02:43, 5.83s/it] 46%|████▌ | 23/50 [02:13<02:37, 5.83s/it] 48%|████▊ | 24/50 [02:19<02:31, 5.83s/it] 50%|█████ | 25/50 [02:25<02:25, 5.83s/it] 52%|█████▏ | 26/50 [02:31<02:19, 5.83s/it] 54%|█████▍ | 27/50 [02:37<02:14, 5.83s/it] 56%|█████▌ | 28/50 [02:42<02:08, 5.83s/it] 58%|█████▊ | 29/50 [02:48<02:02, 5.83s/it] 60%|██████ | 30/50 [02:54<01:56, 5.83s/it] 62%|██████▏ | 31/50 [03:00<01:50, 5.83s/it] 64%|██████▍ | 32/50 [03:06<01:44, 5.83s/it] 66%|██████▌ | 33/50 [03:12<01:39, 5.84s/it] 68%|██████▊ | 34/50 [03:17<01:33, 5.84s/it] 70%|███████ | 35/50 [03:23<01:27, 5.83s/it] 72%|███████▏ | 36/50 [03:26<01:09, 4.96s/it] 74%|███████▍ | 37/50 [03:29<00:56, 4.34s/it] 76%|███████▌ | 38/50 [03:32<00:46, 3.91s/it] 78%|███████▊ | 39/50 [03:35<00:39, 3.61s/it] 80%|████████ | 40/50 [03:38<00:34, 3.40s/it] 82%|████████▏ | 41/50 [03:41<00:29, 3.25s/it] 84%|████████▍ | 42/50 [03:44<00:25, 3.15s/it] 86%|████████▌ | 43/50 [03:47<00:21, 3.08s/it] 88%|████████▊ | 44/50 [03:49<00:18, 3.03s/it] 90%|█████████ | 45/50 [03:52<00:14, 2.99s/it] 92%|█████████▏| 46/50 [03:55<00:11, 2.97s/it] 94%|█████████▍| 47/50 [03:58<00:08, 2.95s/it] 96%|█████████▌| 48/50 [04:01<00:05, 2.94s/it] 98%|█████████▊| 49/50 [04:04<00:02, 2.93s/it] 100%|██████████| 50/50 [04:07<00:00, 2.94s/it] 100%|██████████| 50/50 [04:07<00:00, 4.95s/it]Prediction
cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96ID22bfutdbebewxhrvqvixlnlh2aStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 4096
- height
- 4096
- prompt
- A studio photo of a rainbow coloured cat
- num_inference_steps
- 50
{ "width": 4096, "height": 4096, "prompt": "A studio photo of a rainbow coloured cat", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", { input: { width: 4096, height: 4096, prompt: "A studio photo of a rainbow coloured cat", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", input={ "width": 4096, "height": 4096, "prompt": "A studio photo of a rainbow coloured cat", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96", "input": { "width": 4096, "height": 4096, "prompt": "A studio photo of a rainbow coloured cat", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T18:53:54.197568Z", "created_at": "2023-10-18T18:40:54.506453Z", "data_removed": false, "error": null, "id": "22bfutdbebewxhrvqvixlnlh2a", "input": { "width": 4096, "height": 4096, "prompt": "A studio photo of a rainbow coloured cat", "num_inference_steps": 50 }, "logs": "Using seed: 47054\nReading dilation settings\ndown_blocks.2.resnets.0.conv1 : 3.0\ndown_blocks.2.resnets.0.conv2 : 3.0\ndown_blocks.2.resnets.1.conv1 : 3.0\ndown_blocks.2.resnets.1.conv2 : 3.0\ndown_blocks.2.downsamplers.0.conv : 3.0\ndown_blocks.3.resnets.0.conv1 : 4.0\ndown_blocks.3.resnets.0.conv2 : 4.0\ndown_blocks.3.resnets.1.conv1 : 4.0\ndown_blocks.3.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.0.conv1 : 4.0\nup_blocks.0.resnets.0.conv2 : 4.0\nup_blocks.0.resnets.1.conv1 : 4.0\nup_blocks.0.resnets.1.conv2 : 4.0\nup_blocks.0.resnets.2.conv1 : 4.0\nup_blocks.0.resnets.2.conv2 : 4.0\nup_blocks.0.upsamplers.0.conv : 4.0\nup_blocks.1.resnets.0.conv1 : 3.0\nup_blocks.1.resnets.0.conv2 : 3.0\nup_blocks.1.resnets.1.conv1 : 3.0\nup_blocks.1.resnets.1.conv2 : 3.0\nup_blocks.1.resnets.2.conv1 : 3.0\nup_blocks.1.resnets.2.conv2 : 3.0\nup_blocks.1.upsamplers.0.conv : 3.0\nup_blocks.2.resnets.0.conv1 : 2.0\nup_blocks.2.resnets.0.conv2 : 2.0\nup_blocks.2.resnets.1.conv1 : 2.0\nup_blocks.2.resnets.1.conv2 : 2.0\nup_blocks.2.resnets.2.conv1 : 2.0\nup_blocks.2.resnets.2.conv2 : 2.0\nup_blocks.2.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 4.0\nmid_block.resnets.0.conv2 : 4.0\nmid_block.resnets.1.conv1 : 4.0\nmid_block.resnets.1.conv2 : 4.0\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:13<10:46, 13.20s/it]\n 4%|▍ | 2/50 [00:25<10:19, 12.90s/it]\n 6%|▌ | 3/50 [00:38<10:01, 12.81s/it]\n 8%|▊ | 4/50 [00:51<09:49, 12.81s/it]\n 10%|█ | 5/50 [01:04<09:35, 12.79s/it]\n 12%|█▏ | 6/50 [01:16<09:21, 12.77s/it]\n 14%|█▍ | 7/50 [01:29<09:07, 12.74s/it]\n 16%|█▌ | 8/50 [01:42<08:54, 12.74s/it]\n 18%|█▊ | 9/50 [01:55<08:42, 12.74s/it]\n 20%|██ | 10/50 [02:07<08:29, 12.74s/it]\n 22%|██▏ | 11/50 [02:20<08:16, 12.73s/it]\n 24%|██▍ | 12/50 [02:33<08:03, 12.72s/it]\n 26%|██▌ | 13/50 [02:45<07:51, 12.73s/it]\n 28%|██▊ | 14/50 [02:58<07:38, 12.72s/it]\n 30%|███ | 15/50 [03:11<07:25, 12.72s/it]\n 32%|███▏ | 16/50 [03:24<07:12, 12.72s/it]\n 34%|███▍ | 17/50 [03:36<06:59, 12.72s/it]\n 36%|███▌ | 18/50 [03:49<06:47, 12.73s/it]\n 38%|███▊ | 19/50 [04:02<06:34, 12.73s/it]\n 40%|████ | 20/50 [04:15<06:21, 12.73s/it]\n 42%|████▏ | 21/50 [04:27<06:09, 12.74s/it]\n 44%|████▍ | 22/50 [04:40<05:56, 12.74s/it]\n 46%|████▌ | 23/50 [04:53<05:44, 12.75s/it]\n 48%|████▊ | 24/50 [05:06<05:31, 12.74s/it]\n 50%|█████ | 25/50 [05:18<05:18, 12.74s/it]\n 52%|█████▏ | 26/50 [05:31<05:05, 12.73s/it]\n 54%|█████▍ | 27/50 [05:44<04:52, 12.74s/it]\n 56%|█████▌ | 28/50 [05:56<04:40, 12.73s/it]\n 58%|█████▊ | 29/50 [06:09<04:27, 12.72s/it]\n 60%|██████ | 30/50 [06:22<04:14, 12.72s/it]\n 62%|██████▏ | 31/50 [06:35<04:01, 12.72s/it]\n 64%|██████▍ | 32/50 [06:47<03:48, 12.71s/it]\n 66%|██████▌ | 33/50 [07:00<03:36, 12.71s/it]\n 68%|██████▊ | 34/50 [07:13<03:23, 12.71s/it]\n 70%|███████ | 35/50 [07:25<03:10, 12.71s/it]\n 72%|███████▏ | 36/50 [07:32<02:31, 10.80s/it]\n 74%|███████▍ | 37/50 [07:38<02:03, 9.47s/it]\n 76%|███████▌ | 38/50 [07:44<01:42, 8.53s/it]\n 78%|███████▊ | 39/50 [07:51<01:26, 7.88s/it]\n 80%|████████ | 40/50 [07:57<01:14, 7.42s/it]\n 82%|████████▏ | 41/50 [08:03<01:03, 7.09s/it]\n 84%|████████▍ | 42/50 [08:10<00:54, 6.87s/it]\n 86%|████████▌ | 43/50 [08:16<00:46, 6.71s/it]\n 88%|████████▊ | 44/50 [08:23<00:39, 6.61s/it]\n 90%|█████████ | 45/50 [08:29<00:32, 6.54s/it]\n 92%|█████████▏| 46/50 [08:35<00:25, 6.48s/it]\n 94%|█████████▍| 47/50 [08:42<00:19, 6.44s/it]\n 96%|█████████▌| 48/50 [08:48<00:12, 6.42s/it]\n 98%|█████████▊| 49/50 [08:54<00:06, 6.40s/it]\n100%|██████████| 50/50 [09:01<00:00, 6.38s/it]\n100%|██████████| 50/50 [09:01<00:00, 10.82s/it]", "metrics": { "predict_time": 555.479725, "total_time": 779.691115 }, "output": "https://pbxt.replicate.delivery/MZXlreeGsrpmRUyLshNV5tPX2fD3J6bP0ufKLJbs4PtC829GB/out.png", "started_at": "2023-10-18T18:44:38.717843Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/22bfutdbebewxhrvqvixlnlh2a", "cancel": "https://api.replicate.com/v1/predictions/22bfutdbebewxhrvqvixlnlh2a/cancel" }, "version": "8a767e8ae77ee1aa01d60faac74001ad7570155412acf266f24352228367ac96" }Generated inUsing seed: 47054 Reading dilation settings down_blocks.2.resnets.0.conv1 : 3.0 down_blocks.2.resnets.0.conv2 : 3.0 down_blocks.2.resnets.1.conv1 : 3.0 down_blocks.2.resnets.1.conv2 : 3.0 down_blocks.2.downsamplers.0.conv : 3.0 down_blocks.3.resnets.0.conv1 : 4.0 down_blocks.3.resnets.0.conv2 : 4.0 down_blocks.3.resnets.1.conv1 : 4.0 down_blocks.3.resnets.1.conv2 : 4.0 up_blocks.0.resnets.0.conv1 : 4.0 up_blocks.0.resnets.0.conv2 : 4.0 up_blocks.0.resnets.1.conv1 : 4.0 up_blocks.0.resnets.1.conv2 : 4.0 up_blocks.0.resnets.2.conv1 : 4.0 up_blocks.0.resnets.2.conv2 : 4.0 up_blocks.0.upsamplers.0.conv : 4.0 up_blocks.1.resnets.0.conv1 : 3.0 up_blocks.1.resnets.0.conv2 : 3.0 up_blocks.1.resnets.1.conv1 : 3.0 up_blocks.1.resnets.1.conv2 : 3.0 up_blocks.1.resnets.2.conv1 : 3.0 up_blocks.1.resnets.2.conv2 : 3.0 up_blocks.1.upsamplers.0.conv : 3.0 up_blocks.2.resnets.0.conv1 : 2.0 up_blocks.2.resnets.0.conv2 : 2.0 up_blocks.2.resnets.1.conv1 : 2.0 up_blocks.2.resnets.1.conv2 : 2.0 up_blocks.2.resnets.2.conv1 : 2.0 up_blocks.2.resnets.2.conv2 : 2.0 up_blocks.2.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 4.0 mid_block.resnets.0.conv2 : 4.0 mid_block.resnets.1.conv1 : 4.0 mid_block.resnets.1.conv2 : 4.0 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:13<10:46, 13.20s/it] 4%|▍ | 2/50 [00:25<10:19, 12.90s/it] 6%|▌ | 3/50 [00:38<10:01, 12.81s/it] 8%|▊ | 4/50 [00:51<09:49, 12.81s/it] 10%|█ | 5/50 [01:04<09:35, 12.79s/it] 12%|█▏ | 6/50 [01:16<09:21, 12.77s/it] 14%|█▍ | 7/50 [01:29<09:07, 12.74s/it] 16%|█▌ | 8/50 [01:42<08:54, 12.74s/it] 18%|█▊ | 9/50 [01:55<08:42, 12.74s/it] 20%|██ | 10/50 [02:07<08:29, 12.74s/it] 22%|██▏ | 11/50 [02:20<08:16, 12.73s/it] 24%|██▍ | 12/50 [02:33<08:03, 12.72s/it] 26%|██▌ | 13/50 [02:45<07:51, 12.73s/it] 28%|██▊ | 14/50 [02:58<07:38, 12.72s/it] 30%|███ | 15/50 [03:11<07:25, 12.72s/it] 32%|███▏ | 16/50 [03:24<07:12, 12.72s/it] 34%|███▍ | 17/50 [03:36<06:59, 12.72s/it] 36%|███▌ | 18/50 [03:49<06:47, 12.73s/it] 38%|███▊ | 19/50 [04:02<06:34, 12.73s/it] 40%|████ | 20/50 [04:15<06:21, 12.73s/it] 42%|████▏ | 21/50 [04:27<06:09, 12.74s/it] 44%|████▍ | 22/50 [04:40<05:56, 12.74s/it] 46%|████▌ | 23/50 [04:53<05:44, 12.75s/it] 48%|████▊ | 24/50 [05:06<05:31, 12.74s/it] 50%|█████ | 25/50 [05:18<05:18, 12.74s/it] 52%|█████▏ | 26/50 [05:31<05:05, 12.73s/it] 54%|█████▍ | 27/50 [05:44<04:52, 12.74s/it] 56%|█████▌ | 28/50 [05:56<04:40, 12.73s/it] 58%|█████▊ | 29/50 [06:09<04:27, 12.72s/it] 60%|██████ | 30/50 [06:22<04:14, 12.72s/it] 62%|██████▏ | 31/50 [06:35<04:01, 12.72s/it] 64%|██████▍ | 32/50 [06:47<03:48, 12.71s/it] 66%|██████▌ | 33/50 [07:00<03:36, 12.71s/it] 68%|██████▊ | 34/50 [07:13<03:23, 12.71s/it] 70%|███████ | 35/50 [07:25<03:10, 12.71s/it] 72%|███████▏ | 36/50 [07:32<02:31, 10.80s/it] 74%|███████▍ | 37/50 [07:38<02:03, 9.47s/it] 76%|███████▌ | 38/50 [07:44<01:42, 8.53s/it] 78%|███████▊ | 39/50 [07:51<01:26, 7.88s/it] 80%|████████ | 40/50 [07:57<01:14, 7.42s/it] 82%|████████▏ | 41/50 [08:03<01:03, 7.09s/it] 84%|████████▍ | 42/50 [08:10<00:54, 6.87s/it] 86%|████████▌ | 43/50 [08:16<00:46, 6.71s/it] 88%|████████▊ | 44/50 [08:23<00:39, 6.61s/it] 90%|█████████ | 45/50 [08:29<00:32, 6.54s/it] 92%|█████████▏| 46/50 [08:35<00:25, 6.48s/it] 94%|█████████▍| 47/50 [08:42<00:19, 6.44s/it] 96%|█████████▌| 48/50 [08:48<00:12, 6.42s/it] 98%|█████████▊| 49/50 [08:54<00:06, 6.40s/it] 100%|██████████| 50/50 [09:01<00:00, 6.38s/it] 100%|██████████| 50/50 [09:01<00:00, 10.82s/it]Prediction
cjwbw/scalecrafter:bfe45e8e9dd4d1e9d06651e3f8a4d7cceb0be755edef2e30cfde0dccc7b5b3e5ID5kcvc23bfgboayumajxf6rn5feStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 4096
- height
- 2048
- prompt
- baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas
- num_inference_steps
- 50
{ "width": 4096, "height": 2048, "prompt": "baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:bfe45e8e9dd4d1e9d06651e3f8a4d7cceb0be755edef2e30cfde0dccc7b5b3e5", { input: { width: 4096, height: 2048, prompt: "baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:bfe45e8e9dd4d1e9d06651e3f8a4d7cceb0be755edef2e30cfde0dccc7b5b3e5", input={ "width": 4096, "height": 2048, "prompt": "baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:bfe45e8e9dd4d1e9d06651e3f8a4d7cceb0be755edef2e30cfde0dccc7b5b3e5", "input": { "width": 4096, "height": 2048, "prompt": "baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T19:43:00.285315Z", "created_at": "2023-10-18T19:41:09.668279Z", "data_removed": false, "error": null, "id": "5kcvc23bfgboayumajxf6rn5fe", "input": { "width": 4096, "height": 2048, "prompt": "baby succulents from ikea interior pinterest plants cacti and flora. Black Bedroom Furniture Sets. Home Design Ideas", "num_inference_steps": 50 }, "logs": "Using seed: 48261\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:02<01:41, 2.07s/it]\n 4%|▍ | 2/50 [00:04<01:38, 2.06s/it]\n 6%|▌ | 3/50 [00:06<01:36, 2.05s/it]\n 8%|▊ | 4/50 [00:08<01:34, 2.05s/it]\n 10%|█ | 5/50 [00:10<01:32, 2.05s/it]\n 12%|█▏ | 6/50 [00:12<01:30, 2.05s/it]\n 14%|█▍ | 7/50 [00:14<01:28, 2.05s/it]\n 16%|█▌ | 8/50 [00:16<01:26, 2.05s/it]\n 18%|█▊ | 9/50 [00:18<01:24, 2.05s/it]\n 20%|██ | 10/50 [00:20<01:22, 2.05s/it]\n 22%|██▏ | 11/50 [00:22<01:20, 2.05s/it]\n 24%|██▍ | 12/50 [00:24<01:18, 2.06s/it]\n 26%|██▌ | 13/50 [00:26<01:16, 2.06s/it]\n 28%|██▊ | 14/50 [00:28<01:14, 2.06s/it]\n 30%|███ | 15/50 [00:30<01:12, 2.06s/it]\n 32%|███▏ | 16/50 [00:32<01:10, 2.06s/it]\n 34%|███▍ | 17/50 [00:34<01:08, 2.06s/it]\n 36%|███▌ | 18/50 [00:37<01:06, 2.06s/it]\n 38%|███▊ | 19/50 [00:39<01:03, 2.06s/it]\n 40%|████ | 20/50 [00:41<01:01, 2.06s/it]\n 42%|████▏ | 21/50 [00:43<00:59, 2.06s/it]\n 44%|████▍ | 22/50 [00:45<00:57, 2.06s/it]\n 46%|████▌ | 23/50 [00:47<00:55, 2.06s/it]\n 48%|████▊ | 24/50 [00:49<00:53, 2.06s/it]\n 50%|█████ | 25/50 [00:51<00:51, 2.06s/it]\n 52%|█████▏ | 26/50 [00:53<00:49, 2.06s/it]\n 54%|█████▍ | 27/50 [00:55<00:47, 2.06s/it]\n 56%|█████▌ | 28/50 [00:57<00:45, 2.06s/it]\n 58%|█████▊ | 29/50 [00:59<00:43, 2.06s/it]\n 60%|██████ | 30/50 [01:01<00:41, 2.06s/it]\n 62%|██████▏ | 31/50 [01:03<00:39, 2.06s/it]\n 64%|██████▍ | 32/50 [01:05<00:37, 2.06s/it]\n 66%|██████▌ | 33/50 [01:07<00:35, 2.06s/it]\n 68%|██████▊ | 34/50 [01:10<00:32, 2.06s/it]\n 70%|███████ | 35/50 [01:12<00:30, 2.06s/it]\n 72%|███████▏ | 36/50 [01:14<00:28, 2.06s/it]\n 74%|███████▍ | 37/50 [01:16<00:26, 2.07s/it]\n 76%|███████▌ | 38/50 [01:18<00:24, 2.07s/it]\n 78%|███████▊ | 39/50 [01:20<00:22, 2.06s/it]\n 80%|████████ | 40/50 [01:22<00:20, 2.06s/it]\n 82%|████████▏ | 41/50 [01:24<00:18, 2.06s/it]\n 84%|████████▍ | 42/50 [01:26<00:16, 2.06s/it]\n 86%|████████▌ | 43/50 [01:28<00:14, 2.07s/it]\n 88%|████████▊ | 44/50 [01:30<00:12, 2.06s/it]\n 90%|█████████ | 45/50 [01:32<00:10, 2.06s/it]\n 92%|█████████▏| 46/50 [01:34<00:08, 2.07s/it]\n 94%|█████████▍| 47/50 [01:36<00:06, 2.06s/it]\n 96%|█████████▌| 48/50 [01:38<00:04, 2.06s/it]\n 98%|█████████▊| 49/50 [01:40<00:02, 2.06s/it]\n100%|██████████| 50/50 [01:43<00:00, 2.06s/it]\n100%|██████████| 50/50 [01:43<00:00, 2.06s/it]", "metrics": { "predict_time": 110.621309, "total_time": 110.617036 }, "output": "https://pbxt.replicate.delivery/Epy6KQm76Yb8HB6bOhzBEH1eJU4rIM13pyvB6EuOcfOCdeeGB/out.png", "started_at": "2023-10-18T19:41:09.664006Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5kcvc23bfgboayumajxf6rn5fe", "cancel": "https://api.replicate.com/v1/predictions/5kcvc23bfgboayumajxf6rn5fe/cancel" }, "version": "bfe45e8e9dd4d1e9d06651e3f8a4d7cceb0be755edef2e30cfde0dccc7b5b3e5" }Generated inUsing seed: 48261 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<01:41, 2.07s/it] 4%|▍ | 2/50 [00:04<01:38, 2.06s/it] 6%|▌ | 3/50 [00:06<01:36, 2.05s/it] 8%|▊ | 4/50 [00:08<01:34, 2.05s/it] 10%|█ | 5/50 [00:10<01:32, 2.05s/it] 12%|█▏ | 6/50 [00:12<01:30, 2.05s/it] 14%|█▍ | 7/50 [00:14<01:28, 2.05s/it] 16%|█▌ | 8/50 [00:16<01:26, 2.05s/it] 18%|█▊ | 9/50 [00:18<01:24, 2.05s/it] 20%|██ | 10/50 [00:20<01:22, 2.05s/it] 22%|██▏ | 11/50 [00:22<01:20, 2.05s/it] 24%|██▍ | 12/50 [00:24<01:18, 2.06s/it] 26%|██▌ | 13/50 [00:26<01:16, 2.06s/it] 28%|██▊ | 14/50 [00:28<01:14, 2.06s/it] 30%|███ | 15/50 [00:30<01:12, 2.06s/it] 32%|███▏ | 16/50 [00:32<01:10, 2.06s/it] 34%|███▍ | 17/50 [00:34<01:08, 2.06s/it] 36%|███▌ | 18/50 [00:37<01:06, 2.06s/it] 38%|███▊ | 19/50 [00:39<01:03, 2.06s/it] 40%|████ | 20/50 [00:41<01:01, 2.06s/it] 42%|████▏ | 21/50 [00:43<00:59, 2.06s/it] 44%|████▍ | 22/50 [00:45<00:57, 2.06s/it] 46%|████▌ | 23/50 [00:47<00:55, 2.06s/it] 48%|████▊ | 24/50 [00:49<00:53, 2.06s/it] 50%|█████ | 25/50 [00:51<00:51, 2.06s/it] 52%|█████▏ | 26/50 [00:53<00:49, 2.06s/it] 54%|█████▍ | 27/50 [00:55<00:47, 2.06s/it] 56%|█████▌ | 28/50 [00:57<00:45, 2.06s/it] 58%|█████▊ | 29/50 [00:59<00:43, 2.06s/it] 60%|██████ | 30/50 [01:01<00:41, 2.06s/it] 62%|██████▏ | 31/50 [01:03<00:39, 2.06s/it] 64%|██████▍ | 32/50 [01:05<00:37, 2.06s/it] 66%|██████▌ | 33/50 [01:07<00:35, 2.06s/it] 68%|██████▊ | 34/50 [01:10<00:32, 2.06s/it] 70%|███████ | 35/50 [01:12<00:30, 2.06s/it] 72%|███████▏ | 36/50 [01:14<00:28, 2.06s/it] 74%|███████▍ | 37/50 [01:16<00:26, 2.07s/it] 76%|███████▌ | 38/50 [01:18<00:24, 2.07s/it] 78%|███████▊ | 39/50 [01:20<00:22, 2.06s/it] 80%|████████ | 40/50 [01:22<00:20, 2.06s/it] 82%|████████▏ | 41/50 [01:24<00:18, 2.06s/it] 84%|████████▍ | 42/50 [01:26<00:16, 2.06s/it] 86%|████████▌ | 43/50 [01:28<00:14, 2.07s/it] 88%|████████▊ | 44/50 [01:30<00:12, 2.06s/it] 90%|█████████ | 45/50 [01:32<00:10, 2.06s/it] 92%|█████████▏| 46/50 [01:34<00:08, 2.07s/it] 94%|█████████▍| 47/50 [01:36<00:06, 2.06s/it] 96%|█████████▌| 48/50 [01:38<00:04, 2.06s/it] 98%|█████████▊| 49/50 [01:40<00:02, 2.06s/it] 100%|██████████| 50/50 [01:43<00:00, 2.06s/it] 100%|██████████| 50/50 [01:43<00:00, 2.06s/it]Prediction
cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59IDeigpjbtbiz7ebcpkqigm2bmj4uStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 2048
- height
- 1024
- prompt
- A Cute Puppy with wings, Cartoon Drawings, high details
- dilate_scale
- down_blocks.3.resnets.0.conv1:2 down_blocks.3.resnets.0.conv2:2 down_blocks.3.resnets.1.conv1:2 down_blocks.3.resnets.1.conv2:2 up_blocks.0.resnets.0.conv1:2 up_blocks.0.resnets.0.conv2:2 up_blocks.0.resnets.1.conv1:2 up_blocks.0.resnets.1.conv2:2 up_blocks.0.resnets.2.conv1:2 up_blocks.0.resnets.2.conv2:2 up_blocks.0.upsamplers.0.conv:2 mid_block.resnets.0.conv1:2 mid_block.resnets.0.conv2:2 mid_block.resnets.1.conv1:2 mid_block.resnets.1.conv2:2
- num_inference_steps
- 50
{ "width": 2048, "height": 1024, "prompt": "A Cute Puppy with wings, Cartoon Drawings, high details", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2\n", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", { input: { width: 2048, height: 1024, prompt: "A Cute Puppy with wings, Cartoon Drawings, high details", dilate_scale: "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2\n", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", input={ "width": 2048, "height": 1024, "prompt": "A Cute Puppy with wings, Cartoon Drawings, high details", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2\n", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", "input": { "width": 2048, "height": 1024, "prompt": "A Cute Puppy with wings, Cartoon Drawings, high details", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\\ndown_blocks.3.resnets.0.conv2:2\\ndown_blocks.3.resnets.1.conv1:2\\ndown_blocks.3.resnets.1.conv2:2\\nup_blocks.0.resnets.0.conv1:2\\nup_blocks.0.resnets.0.conv2:2\\nup_blocks.0.resnets.1.conv1:2\\nup_blocks.0.resnets.1.conv2:2\\nup_blocks.0.resnets.2.conv1:2\\nup_blocks.0.resnets.2.conv2:2\\nup_blocks.0.upsamplers.0.conv:2\\nmid_block.resnets.0.conv1:2\\nmid_block.resnets.0.conv2:2\\nmid_block.resnets.1.conv1:2\\nmid_block.resnets.1.conv2:2\\n", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T20:31:08.348075Z", "created_at": "2023-10-18T20:30:03.908827Z", "data_removed": false, "error": null, "id": "eigpjbtbiz7ebcpkqigm2bmj4u", "input": { "width": 2048, "height": 1024, "prompt": "A Cute Puppy with wings, Cartoon Drawings, high details", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2\n", "num_inference_steps": 50 }, "logs": "Using seed: 6314\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:15, 3.08it/s]\n 4%|▍ | 2/50 [00:00<00:14, 3.32it/s]\n 6%|▌ | 3/50 [00:00<00:13, 3.39it/s]\n 8%|▊ | 4/50 [00:01<00:13, 3.43it/s]\n 10%|█ | 5/50 [00:01<00:13, 3.46it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.47it/s]\n 14%|█▍ | 7/50 [00:02<00:12, 3.48it/s]\n 16%|█▌ | 8/50 [00:02<00:12, 3.48it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.48it/s]\n 20%|██ | 10/50 [00:02<00:11, 3.48it/s]\n 22%|██▏ | 11/50 [00:03<00:11, 3.48it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.49it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.49it/s]\n 28%|██▊ | 14/50 [00:04<00:10, 3.48it/s]\n 30%|███ | 15/50 [00:04<00:10, 3.48it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.49it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.49it/s]\n 36%|███▌ | 18/50 [00:05<00:09, 3.49it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.49it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.47it/s]\n 42%|████▏ | 21/50 [00:06<00:08, 3.47it/s]\n 44%|████▍ | 22/50 [00:06<00:08, 3.47it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.47it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.47it/s]\n 50%|█████ | 25/50 [00:07<00:07, 3.47it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.47it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.47it/s]\n 56%|█████▌ | 28/50 [00:08<00:06, 3.47it/s]\n 58%|█████▊ | 29/50 [00:08<00:06, 3.47it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.48it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.47it/s]\n 64%|██████▍ | 32/50 [00:09<00:05, 3.47it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.48it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.48it/s]\n 70%|███████ | 35/50 [00:10<00:04, 3.48it/s]\n 72%|███████▏ | 36/50 [00:10<00:04, 3.48it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.48it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.48it/s]\n 78%|███████▊ | 39/50 [00:11<00:03, 3.49it/s]\n 80%|████████ | 40/50 [00:11<00:02, 3.49it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.49it/s]\n 84%|████████▍ | 42/50 [00:12<00:02, 3.48it/s]\n 86%|████████▌ | 43/50 [00:12<00:02, 3.48it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.48it/s]\n 90%|█████████ | 45/50 [00:12<00:01, 3.49it/s]\n 92%|█████████▏| 46/50 [00:13<00:01, 3.49it/s]\n 94%|█████████▍| 47/50 [00:13<00:00, 3.49it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.48it/s]\n 98%|█████████▊| 49/50 [00:14<00:00, 3.48it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.48it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.47it/s]", "metrics": { "predict_time": 17.024003, "total_time": 64.439248 }, "output": "https://replicate.delivery/pbxt/3PvZeydlNqRoGS45u0ah06E2evRqGtXCKEYUvpctzepXUe9GB/out.png", "started_at": "2023-10-18T20:30:51.324072Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/eigpjbtbiz7ebcpkqigm2bmj4u", "cancel": "https://api.replicate.com/v1/predictions/eigpjbtbiz7ebcpkqigm2bmj4u/cancel" }, "version": "3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59" }Generated inUsing seed: 6314 down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:15, 3.08it/s] 4%|▍ | 2/50 [00:00<00:14, 3.32it/s] 6%|▌ | 3/50 [00:00<00:13, 3.39it/s] 8%|▊ | 4/50 [00:01<00:13, 3.43it/s] 10%|█ | 5/50 [00:01<00:13, 3.46it/s] 12%|█▏ | 6/50 [00:01<00:12, 3.47it/s] 14%|█▍ | 7/50 [00:02<00:12, 3.48it/s] 16%|█▌ | 8/50 [00:02<00:12, 3.48it/s] 18%|█▊ | 9/50 [00:02<00:11, 3.48it/s] 20%|██ | 10/50 [00:02<00:11, 3.48it/s] 22%|██▏ | 11/50 [00:03<00:11, 3.48it/s] 24%|██▍ | 12/50 [00:03<00:10, 3.49it/s] 26%|██▌ | 13/50 [00:03<00:10, 3.49it/s] 28%|██▊ | 14/50 [00:04<00:10, 3.48it/s] 30%|███ | 15/50 [00:04<00:10, 3.48it/s] 32%|███▏ | 16/50 [00:04<00:09, 3.49it/s] 34%|███▍ | 17/50 [00:04<00:09, 3.49it/s] 36%|███▌ | 18/50 [00:05<00:09, 3.49it/s] 38%|███▊ | 19/50 [00:05<00:08, 3.49it/s] 40%|████ | 20/50 [00:05<00:08, 3.47it/s] 42%|████▏ | 21/50 [00:06<00:08, 3.47it/s] 44%|████▍ | 22/50 [00:06<00:08, 3.47it/s] 46%|████▌ | 23/50 [00:06<00:07, 3.47it/s] 48%|████▊ | 24/50 [00:06<00:07, 3.47it/s] 50%|█████ | 25/50 [00:07<00:07, 3.47it/s] 52%|█████▏ | 26/50 [00:07<00:06, 3.47it/s] 54%|█████▍ | 27/50 [00:07<00:06, 3.47it/s] 56%|█████▌ | 28/50 [00:08<00:06, 3.47it/s] 58%|█████▊ | 29/50 [00:08<00:06, 3.47it/s] 60%|██████ | 30/50 [00:08<00:05, 3.48it/s] 62%|██████▏ | 31/50 [00:08<00:05, 3.47it/s] 64%|██████▍ | 32/50 [00:09<00:05, 3.47it/s] 66%|██████▌ | 33/50 [00:09<00:04, 3.48it/s] 68%|██████▊ | 34/50 [00:09<00:04, 3.48it/s] 70%|███████ | 35/50 [00:10<00:04, 3.48it/s] 72%|███████▏ | 36/50 [00:10<00:04, 3.48it/s] 74%|███████▍ | 37/50 [00:10<00:03, 3.48it/s] 76%|███████▌ | 38/50 [00:10<00:03, 3.48it/s] 78%|███████▊ | 39/50 [00:11<00:03, 3.49it/s] 80%|████████ | 40/50 [00:11<00:02, 3.49it/s] 82%|████████▏ | 41/50 [00:11<00:02, 3.49it/s] 84%|████████▍ | 42/50 [00:12<00:02, 3.48it/s] 86%|████████▌ | 43/50 [00:12<00:02, 3.48it/s] 88%|████████▊ | 44/50 [00:12<00:01, 3.48it/s] 90%|█████████ | 45/50 [00:12<00:01, 3.49it/s] 92%|█████████▏| 46/50 [00:13<00:01, 3.49it/s] 94%|█████████▍| 47/50 [00:13<00:00, 3.49it/s] 96%|█████████▌| 48/50 [00:13<00:00, 3.48it/s] 98%|█████████▊| 49/50 [00:14<00:00, 3.48it/s] 100%|██████████| 50/50 [00:14<00:00, 3.48it/s] 100%|██████████| 50/50 [00:14<00:00, 3.47it/s]Prediction
cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59ID4hllaalbfkhnlzkzwbqfpvznnuStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 2048
- height
- 2048
- prompt
- a professional photograph of an astronaut riding a horse
- num_inference_steps
- 50
{ "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", { input: { width: 2048, height: 2048, prompt: "a professional photograph of an astronaut riding a horse", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", input={ "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", "input": { "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T21:41:50.808384Z", "created_at": "2023-10-18T21:41:09.383528Z", "data_removed": false, "error": null, "id": "4hllaalbfkhnlzkzwbqfpvznnu", "input": { "width": 2048, "height": 2048, "prompt": "a professional photograph of an astronaut riding a horse", "num_inference_steps": 50 }, "logs": "Using seed: 43181\nReading dilation settings\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:36, 1.35it/s]\n 4%|▍ | 2/50 [00:01<00:35, 1.35it/s]\n 6%|▌ | 3/50 [00:02<00:34, 1.35it/s]\n 8%|▊ | 4/50 [00:02<00:34, 1.35it/s]\n 10%|█ | 5/50 [00:03<00:33, 1.35it/s]\n 12%|█▏ | 6/50 [00:04<00:32, 1.34it/s]\n 14%|█▍ | 7/50 [00:05<00:32, 1.34it/s]\n 16%|█▌ | 8/50 [00:05<00:31, 1.34it/s]\n 18%|█▊ | 9/50 [00:06<00:30, 1.34it/s]\n 20%|██ | 10/50 [00:07<00:29, 1.34it/s]\n 22%|██▏ | 11/50 [00:08<00:29, 1.34it/s]\n 24%|██▍ | 12/50 [00:08<00:28, 1.34it/s]\n 26%|██▌ | 13/50 [00:09<00:27, 1.34it/s]\n 28%|██▊ | 14/50 [00:10<00:26, 1.34it/s]\n 30%|███ | 15/50 [00:11<00:26, 1.34it/s]\n 32%|███▏ | 16/50 [00:11<00:25, 1.34it/s]\n 34%|███▍ | 17/50 [00:12<00:24, 1.34it/s]\n 36%|███▌ | 18/50 [00:13<00:23, 1.34it/s]\n 38%|███▊ | 19/50 [00:14<00:23, 1.34it/s]\n 40%|████ | 20/50 [00:14<00:22, 1.34it/s]\n 42%|████▏ | 21/50 [00:15<00:21, 1.34it/s]\n 44%|████▍ | 22/50 [00:16<00:20, 1.34it/s]\n 46%|████▌ | 23/50 [00:17<00:20, 1.34it/s]\n 48%|████▊ | 24/50 [00:17<00:19, 1.34it/s]\n 50%|█████ | 25/50 [00:18<00:18, 1.34it/s]\n 52%|█████▏ | 26/50 [00:19<00:17, 1.34it/s]\n 54%|█████▍ | 27/50 [00:20<00:17, 1.34it/s]\n 56%|█████▌ | 28/50 [00:20<00:16, 1.34it/s]\n 58%|█████▊ | 29/50 [00:21<00:15, 1.34it/s]\n 60%|██████ | 30/50 [00:22<00:14, 1.34it/s]\n 62%|██████▏ | 31/50 [00:23<00:14, 1.34it/s]\n 64%|██████▍ | 32/50 [00:23<00:13, 1.34it/s]\n 66%|██████▌ | 33/50 [00:24<00:12, 1.34it/s]\n 68%|██████▊ | 34/50 [00:25<00:11, 1.34it/s]\n 70%|███████ | 35/50 [00:26<00:11, 1.34it/s]\n 72%|███████▏ | 36/50 [00:26<00:10, 1.34it/s]\n 74%|███████▍ | 37/50 [00:27<00:09, 1.34it/s]\n 76%|███████▌ | 38/50 [00:28<00:08, 1.34it/s]\n 78%|███████▊ | 39/50 [00:29<00:08, 1.34it/s]\n 80%|████████ | 40/50 [00:29<00:07, 1.34it/s]\n 82%|████████▏ | 41/50 [00:30<00:06, 1.34it/s]\n 84%|████████▍ | 42/50 [00:31<00:05, 1.34it/s]\n 86%|████████▌ | 43/50 [00:32<00:05, 1.34it/s]\n 88%|████████▊ | 44/50 [00:32<00:04, 1.34it/s]\n 90%|█████████ | 45/50 [00:33<00:03, 1.34it/s]\n 92%|█████████▏| 46/50 [00:34<00:02, 1.34it/s]\n 94%|█████████▍| 47/50 [00:35<00:02, 1.34it/s]\n 96%|█████████▌| 48/50 [00:35<00:01, 1.34it/s]\n 98%|█████████▊| 49/50 [00:36<00:00, 1.34it/s]\n100%|██████████| 50/50 [00:37<00:00, 1.34it/s]\n100%|██████████| 50/50 [00:37<00:00, 1.34it/s]", "metrics": { "predict_time": 41.445016, "total_time": 41.424856 }, "output": "https://replicate.delivery/pbxt/46puDNY7c9oKKVHo5haYa5zcNK31fOgmycBSGVCBnXxOGw3IA/out.png", "started_at": "2023-10-18T21:41:09.363368Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4hllaalbfkhnlzkzwbqfpvznnu", "cancel": "https://api.replicate.com/v1/predictions/4hllaalbfkhnlzkzwbqfpvznnu/cancel" }, "version": "3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59" }Generated inUsing seed: 43181 Reading dilation settings down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:36, 1.35it/s] 4%|▍ | 2/50 [00:01<00:35, 1.35it/s] 6%|▌ | 3/50 [00:02<00:34, 1.35it/s] 8%|▊ | 4/50 [00:02<00:34, 1.35it/s] 10%|█ | 5/50 [00:03<00:33, 1.35it/s] 12%|█▏ | 6/50 [00:04<00:32, 1.34it/s] 14%|█▍ | 7/50 [00:05<00:32, 1.34it/s] 16%|█▌ | 8/50 [00:05<00:31, 1.34it/s] 18%|█▊ | 9/50 [00:06<00:30, 1.34it/s] 20%|██ | 10/50 [00:07<00:29, 1.34it/s] 22%|██▏ | 11/50 [00:08<00:29, 1.34it/s] 24%|██▍ | 12/50 [00:08<00:28, 1.34it/s] 26%|██▌ | 13/50 [00:09<00:27, 1.34it/s] 28%|██▊ | 14/50 [00:10<00:26, 1.34it/s] 30%|███ | 15/50 [00:11<00:26, 1.34it/s] 32%|███▏ | 16/50 [00:11<00:25, 1.34it/s] 34%|███▍ | 17/50 [00:12<00:24, 1.34it/s] 36%|███▌ | 18/50 [00:13<00:23, 1.34it/s] 38%|███▊ | 19/50 [00:14<00:23, 1.34it/s] 40%|████ | 20/50 [00:14<00:22, 1.34it/s] 42%|████▏ | 21/50 [00:15<00:21, 1.34it/s] 44%|████▍ | 22/50 [00:16<00:20, 1.34it/s] 46%|████▌ | 23/50 [00:17<00:20, 1.34it/s] 48%|████▊ | 24/50 [00:17<00:19, 1.34it/s] 50%|█████ | 25/50 [00:18<00:18, 1.34it/s] 52%|█████▏ | 26/50 [00:19<00:17, 1.34it/s] 54%|█████▍ | 27/50 [00:20<00:17, 1.34it/s] 56%|█████▌ | 28/50 [00:20<00:16, 1.34it/s] 58%|█████▊ | 29/50 [00:21<00:15, 1.34it/s] 60%|██████ | 30/50 [00:22<00:14, 1.34it/s] 62%|██████▏ | 31/50 [00:23<00:14, 1.34it/s] 64%|██████▍ | 32/50 [00:23<00:13, 1.34it/s] 66%|██████▌ | 33/50 [00:24<00:12, 1.34it/s] 68%|██████▊ | 34/50 [00:25<00:11, 1.34it/s] 70%|███████ | 35/50 [00:26<00:11, 1.34it/s] 72%|███████▏ | 36/50 [00:26<00:10, 1.34it/s] 74%|███████▍ | 37/50 [00:27<00:09, 1.34it/s] 76%|███████▌ | 38/50 [00:28<00:08, 1.34it/s] 78%|███████▊ | 39/50 [00:29<00:08, 1.34it/s] 80%|████████ | 40/50 [00:29<00:07, 1.34it/s] 82%|████████▏ | 41/50 [00:30<00:06, 1.34it/s] 84%|████████▍ | 42/50 [00:31<00:05, 1.34it/s] 86%|████████▌ | 43/50 [00:32<00:05, 1.34it/s] 88%|████████▊ | 44/50 [00:32<00:04, 1.34it/s] 90%|█████████ | 45/50 [00:33<00:03, 1.34it/s] 92%|█████████▏| 46/50 [00:34<00:02, 1.34it/s] 94%|█████████▍| 47/50 [00:35<00:02, 1.34it/s] 96%|█████████▌| 48/50 [00:35<00:01, 1.34it/s] 98%|█████████▊| 49/50 [00:36<00:00, 1.34it/s] 100%|██████████| 50/50 [00:37<00:00, 1.34it/s] 100%|██████████| 50/50 [00:37<00:00, 1.34it/s]Prediction
cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59IDgooz3wtbiwane442po66rosp4uStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a rabbit riding a bike on a street in New York
- dilate_scale
- down_blocks.3.resnets.0.conv1:2 down_blocks.3.resnets.0.conv2:2 down_blocks.3.resnets.1.conv1:2 down_blocks.3.resnets.1.conv2:2 up_blocks.0.resnets.0.conv1:2 up_blocks.0.resnets.0.conv2:2 up_blocks.0.resnets.1.conv1:2 up_blocks.0.resnets.1.conv2:2 up_blocks.0.resnets.2.conv1:2 up_blocks.0.resnets.2.conv2:2 up_blocks.0.upsamplers.0.conv:2 mid_block.resnets.0.conv1:2 mid_block.resnets.0.conv2:2 mid_block.resnets.1.conv1:2 mid_block.resnets.1.conv2:2
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a rabbit riding a bike on a street in New York", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2", "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", { input: { width: 1024, height: 1024, prompt: "a rabbit riding a bike on a street in New York", dilate_scale: "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2", num_inference_steps: 50 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", 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 cjwbw/scalecrafter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", input={ "width": 1024, "height": 1024, "prompt": "a rabbit riding a bike on a street in New York", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2", "num_inference_steps": 50 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run cjwbw/scalecrafter 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": "cjwbw/scalecrafter:3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59", "input": { "width": 1024, "height": 1024, "prompt": "a rabbit riding a bike on a street in New York", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\\ndown_blocks.3.resnets.0.conv2:2\\ndown_blocks.3.resnets.1.conv1:2\\ndown_blocks.3.resnets.1.conv2:2\\nup_blocks.0.resnets.0.conv1:2\\nup_blocks.0.resnets.0.conv2:2\\nup_blocks.0.resnets.1.conv1:2\\nup_blocks.0.resnets.1.conv2:2\\nup_blocks.0.resnets.2.conv1:2\\nup_blocks.0.resnets.2.conv2:2\\nup_blocks.0.upsamplers.0.conv:2\\nmid_block.resnets.0.conv1:2\\nmid_block.resnets.0.conv2:2\\nmid_block.resnets.1.conv1:2\\nmid_block.resnets.1.conv2:2", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-18T21:47:09.510214Z", "created_at": "2023-10-18T21:47:01.022209Z", "data_removed": false, "error": null, "id": "gooz3wtbiwane442po66rosp4u", "input": { "width": 1024, "height": 1024, "prompt": "a rabbit riding a bike on a street in New York", "dilate_scale": "down_blocks.3.resnets.0.conv1:2\ndown_blocks.3.resnets.0.conv2:2\ndown_blocks.3.resnets.1.conv1:2\ndown_blocks.3.resnets.1.conv2:2\nup_blocks.0.resnets.0.conv1:2\nup_blocks.0.resnets.0.conv2:2\nup_blocks.0.resnets.1.conv1:2\nup_blocks.0.resnets.1.conv2:2\nup_blocks.0.resnets.2.conv1:2\nup_blocks.0.resnets.2.conv2:2\nup_blocks.0.upsamplers.0.conv:2\nmid_block.resnets.0.conv1:2\nmid_block.resnets.0.conv2:2\nmid_block.resnets.1.conv1:2\nmid_block.resnets.1.conv2:2", "num_inference_steps": 50 }, "logs": "Using seed: 2223\ndown_blocks.3.resnets.0.conv1 : 2.0\ndown_blocks.3.resnets.0.conv2 : 2.0\ndown_blocks.3.resnets.1.conv1 : 2.0\ndown_blocks.3.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.0.conv1 : 2.0\nup_blocks.0.resnets.0.conv2 : 2.0\nup_blocks.0.resnets.1.conv1 : 2.0\nup_blocks.0.resnets.1.conv2 : 2.0\nup_blocks.0.resnets.2.conv1 : 2.0\nup_blocks.0.resnets.2.conv2 : 2.0\nup_blocks.0.upsamplers.0.conv : 2.0\nmid_block.resnets.0.conv1 : 2.0\nmid_block.resnets.0.conv2 : 2.0\nmid_block.resnets.1.conv1 : 2.0\nmid_block.resnets.1.conv2 : 2.0\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:06, 7.39it/s]\n 4%|▍ | 2/50 [00:00<00:06, 7.39it/s]\n 6%|▌ | 3/50 [00:00<00:06, 7.38it/s]\n 8%|▊ | 4/50 [00:00<00:06, 7.34it/s]\n 10%|█ | 5/50 [00:00<00:06, 7.36it/s]\n 12%|█▏ | 6/50 [00:00<00:06, 7.33it/s]\n 14%|█▍ | 7/50 [00:00<00:05, 7.35it/s]\n 16%|█▌ | 8/50 [00:01<00:05, 7.37it/s]\n 18%|█▊ | 9/50 [00:01<00:05, 7.38it/s]\n 20%|██ | 10/50 [00:01<00:05, 7.39it/s]\n 22%|██▏ | 11/50 [00:01<00:05, 7.39it/s]\n 24%|██▍ | 12/50 [00:01<00:05, 7.38it/s]\n 26%|██▌ | 13/50 [00:01<00:05, 7.39it/s]\n 28%|██▊ | 14/50 [00:01<00:04, 7.39it/s]\n 30%|███ | 15/50 [00:02<00:04, 7.38it/s]\n 32%|███▏ | 16/50 [00:02<00:04, 7.37it/s]\n 34%|███▍ | 17/50 [00:02<00:04, 7.38it/s]\n 36%|███▌ | 18/50 [00:02<00:04, 7.37it/s]\n 38%|███▊ | 19/50 [00:02<00:04, 7.36it/s]\n 40%|████ | 20/50 [00:02<00:04, 7.37it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 7.38it/s]\n 44%|████▍ | 22/50 [00:02<00:03, 7.37it/s]\n 46%|████▌ | 23/50 [00:03<00:03, 7.38it/s]\n 48%|████▊ | 24/50 [00:03<00:03, 7.38it/s]\n 50%|█████ | 25/50 [00:03<00:03, 7.38it/s]\n 52%|█████▏ | 26/50 [00:03<00:03, 7.37it/s]\n 54%|█████▍ | 27/50 [00:03<00:03, 7.37it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 7.37it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 7.37it/s]\n 60%|██████ | 30/50 [00:04<00:02, 7.37it/s]\n 62%|██████▏ | 31/50 [00:04<00:02, 7.38it/s]\n 64%|██████▍ | 32/50 [00:04<00:02, 7.39it/s]\n 66%|██████▌ | 33/50 [00:04<00:02, 7.38it/s]\n 68%|██████▊ | 34/50 [00:04<00:02, 7.36it/s]\n 70%|███████ | 35/50 [00:04<00:02, 7.35it/s]\n 72%|███████▏ | 36/50 [00:04<00:01, 7.35it/s]\n 74%|███████▍ | 37/50 [00:05<00:01, 7.36it/s]\n 76%|███████▌ | 38/50 [00:05<00:01, 7.36it/s]\n 78%|███████▊ | 39/50 [00:05<00:01, 7.38it/s]\n 80%|████████ | 40/50 [00:05<00:01, 7.37it/s]\n 82%|████████▏ | 41/50 [00:05<00:01, 7.31it/s]\n 84%|████████▍ | 42/50 [00:05<00:01, 7.32it/s]\n 86%|████████▌ | 43/50 [00:05<00:00, 7.34it/s]\n 88%|████████▊ | 44/50 [00:05<00:00, 7.35it/s]\n 90%|█████████ | 45/50 [00:06<00:00, 7.36it/s]\n 92%|█████████▏| 46/50 [00:06<00:00, 7.36it/s]\n 94%|█████████▍| 47/50 [00:06<00:00, 7.36it/s]\n 96%|█████████▌| 48/50 [00:06<00:00, 7.35it/s]\n 98%|█████████▊| 49/50 [00:06<00:00, 7.36it/s]\n100%|██████████| 50/50 [00:06<00:00, 7.37it/s]\n100%|██████████| 50/50 [00:06<00:00, 7.37it/s]", "metrics": { "predict_time": 8.535166, "total_time": 8.488005 }, "output": "https://replicate.delivery/pbxt/Ce2gRmarULT9Hi2XVrTIScAX1zb3Pr2Y5VxWSHKxfaXcRgvRA/out.png", "started_at": "2023-10-18T21:47:00.975048Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/gooz3wtbiwane442po66rosp4u", "cancel": "https://api.replicate.com/v1/predictions/gooz3wtbiwane442po66rosp4u/cancel" }, "version": "3b367f9321bd18ca8b29ef9bf9507348d822c2cfcd5764b9414eff879f086b59" }Generated inUsing seed: 2223 down_blocks.3.resnets.0.conv1 : 2.0 down_blocks.3.resnets.0.conv2 : 2.0 down_blocks.3.resnets.1.conv1 : 2.0 down_blocks.3.resnets.1.conv2 : 2.0 up_blocks.0.resnets.0.conv1 : 2.0 up_blocks.0.resnets.0.conv2 : 2.0 up_blocks.0.resnets.1.conv1 : 2.0 up_blocks.0.resnets.1.conv2 : 2.0 up_blocks.0.resnets.2.conv1 : 2.0 up_blocks.0.resnets.2.conv2 : 2.0 up_blocks.0.upsamplers.0.conv : 2.0 mid_block.resnets.0.conv1 : 2.0 mid_block.resnets.0.conv2 : 2.0 mid_block.resnets.1.conv1 : 2.0 mid_block.resnets.1.conv2 : 2.0 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:06, 7.39it/s] 4%|▍ | 2/50 [00:00<00:06, 7.39it/s] 6%|▌ | 3/50 [00:00<00:06, 7.38it/s] 8%|▊ | 4/50 [00:00<00:06, 7.34it/s] 10%|█ | 5/50 [00:00<00:06, 7.36it/s] 12%|█▏ | 6/50 [00:00<00:06, 7.33it/s] 14%|█▍ | 7/50 [00:00<00:05, 7.35it/s] 16%|█▌ | 8/50 [00:01<00:05, 7.37it/s] 18%|█▊ | 9/50 [00:01<00:05, 7.38it/s] 20%|██ | 10/50 [00:01<00:05, 7.39it/s] 22%|██▏ | 11/50 [00:01<00:05, 7.39it/s] 24%|██▍ | 12/50 [00:01<00:05, 7.38it/s] 26%|██▌ | 13/50 [00:01<00:05, 7.39it/s] 28%|██▊ | 14/50 [00:01<00:04, 7.39it/s] 30%|███ | 15/50 [00:02<00:04, 7.38it/s] 32%|███▏ | 16/50 [00:02<00:04, 7.37it/s] 34%|███▍ | 17/50 [00:02<00:04, 7.38it/s] 36%|███▌ | 18/50 [00:02<00:04, 7.37it/s] 38%|███▊ | 19/50 [00:02<00:04, 7.36it/s] 40%|████ | 20/50 [00:02<00:04, 7.37it/s] 42%|████▏ | 21/50 [00:02<00:03, 7.38it/s] 44%|████▍ | 22/50 [00:02<00:03, 7.37it/s] 46%|████▌ | 23/50 [00:03<00:03, 7.38it/s] 48%|████▊ | 24/50 [00:03<00:03, 7.38it/s] 50%|█████ | 25/50 [00:03<00:03, 7.38it/s] 52%|█████▏ | 26/50 [00:03<00:03, 7.37it/s] 54%|█████▍ | 27/50 [00:03<00:03, 7.37it/s] 56%|█████▌ | 28/50 [00:03<00:02, 7.37it/s] 58%|█████▊ | 29/50 [00:03<00:02, 7.37it/s] 60%|██████ | 30/50 [00:04<00:02, 7.37it/s] 62%|██████▏ | 31/50 [00:04<00:02, 7.38it/s] 64%|██████▍ | 32/50 [00:04<00:02, 7.39it/s] 66%|██████▌ | 33/50 [00:04<00:02, 7.38it/s] 68%|██████▊ | 34/50 [00:04<00:02, 7.36it/s] 70%|███████ | 35/50 [00:04<00:02, 7.35it/s] 72%|███████▏ | 36/50 [00:04<00:01, 7.35it/s] 74%|███████▍ | 37/50 [00:05<00:01, 7.36it/s] 76%|███████▌ | 38/50 [00:05<00:01, 7.36it/s] 78%|███████▊ | 39/50 [00:05<00:01, 7.38it/s] 80%|████████ | 40/50 [00:05<00:01, 7.37it/s] 82%|████████▏ | 41/50 [00:05<00:01, 7.31it/s] 84%|████████▍ | 42/50 [00:05<00:01, 7.32it/s] 86%|████████▌ | 43/50 [00:05<00:00, 7.34it/s] 88%|████████▊ | 44/50 [00:05<00:00, 7.35it/s] 90%|█████████ | 45/50 [00:06<00:00, 7.36it/s] 92%|█████████▏| 46/50 [00:06<00:00, 7.36it/s] 94%|█████████▍| 47/50 [00:06<00:00, 7.36it/s] 96%|█████████▌| 48/50 [00:06<00:00, 7.35it/s] 98%|█████████▊| 49/50 [00:06<00:00, 7.36it/s] 100%|██████████| 50/50 [00:06<00:00, 7.37it/s] 100%|██████████| 50/50 [00:06<00:00, 7.37it/s]
Want to make some of these yourself?
Run this model
