prompthero
/
lookbook
Fashion Diffusion by Dreamshot
- Public
- 207.4K runs
-
A100 (80GB)
Prediction
prompthero/lookbook:afd0956cIDaoejgdjelvfb3lzotxr6oslqzqStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a close up of a person wearing a brown shirt
- scheduler
- EULERa
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "100"
{ "width": 512, "height": 512, "prompt": "a close up of a person wearing a brown shirt", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "100" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", { input: { width: 512, height: 512, prompt: "a close up of a person wearing a brown shirt", scheduler: "EULERa", num_outputs: 1, guidance_scale: "7", num_inference_steps: "100" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", input={ "width": 512, "height": 512, "prompt": "a close up of a person wearing a brown shirt", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "100" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run prompthero/lookbook 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": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", "input": { "width": 512, "height": 512, "prompt": "a close up of a person wearing a brown shirt", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "100" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run prompthero/lookbook using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a close up of a person wearing a brown shirt"' \ -i 'scheduler="EULERa"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="100"'
To learn more, take a look at the Cog documentation.
Pull and run prompthero/lookbook using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a close up of a person wearing a brown shirt", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "100" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-12-08T11:47:47.758268Z", "created_at": "2022-12-08T11:46:46.526357Z", "data_removed": false, "error": null, "id": "aoejgdjelvfb3lzotxr6oslqzq", "input": { "width": 512, "height": 512, "prompt": "a close up of a person wearing a brown shirt", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "100" }, "logs": "Using seed: 34339\nGlobal seed set to 34339\n 0%| | 0/100 [00:00<?, ?it/s]\n 2%|▏ | 2/100 [00:00<00:06, 14.48it/s]\n 4%|▍ | 4/100 [00:00<00:06, 14.65it/s]\n 6%|▌ | 6/100 [00:00<00:06, 14.66it/s]\n 8%|▊ | 8/100 [00:00<00:06, 13.97it/s]\n 10%|█ | 10/100 [00:00<00:06, 14.27it/s]\n 12%|█▏ | 12/100 [00:00<00:06, 14.47it/s]\n 14%|█▍ | 14/100 [00:00<00:05, 14.60it/s]\n 16%|█▌ | 16/100 [00:01<00:05, 14.58it/s]\n 18%|█▊ | 18/100 [00:01<00:05, 14.68it/s]\n 20%|██ | 20/100 [00:01<00:05, 14.70it/s]\n 22%|██▏ | 22/100 [00:01<00:05, 14.68it/s]\n 24%|██▍ | 24/100 [00:01<00:05, 14.23it/s]\n 26%|██▌ | 26/100 [00:01<00:05, 14.43it/s]\n 28%|██▊ | 28/100 [00:01<00:04, 14.44it/s]\n 30%|███ | 30/100 [00:02<00:04, 14.49it/s]\n 32%|███▏ | 32/100 [00:02<00:04, 14.59it/s]\n 34%|███▍ | 34/100 [00:02<00:04, 14.64it/s]\n 36%|███▌ | 36/100 [00:02<00:04, 14.62it/s]\n 38%|███▊ | 38/100 [00:02<00:04, 13.84it/s]\n 40%|████ | 40/100 [00:02<00:04, 13.95it/s]\n 42%|████▏ | 42/100 [00:02<00:04, 14.05it/s]\n 44%|████▍ | 44/100 [00:03<00:03, 14.11it/s]\n 46%|████▌ | 46/100 [00:03<00:03, 14.33it/s]\n 48%|████▊ | 48/100 [00:03<00:03, 14.46it/s]\n 50%|█████ | 50/100 [00:03<00:03, 14.48it/s]\n 52%|█████▏ | 52/100 [00:03<00:03, 14.45it/s]\n 54%|█████▍ | 54/100 [00:03<00:03, 14.49it/s]\n 56%|█████▌ | 56/100 [00:03<00:03, 14.35it/s]\n 58%|█████▊ | 58/100 [00:04<00:02, 14.31it/s]\n 60%|██████ | 60/100 [00:04<00:02, 14.45it/s]\n 62%|██████▏ | 62/100 [00:04<00:02, 14.54it/s]\n 64%|██████▍ | 64/100 [00:04<00:02, 14.56it/s]\n 66%|██████▌ | 66/100 [00:04<00:02, 14.59it/s]\n 68%|██████▊ | 68/100 [00:04<00:02, 14.22it/s]\n 70%|███████ | 70/100 [00:04<00:02, 14.10it/s]\n 72%|███████▏ | 72/100 [00:05<00:01, 14.32it/s]\n 74%|███████▍ | 74/100 [00:05<00:01, 14.43it/s]\n 76%|███████▌ | 76/100 [00:05<00:01, 14.59it/s]\n 78%|███████▊ | 78/100 [00:05<00:01, 14.66it/s]\n 80%|████████ | 80/100 [00:05<00:01, 14.71it/s]\n 82%|████████▏ | 82/100 [00:05<00:01, 14.28it/s]\n 84%|████████▍ | 84/100 [00:05<00:01, 14.41it/s]\n 86%|████████▌ | 86/100 [00:05<00:00, 14.48it/s]\n 88%|████████▊ | 88/100 [00:06<00:00, 14.41it/s]\n 90%|█████████ | 90/100 [00:06<00:00, 14.02it/s]\n 92%|█████████▏| 92/100 [00:06<00:00, 14.20it/s]\n 94%|█████████▍| 94/100 [00:06<00:00, 14.37it/s]\n 96%|█████████▌| 96/100 [00:06<00:00, 14.51it/s]\n 98%|█████████▊| 98/100 [00:06<00:00, 13.76it/s]\n100%|██████████| 100/100 [00:06<00:00, 13.97it/s]\n100%|██████████| 100/100 [00:06<00:00, 14.36it/s]", "metrics": { "predict_time": 7.589341, "total_time": 61.231911 }, "output": [ "https://replicate.delivery/pbxt/pemLRGGnxq1dIKFZ8SG0SczfeEEbEuU2frVb5fw7Hq1e4AeDIA/out-0.png" ], "started_at": "2022-12-08T11:47:40.168927Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/aoejgdjelvfb3lzotxr6oslqzq", "cancel": "https://api.replicate.com/v1/predictions/aoejgdjelvfb3lzotxr6oslqzq/cancel" }, "version": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522" }
Generated inUsing seed: 34339 Global seed set to 34339 0%| | 0/100 [00:00<?, ?it/s] 2%|▏ | 2/100 [00:00<00:06, 14.48it/s] 4%|▍ | 4/100 [00:00<00:06, 14.65it/s] 6%|▌ | 6/100 [00:00<00:06, 14.66it/s] 8%|▊ | 8/100 [00:00<00:06, 13.97it/s] 10%|█ | 10/100 [00:00<00:06, 14.27it/s] 12%|█▏ | 12/100 [00:00<00:06, 14.47it/s] 14%|█▍ | 14/100 [00:00<00:05, 14.60it/s] 16%|█▌ | 16/100 [00:01<00:05, 14.58it/s] 18%|█▊ | 18/100 [00:01<00:05, 14.68it/s] 20%|██ | 20/100 [00:01<00:05, 14.70it/s] 22%|██▏ | 22/100 [00:01<00:05, 14.68it/s] 24%|██▍ | 24/100 [00:01<00:05, 14.23it/s] 26%|██▌ | 26/100 [00:01<00:05, 14.43it/s] 28%|██▊ | 28/100 [00:01<00:04, 14.44it/s] 30%|███ | 30/100 [00:02<00:04, 14.49it/s] 32%|███▏ | 32/100 [00:02<00:04, 14.59it/s] 34%|███▍ | 34/100 [00:02<00:04, 14.64it/s] 36%|███▌ | 36/100 [00:02<00:04, 14.62it/s] 38%|███▊ | 38/100 [00:02<00:04, 13.84it/s] 40%|████ | 40/100 [00:02<00:04, 13.95it/s] 42%|████▏ | 42/100 [00:02<00:04, 14.05it/s] 44%|████▍ | 44/100 [00:03<00:03, 14.11it/s] 46%|████▌ | 46/100 [00:03<00:03, 14.33it/s] 48%|████▊ | 48/100 [00:03<00:03, 14.46it/s] 50%|█████ | 50/100 [00:03<00:03, 14.48it/s] 52%|█████▏ | 52/100 [00:03<00:03, 14.45it/s] 54%|█████▍ | 54/100 [00:03<00:03, 14.49it/s] 56%|█████▌ | 56/100 [00:03<00:03, 14.35it/s] 58%|█████▊ | 58/100 [00:04<00:02, 14.31it/s] 60%|██████ | 60/100 [00:04<00:02, 14.45it/s] 62%|██████▏ | 62/100 [00:04<00:02, 14.54it/s] 64%|██████▍ | 64/100 [00:04<00:02, 14.56it/s] 66%|██████▌ | 66/100 [00:04<00:02, 14.59it/s] 68%|██████▊ | 68/100 [00:04<00:02, 14.22it/s] 70%|███████ | 70/100 [00:04<00:02, 14.10it/s] 72%|███████▏ | 72/100 [00:05<00:01, 14.32it/s] 74%|███████▍ | 74/100 [00:05<00:01, 14.43it/s] 76%|███████▌ | 76/100 [00:05<00:01, 14.59it/s] 78%|███████▊ | 78/100 [00:05<00:01, 14.66it/s] 80%|████████ | 80/100 [00:05<00:01, 14.71it/s] 82%|████████▏ | 82/100 [00:05<00:01, 14.28it/s] 84%|████████▍ | 84/100 [00:05<00:01, 14.41it/s] 86%|████████▌ | 86/100 [00:05<00:00, 14.48it/s] 88%|████████▊ | 88/100 [00:06<00:00, 14.41it/s] 90%|█████████ | 90/100 [00:06<00:00, 14.02it/s] 92%|█████████▏| 92/100 [00:06<00:00, 14.20it/s] 94%|█████████▍| 94/100 [00:06<00:00, 14.37it/s] 96%|█████████▌| 96/100 [00:06<00:00, 14.51it/s] 98%|█████████▊| 98/100 [00:06<00:00, 13.76it/s] 100%|██████████| 100/100 [00:06<00:00, 13.97it/s] 100%|██████████| 100/100 [00:06<00:00, 14.36it/s]
Prediction
prompthero/lookbook:afd0956cIDihdbsokt7ncelcn2fcanbjkrruStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 4025708662
- width
- 512
- height
- "640"
- prompt
- a close up of a person wearing a dress and a pair of yellow and blue earrings
- scheduler
- EULERa
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "150"
{ "seed": 4025708662, "width": 512, "height": "640", "prompt": "a close up of a person wearing a dress and a pair of yellow and blue earrings", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", { input: { seed: 4025708662, width: 512, height: "640", prompt: "a close up of a person wearing a dress and a pair of yellow and blue earrings", scheduler: "EULERa", num_outputs: 1, guidance_scale: "7", num_inference_steps: "150" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", input={ "seed": 4025708662, "width": 512, "height": "640", "prompt": "a close up of a person wearing a dress and a pair of yellow and blue earrings", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run prompthero/lookbook 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": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", "input": { "seed": 4025708662, "width": 512, "height": "640", "prompt": "a close up of a person wearing a dress and a pair of yellow and blue earrings", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run prompthero/lookbook using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522 \ -i 'seed=4025708662' \ -i 'width=512' \ -i 'height="640"' \ -i 'prompt="a close up of a person wearing a dress and a pair of yellow and blue earrings"' \ -i 'scheduler="EULERa"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="150"'
To learn more, take a look at the Cog documentation.
Pull and run prompthero/lookbook using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 4025708662, "width": 512, "height": "640", "prompt": "a close up of a person wearing a dress and a pair of yellow and blue earrings", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-12-08T11:51:39.520073Z", "created_at": "2022-12-08T11:51:26.655546Z", "data_removed": false, "error": null, "id": "ihdbsokt7ncelcn2fcanbjkrru", "input": { "seed": 4025708662, "width": 512, "height": "640", "prompt": "a close up of a person wearing a dress and a pair of yellow and blue earrings", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }, "logs": "Using seed: 4025708662\nGlobal seed set to 4025708662\n 0%| | 0/150 [00:00<?, ?it/s]\n 1%|▏ | 2/150 [00:00<00:12, 12.18it/s]\n 3%|▎ | 4/150 [00:00<00:11, 12.57it/s]\n 4%|▍ | 6/150 [00:00<00:11, 12.68it/s]\n 5%|▌ | 8/150 [00:00<00:11, 12.63it/s]\n 7%|▋ | 10/150 [00:00<00:11, 12.64it/s]\n 8%|▊ | 12/150 [00:00<00:11, 11.84it/s]\n 9%|▉ | 14/150 [00:01<00:11, 12.14it/s]\n 11%|█ | 16/150 [00:01<00:10, 12.34it/s]\n 12%|█▏ | 18/150 [00:01<00:10, 12.52it/s]\n 13%|█▎ | 20/150 [00:01<00:10, 12.58it/s]\n 15%|█▍ | 22/150 [00:01<00:10, 12.65it/s]\n 16%|█▌ | 24/150 [00:01<00:10, 12.37it/s]\n 17%|█▋ | 26/150 [00:02<00:09, 12.47it/s]\n 19%|█▊ | 28/150 [00:02<00:09, 12.54it/s]\n 20%|██ | 30/150 [00:02<00:09, 12.57it/s]\n 21%|██▏ | 32/150 [00:02<00:09, 12.59it/s]\n 23%|██▎ | 34/150 [00:02<00:09, 12.57it/s]\n 24%|██▍ | 36/150 [00:02<00:09, 12.62it/s]\n 25%|██▌ | 38/150 [00:03<00:08, 12.53it/s]\n 27%|██▋ | 40/150 [00:03<00:08, 12.60it/s]\n 28%|██▊ | 42/150 [00:03<00:08, 12.66it/s]\n 29%|██▉ | 44/150 [00:03<00:08, 12.75it/s]\n 31%|███ | 46/150 [00:03<00:08, 12.70it/s]\n 32%|███▏ | 48/150 [00:03<00:08, 12.74it/s]\n 33%|███▎ | 50/150 [00:03<00:07, 12.56it/s]\n 35%|███▍ | 52/150 [00:04<00:07, 12.64it/s]\n 36%|███▌ | 54/150 [00:04<00:07, 12.70it/s]\n 37%|███▋ | 56/150 [00:04<00:07, 12.72it/s]\n 39%|███▊ | 58/150 [00:04<00:07, 12.74it/s]\n 40%|████ | 60/150 [00:04<00:07, 12.72it/s]\n 41%|████▏ | 62/150 [00:04<00:06, 12.78it/s]\n 43%|████▎ | 64/150 [00:05<00:06, 12.67it/s]\n 44%|████▍ | 66/150 [00:05<00:06, 12.74it/s]\n 45%|████▌ | 68/150 [00:05<00:06, 12.78it/s]\n 47%|████▋ | 70/150 [00:05<00:06, 12.72it/s]\n 48%|████▊ | 72/150 [00:05<00:06, 12.73it/s]\n 49%|████▉ | 74/150 [00:05<00:05, 12.85it/s]\n 51%|█████ | 76/150 [00:06<00:05, 12.69it/s]\n 52%|█████▏ | 78/150 [00:06<00:05, 12.79it/s]\n 53%|█████▎ | 80/150 [00:06<00:05, 12.87it/s]\n 55%|█████▍ | 82/150 [00:06<00:05, 12.94it/s]\n 56%|█████▌ | 84/150 [00:06<00:05, 12.97it/s]\n 57%|█████▋ | 86/150 [00:06<00:04, 13.03it/s]\n 59%|█████▊ | 88/150 [00:06<00:04, 13.08it/s]\n 60%|██████ | 90/150 [00:07<00:04, 13.03it/s]\n 61%|██████▏ | 92/150 [00:07<00:04, 13.02it/s]\n 63%|██████▎ | 94/150 [00:07<00:04, 13.03it/s]\n 64%|██████▍ | 96/150 [00:07<00:04, 13.04it/s]\n 65%|██████▌ | 98/150 [00:07<00:03, 13.02it/s]\n 67%|██████▋ | 100/150 [00:07<00:03, 12.98it/s]\n 68%|██████▊ | 102/150 [00:08<00:03, 12.96it/s]\n 69%|██████▉ | 104/150 [00:08<00:03, 12.81it/s]\n 71%|███████ | 106/150 [00:08<00:03, 12.65it/s]\n 72%|███████▏ | 108/150 [00:08<00:03, 12.69it/s]\n 73%|███████▎ | 110/150 [00:08<00:03, 12.43it/s]\n 75%|███████▍ | 112/150 [00:08<00:03, 12.30it/s]\n 76%|███████▌ | 114/150 [00:08<00:02, 12.47it/s]\n 77%|███████▋ | 116/150 [00:09<00:02, 12.51it/s]\n 79%|███████▊ | 118/150 [00:09<00:02, 12.57it/s]\n 80%|████████ | 120/150 [00:09<00:02, 12.62it/s]\n 81%|████████▏ | 122/150 [00:09<00:02, 12.64it/s]\n 83%|████████▎ | 124/150 [00:09<00:02, 12.71it/s]\n 84%|████████▍ | 126/150 [00:09<00:01, 12.78it/s]\n 85%|████████▌ | 128/150 [00:10<00:01, 12.67it/s]\n 87%|████████▋ | 130/150 [00:10<00:01, 12.68it/s]\n 88%|████████▊ | 132/150 [00:10<00:01, 12.72it/s]\n 89%|████████▉ | 134/150 [00:10<00:01, 12.77it/s]\n 91%|█████████ | 136/150 [00:10<00:01, 12.80it/s]\n 92%|█████████▏| 138/150 [00:10<00:00, 12.86it/s]\n 93%|█████████▎| 140/150 [00:11<00:00, 12.89it/s]\n 95%|█████████▍| 142/150 [00:11<00:00, 12.61it/s]\n 96%|█████████▌| 144/150 [00:11<00:00, 12.52it/s]\n 97%|█████████▋| 146/150 [00:11<00:00, 12.64it/s]\n 99%|█████████▊| 148/150 [00:11<00:00, 12.66it/s]\n100%|██████████| 150/150 [00:11<00:00, 12.76it/s]\n100%|██████████| 150/150 [00:11<00:00, 12.69it/s]", "metrics": { "predict_time": 12.824862, "total_time": 12.864527 }, "output": [ "https://replicate.delivery/pbxt/tZPu6TH5a1a6E1vMgwgRziyCICr5fG1Dv0FiZY3SAhalD8DIA/out-0.png" ], "started_at": "2022-12-08T11:51:26.695211Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ihdbsokt7ncelcn2fcanbjkrru", "cancel": "https://api.replicate.com/v1/predictions/ihdbsokt7ncelcn2fcanbjkrru/cancel" }, "version": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522" }
Generated inUsing seed: 4025708662 Global seed set to 4025708662 0%| | 0/150 [00:00<?, ?it/s] 1%|▏ | 2/150 [00:00<00:12, 12.18it/s] 3%|▎ | 4/150 [00:00<00:11, 12.57it/s] 4%|▍ | 6/150 [00:00<00:11, 12.68it/s] 5%|▌ | 8/150 [00:00<00:11, 12.63it/s] 7%|▋ | 10/150 [00:00<00:11, 12.64it/s] 8%|▊ | 12/150 [00:00<00:11, 11.84it/s] 9%|▉ | 14/150 [00:01<00:11, 12.14it/s] 11%|█ | 16/150 [00:01<00:10, 12.34it/s] 12%|█▏ | 18/150 [00:01<00:10, 12.52it/s] 13%|█▎ | 20/150 [00:01<00:10, 12.58it/s] 15%|█▍ | 22/150 [00:01<00:10, 12.65it/s] 16%|█▌ | 24/150 [00:01<00:10, 12.37it/s] 17%|█▋ | 26/150 [00:02<00:09, 12.47it/s] 19%|█▊ | 28/150 [00:02<00:09, 12.54it/s] 20%|██ | 30/150 [00:02<00:09, 12.57it/s] 21%|██▏ | 32/150 [00:02<00:09, 12.59it/s] 23%|██▎ | 34/150 [00:02<00:09, 12.57it/s] 24%|██▍ | 36/150 [00:02<00:09, 12.62it/s] 25%|██▌ | 38/150 [00:03<00:08, 12.53it/s] 27%|██▋ | 40/150 [00:03<00:08, 12.60it/s] 28%|██▊ | 42/150 [00:03<00:08, 12.66it/s] 29%|██▉ | 44/150 [00:03<00:08, 12.75it/s] 31%|███ | 46/150 [00:03<00:08, 12.70it/s] 32%|███▏ | 48/150 [00:03<00:08, 12.74it/s] 33%|███▎ | 50/150 [00:03<00:07, 12.56it/s] 35%|███▍ | 52/150 [00:04<00:07, 12.64it/s] 36%|███▌ | 54/150 [00:04<00:07, 12.70it/s] 37%|███▋ | 56/150 [00:04<00:07, 12.72it/s] 39%|███▊ | 58/150 [00:04<00:07, 12.74it/s] 40%|████ | 60/150 [00:04<00:07, 12.72it/s] 41%|████▏ | 62/150 [00:04<00:06, 12.78it/s] 43%|████▎ | 64/150 [00:05<00:06, 12.67it/s] 44%|████▍ | 66/150 [00:05<00:06, 12.74it/s] 45%|████▌ | 68/150 [00:05<00:06, 12.78it/s] 47%|████▋ | 70/150 [00:05<00:06, 12.72it/s] 48%|████▊ | 72/150 [00:05<00:06, 12.73it/s] 49%|████▉ | 74/150 [00:05<00:05, 12.85it/s] 51%|█████ | 76/150 [00:06<00:05, 12.69it/s] 52%|█████▏ | 78/150 [00:06<00:05, 12.79it/s] 53%|█████▎ | 80/150 [00:06<00:05, 12.87it/s] 55%|█████▍ | 82/150 [00:06<00:05, 12.94it/s] 56%|█████▌ | 84/150 [00:06<00:05, 12.97it/s] 57%|█████▋ | 86/150 [00:06<00:04, 13.03it/s] 59%|█████▊ | 88/150 [00:06<00:04, 13.08it/s] 60%|██████ | 90/150 [00:07<00:04, 13.03it/s] 61%|██████▏ | 92/150 [00:07<00:04, 13.02it/s] 63%|██████▎ | 94/150 [00:07<00:04, 13.03it/s] 64%|██████▍ | 96/150 [00:07<00:04, 13.04it/s] 65%|██████▌ | 98/150 [00:07<00:03, 13.02it/s] 67%|██████▋ | 100/150 [00:07<00:03, 12.98it/s] 68%|██████▊ | 102/150 [00:08<00:03, 12.96it/s] 69%|██████▉ | 104/150 [00:08<00:03, 12.81it/s] 71%|███████ | 106/150 [00:08<00:03, 12.65it/s] 72%|███████▏ | 108/150 [00:08<00:03, 12.69it/s] 73%|███████▎ | 110/150 [00:08<00:03, 12.43it/s] 75%|███████▍ | 112/150 [00:08<00:03, 12.30it/s] 76%|███████▌ | 114/150 [00:08<00:02, 12.47it/s] 77%|███████▋ | 116/150 [00:09<00:02, 12.51it/s] 79%|███████▊ | 118/150 [00:09<00:02, 12.57it/s] 80%|████████ | 120/150 [00:09<00:02, 12.62it/s] 81%|████████▏ | 122/150 [00:09<00:02, 12.64it/s] 83%|████████▎ | 124/150 [00:09<00:02, 12.71it/s] 84%|████████▍ | 126/150 [00:09<00:01, 12.78it/s] 85%|████████▌ | 128/150 [00:10<00:01, 12.67it/s] 87%|████████▋ | 130/150 [00:10<00:01, 12.68it/s] 88%|████████▊ | 132/150 [00:10<00:01, 12.72it/s] 89%|████████▉ | 134/150 [00:10<00:01, 12.77it/s] 91%|█████████ | 136/150 [00:10<00:01, 12.80it/s] 92%|█████████▏| 138/150 [00:10<00:00, 12.86it/s] 93%|█████████▎| 140/150 [00:11<00:00, 12.89it/s] 95%|█████████▍| 142/150 [00:11<00:00, 12.61it/s] 96%|█████████▌| 144/150 [00:11<00:00, 12.52it/s] 97%|█████████▋| 146/150 [00:11<00:00, 12.64it/s] 99%|█████████▊| 148/150 [00:11<00:00, 12.66it/s] 100%|██████████| 150/150 [00:11<00:00, 12.76it/s] 100%|██████████| 150/150 [00:11<00:00, 12.69it/s]
Prediction
prompthero/lookbook:afd0956cIDjc2xtzhqnvgb7dvxshg2v2rfjiStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- "640"
- prompt
- a photography of a handsome fashion model wearing a beige jacket
- scheduler
- EULERa
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "150"
{ "width": 512, "height": "640", "prompt": "a photography of a handsome fashion model wearing a beige jacket", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", { input: { width: 512, height: "640", prompt: "a photography of a handsome fashion model wearing a beige jacket", scheduler: "EULERa", num_outputs: 1, guidance_scale: "7", num_inference_steps: "150" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", input={ "width": 512, "height": "640", "prompt": "a photography of a handsome fashion model wearing a beige jacket", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run prompthero/lookbook 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": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", "input": { "width": 512, "height": "640", "prompt": "a photography of a handsome fashion model wearing a beige jacket", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run prompthero/lookbook using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522 \ -i 'width=512' \ -i 'height="640"' \ -i 'prompt="a photography of a handsome fashion model wearing a beige jacket"' \ -i 'scheduler="EULERa"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="150"'
To learn more, take a look at the Cog documentation.
Pull and run prompthero/lookbook using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": "640", "prompt": "a photography of a handsome fashion model wearing a beige jacket", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-12-08T23:01:12.407294Z", "created_at": "2022-12-08T23:00:59.553946Z", "data_removed": false, "error": null, "id": "jc2xtzhqnvgb7dvxshg2v2rfji", "input": { "width": 512, "height": "640", "prompt": "a photography of a handsome fashion model wearing a beige jacket", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }, "logs": "Using seed: 42838\nGlobal seed set to 42838\n 0%| | 0/150 [00:00<?, ?it/s]\n 1%|▏ | 2/150 [00:00<00:11, 12.37it/s]\n 3%|▎ | 4/150 [00:00<00:11, 12.65it/s]\n 4%|▍ | 6/150 [00:00<00:11, 12.83it/s]\n 5%|▌ | 8/150 [00:00<00:11, 12.83it/s]\n 7%|▋ | 10/150 [00:00<00:10, 12.83it/s]\n 8%|▊ | 12/150 [00:00<00:10, 12.87it/s]\n 9%|▉ | 14/150 [00:01<00:10, 12.88it/s]\n 11%|█ | 16/150 [00:01<00:10, 12.91it/s]\n 12%|█▏ | 18/150 [00:01<00:10, 12.92it/s]\n 13%|█▎ | 20/150 [00:01<00:10, 12.84it/s]\n 15%|█▍ | 22/150 [00:01<00:10, 12.75it/s]\n 16%|█▌ | 24/150 [00:01<00:09, 12.78it/s]\n 17%|█▋ | 26/150 [00:02<00:09, 12.73it/s]\n 19%|█▊ | 28/150 [00:02<00:09, 12.78it/s]\n 20%|██ | 30/150 [00:02<00:09, 12.71it/s]\n 21%|██▏ | 32/150 [00:02<00:09, 12.63it/s]\n 23%|██▎ | 34/150 [00:02<00:09, 12.58it/s]\n 24%|██▍ | 36/150 [00:02<00:09, 12.66it/s]\n 25%|██▌ | 38/150 [00:02<00:08, 12.73it/s]\n 27%|██▋ | 40/150 [00:03<00:08, 12.78it/s]\n 28%|██▊ | 42/150 [00:03<00:08, 12.83it/s]\n 29%|██▉ | 44/150 [00:03<00:08, 12.86it/s]\n 31%|███ | 46/150 [00:03<00:08, 12.80it/s]\n 32%|███▏ | 48/150 [00:03<00:07, 12.86it/s]\n 33%|███▎ | 50/150 [00:03<00:08, 12.46it/s]\n 35%|███▍ | 52/150 [00:04<00:07, 12.57it/s]\n 36%|███▌ | 54/150 [00:04<00:07, 12.65it/s]\n 37%|███▋ | 56/150 [00:04<00:07, 12.76it/s]\n 39%|███▊ | 58/150 [00:04<00:07, 12.85it/s]\n 40%|████ | 60/150 [00:04<00:07, 12.83it/s]\n 41%|████▏ | 62/150 [00:04<00:06, 12.86it/s]\n 43%|████▎ | 64/150 [00:05<00:06, 12.69it/s]\n 44%|████▍ | 66/150 [00:05<00:06, 12.73it/s]\n 45%|████▌ | 68/150 [00:05<00:06, 12.76it/s]\n 47%|████▋ | 70/150 [00:05<00:06, 12.77it/s]\n 48%|████▊ | 72/150 [00:05<00:06, 12.84it/s]\n 49%|████▉ | 74/150 [00:05<00:05, 12.90it/s]\n 51%|█████ | 76/150 [00:05<00:05, 12.95it/s]\n 52%|█████▏ | 78/150 [00:06<00:05, 12.74it/s]\n 53%|█████▎ | 80/150 [00:06<00:05, 12.80it/s]\n 55%|█████▍ | 82/150 [00:06<00:05, 12.83it/s]\n 56%|█████▌ | 84/150 [00:06<00:05, 12.88it/s]\n 57%|█████▋ | 86/150 [00:06<00:04, 12.92it/s]\n 59%|█████▊ | 88/150 [00:06<00:04, 12.97it/s]\n 60%|██████ | 90/150 [00:07<00:04, 12.98it/s]\n 61%|██████▏ | 92/150 [00:07<00:04, 12.92it/s]\n 63%|██████▎ | 94/150 [00:07<00:04, 12.95it/s]\n 64%|██████▍ | 96/150 [00:07<00:04, 12.96it/s]\n 65%|██████▌ | 98/150 [00:07<00:04, 12.90it/s]\n 67%|██████▋ | 100/150 [00:07<00:03, 12.52it/s]\n 68%|██████▊ | 102/150 [00:07<00:03, 12.32it/s]\n 69%|██████▉ | 104/150 [00:08<00:03, 12.38it/s]\n 71%|███████ | 106/150 [00:08<00:03, 12.51it/s]\n 72%|███████▏ | 108/150 [00:08<00:03, 12.61it/s]\n 73%|███████▎ | 110/150 [00:08<00:03, 12.71it/s]\n 75%|███████▍ | 112/150 [00:08<00:02, 12.75it/s]\n 76%|███████▌ | 114/150 [00:08<00:02, 12.84it/s]\n 77%|███████▋ | 116/150 [00:09<00:02, 12.80it/s]\n 79%|███████▊ | 118/150 [00:09<00:02, 12.86it/s]\n 80%|████████ | 120/150 [00:09<00:02, 12.86it/s]\n 81%|████████▏ | 122/150 [00:09<00:02, 12.80it/s]\n 83%|████████▎ | 124/150 [00:09<00:02, 12.82it/s]\n 84%|████████▍ | 126/150 [00:09<00:01, 12.81it/s]\n 85%|████████▌ | 128/150 [00:10<00:01, 12.82it/s]\n 87%|████████▋ | 130/150 [00:10<00:01, 12.72it/s]\n 88%|████████▊ | 132/150 [00:10<00:01, 12.80it/s]\n 89%|████████▉ | 134/150 [00:10<00:01, 12.85it/s]\n 91%|█████████ | 136/150 [00:10<00:01, 12.79it/s]\n 92%|█████████▏| 138/150 [00:10<00:00, 12.89it/s]\n 93%|█████████▎| 140/150 [00:10<00:00, 12.91it/s]\n 95%|█████████▍| 142/150 [00:11<00:00, 12.92it/s]\n 96%|█████████▌| 144/150 [00:11<00:00, 12.75it/s]\n 97%|█████████▋| 146/150 [00:11<00:00, 12.64it/s]\n 99%|█████████▊| 148/150 [00:11<00:00, 12.51it/s]\n100%|██████████| 150/150 [00:11<00:00, 12.35it/s]\n100%|██████████| 150/150 [00:11<00:00, 12.75it/s]", "metrics": { "predict_time": 12.814997, "total_time": 12.853348 }, "output": [ "https://replicate.delivery/pbxt/q6TBNBQeW1W4EyEBws3igeMYfVNi5xXQnZG84DTkeVAeWPABC/out-0.png" ], "started_at": "2022-12-08T23:00:59.592297Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jc2xtzhqnvgb7dvxshg2v2rfji", "cancel": "https://api.replicate.com/v1/predictions/jc2xtzhqnvgb7dvxshg2v2rfji/cancel" }, "version": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522" }
Generated inUsing seed: 42838 Global seed set to 42838 0%| | 0/150 [00:00<?, ?it/s] 1%|▏ | 2/150 [00:00<00:11, 12.37it/s] 3%|▎ | 4/150 [00:00<00:11, 12.65it/s] 4%|▍ | 6/150 [00:00<00:11, 12.83it/s] 5%|▌ | 8/150 [00:00<00:11, 12.83it/s] 7%|▋ | 10/150 [00:00<00:10, 12.83it/s] 8%|▊ | 12/150 [00:00<00:10, 12.87it/s] 9%|▉ | 14/150 [00:01<00:10, 12.88it/s] 11%|█ | 16/150 [00:01<00:10, 12.91it/s] 12%|█▏ | 18/150 [00:01<00:10, 12.92it/s] 13%|█▎ | 20/150 [00:01<00:10, 12.84it/s] 15%|█▍ | 22/150 [00:01<00:10, 12.75it/s] 16%|█▌ | 24/150 [00:01<00:09, 12.78it/s] 17%|█▋ | 26/150 [00:02<00:09, 12.73it/s] 19%|█▊ | 28/150 [00:02<00:09, 12.78it/s] 20%|██ | 30/150 [00:02<00:09, 12.71it/s] 21%|██▏ | 32/150 [00:02<00:09, 12.63it/s] 23%|██▎ | 34/150 [00:02<00:09, 12.58it/s] 24%|██▍ | 36/150 [00:02<00:09, 12.66it/s] 25%|██▌ | 38/150 [00:02<00:08, 12.73it/s] 27%|██▋ | 40/150 [00:03<00:08, 12.78it/s] 28%|██▊ | 42/150 [00:03<00:08, 12.83it/s] 29%|██▉ | 44/150 [00:03<00:08, 12.86it/s] 31%|███ | 46/150 [00:03<00:08, 12.80it/s] 32%|███▏ | 48/150 [00:03<00:07, 12.86it/s] 33%|███▎ | 50/150 [00:03<00:08, 12.46it/s] 35%|███▍ | 52/150 [00:04<00:07, 12.57it/s] 36%|███▌ | 54/150 [00:04<00:07, 12.65it/s] 37%|███▋ | 56/150 [00:04<00:07, 12.76it/s] 39%|███▊ | 58/150 [00:04<00:07, 12.85it/s] 40%|████ | 60/150 [00:04<00:07, 12.83it/s] 41%|████▏ | 62/150 [00:04<00:06, 12.86it/s] 43%|████▎ | 64/150 [00:05<00:06, 12.69it/s] 44%|████▍ | 66/150 [00:05<00:06, 12.73it/s] 45%|████▌ | 68/150 [00:05<00:06, 12.76it/s] 47%|████▋ | 70/150 [00:05<00:06, 12.77it/s] 48%|████▊ | 72/150 [00:05<00:06, 12.84it/s] 49%|████▉ | 74/150 [00:05<00:05, 12.90it/s] 51%|█████ | 76/150 [00:05<00:05, 12.95it/s] 52%|█████▏ | 78/150 [00:06<00:05, 12.74it/s] 53%|█████▎ | 80/150 [00:06<00:05, 12.80it/s] 55%|█████▍ | 82/150 [00:06<00:05, 12.83it/s] 56%|█████▌ | 84/150 [00:06<00:05, 12.88it/s] 57%|█████▋ | 86/150 [00:06<00:04, 12.92it/s] 59%|█████▊ | 88/150 [00:06<00:04, 12.97it/s] 60%|██████ | 90/150 [00:07<00:04, 12.98it/s] 61%|██████▏ | 92/150 [00:07<00:04, 12.92it/s] 63%|██████▎ | 94/150 [00:07<00:04, 12.95it/s] 64%|██████▍ | 96/150 [00:07<00:04, 12.96it/s] 65%|██████▌ | 98/150 [00:07<00:04, 12.90it/s] 67%|██████▋ | 100/150 [00:07<00:03, 12.52it/s] 68%|██████▊ | 102/150 [00:07<00:03, 12.32it/s] 69%|██████▉ | 104/150 [00:08<00:03, 12.38it/s] 71%|███████ | 106/150 [00:08<00:03, 12.51it/s] 72%|███████▏ | 108/150 [00:08<00:03, 12.61it/s] 73%|███████▎ | 110/150 [00:08<00:03, 12.71it/s] 75%|███████▍ | 112/150 [00:08<00:02, 12.75it/s] 76%|███████▌ | 114/150 [00:08<00:02, 12.84it/s] 77%|███████▋ | 116/150 [00:09<00:02, 12.80it/s] 79%|███████▊ | 118/150 [00:09<00:02, 12.86it/s] 80%|████████ | 120/150 [00:09<00:02, 12.86it/s] 81%|████████▏ | 122/150 [00:09<00:02, 12.80it/s] 83%|████████▎ | 124/150 [00:09<00:02, 12.82it/s] 84%|████████▍ | 126/150 [00:09<00:01, 12.81it/s] 85%|████████▌ | 128/150 [00:10<00:01, 12.82it/s] 87%|████████▋ | 130/150 [00:10<00:01, 12.72it/s] 88%|████████▊ | 132/150 [00:10<00:01, 12.80it/s] 89%|████████▉ | 134/150 [00:10<00:01, 12.85it/s] 91%|█████████ | 136/150 [00:10<00:01, 12.79it/s] 92%|█████████▏| 138/150 [00:10<00:00, 12.89it/s] 93%|█████████▎| 140/150 [00:10<00:00, 12.91it/s] 95%|█████████▍| 142/150 [00:11<00:00, 12.92it/s] 96%|█████████▌| 144/150 [00:11<00:00, 12.75it/s] 97%|█████████▋| 146/150 [00:11<00:00, 12.64it/s] 99%|█████████▊| 148/150 [00:11<00:00, 12.51it/s] 100%|██████████| 150/150 [00:11<00:00, 12.35it/s] 100%|██████████| 150/150 [00:11<00:00, 12.75it/s]
Prediction
prompthero/lookbook:afd0956cIDfya7kywy6ralheknzkcgxrkixyStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- "512"
- prompt
- a close up of a cap weared by a man with stubble beard
- scheduler
- EULERa
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "150"
{ "width": 512, "height": "512", "prompt": "a close up of a cap weared by a man with stubble beard", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", { input: { width: 512, height: "512", prompt: "a close up of a cap weared by a man with stubble beard", scheduler: "EULERa", num_outputs: 1, guidance_scale: "7", num_inference_steps: "150" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run prompthero/lookbook using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/lookbook:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", input={ "width": 512, "height": "512", "prompt": "a close up of a cap weared by a man with stubble beard", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run prompthero/lookbook 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": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522", "input": { "width": 512, "height": "512", "prompt": "a close up of a cap weared by a man with stubble beard", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run prompthero/lookbook using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522 \ -i 'width=512' \ -i 'height="512"' \ -i 'prompt="a close up of a cap weared by a man with stubble beard"' \ -i 'scheduler="EULERa"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="150"'
To learn more, take a look at the Cog documentation.
Pull and run prompthero/lookbook using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/lookbook@sha256:afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": "512", "prompt": "a close up of a cap weared by a man with stubble beard", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-12-08T23:12:05.572668Z", "created_at": "2022-12-08T23:11:54.762045Z", "data_removed": false, "error": null, "id": "fya7kywy6ralheknzkcgxrkixy", "input": { "width": 512, "height": "512", "prompt": "a close up of a cap weared by a man with stubble beard", "scheduler": "EULERa", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "150" }, "logs": "Using seed: 50078\nGlobal seed set to 50078\n 0%| | 0/150 [00:00<?, ?it/s]\n 1%|▏ | 2/150 [00:00<00:10, 13.46it/s]\n 3%|▎ | 4/150 [00:00<00:10, 13.81it/s]\n 4%|▍ | 6/150 [00:00<00:10, 14.23it/s]\n 5%|▌ | 8/150 [00:00<00:09, 14.49it/s]\n 7%|▋ | 10/150 [00:00<00:09, 14.61it/s]\n 8%|▊ | 12/150 [00:00<00:09, 14.60it/s]\n 9%|▉ | 14/150 [00:00<00:09, 14.57it/s]\n 11%|█ | 16/150 [00:01<00:09, 14.60it/s]\n 12%|█▏ | 18/150 [00:01<00:09, 14.61it/s]\n 13%|█▎ | 20/150 [00:01<00:08, 14.60it/s]\n 15%|█▍ | 22/150 [00:01<00:08, 14.67it/s]\n 16%|█▌ | 24/150 [00:01<00:08, 14.70it/s]\n 17%|█▋ | 26/150 [00:01<00:08, 14.64it/s]\n 19%|█▊ | 28/150 [00:01<00:08, 14.53it/s]\n 20%|██ | 30/150 [00:02<00:08, 14.52it/s]\n 21%|██▏ | 32/150 [00:02<00:08, 14.59it/s]\n 23%|██▎ | 34/150 [00:02<00:07, 14.66it/s]\n 24%|██▍ | 36/150 [00:02<00:07, 14.72it/s]\n 25%|██▌ | 38/150 [00:02<00:07, 14.71it/s]\n 27%|██▋ | 40/150 [00:02<00:07, 14.75it/s]\n 28%|██▊ | 42/150 [00:02<00:07, 14.62it/s]\n 29%|██▉ | 44/150 [00:03<00:07, 14.60it/s]\n 31%|███ | 46/150 [00:03<00:07, 14.59it/s]\n 32%|███▏ | 48/150 [00:03<00:06, 14.63it/s]\n 33%|███▎ | 50/150 [00:03<00:06, 14.68it/s]\n 35%|███▍ | 52/150 [00:03<00:06, 14.70it/s]\n 36%|███▌ | 54/150 [00:03<00:06, 14.72it/s]\n 37%|███▋ | 56/150 [00:03<00:06, 14.58it/s]\n 39%|███▊ | 58/150 [00:03<00:06, 14.63it/s]\n 40%|████ | 60/150 [00:04<00:06, 14.45it/s]\n 41%|████▏ | 62/150 [00:04<00:06, 14.48it/s]\n 43%|████▎ | 64/150 [00:04<00:05, 14.47it/s]\n 44%|████▍ | 66/150 [00:04<00:05, 14.51it/s]\n 45%|████▌ | 68/150 [00:04<00:05, 14.53it/s]\n 47%|████▋ | 70/150 [00:04<00:05, 14.52it/s]\n 48%|████▊ | 72/150 [00:04<00:05, 14.56it/s]\n 49%|████▉ | 74/150 [00:05<00:05, 14.60it/s]\n 51%|█████ | 76/150 [00:05<00:05, 14.46it/s]\n 52%|█████▏ | 78/150 [00:05<00:04, 14.48it/s]\n 53%|█████▎ | 80/150 [00:05<00:04, 14.54it/s]\n 55%|█████▍ | 82/150 [00:05<00:04, 14.59it/s]\n 56%|█████▌ | 84/150 [00:05<00:04, 14.62it/s]\n 57%|█████▋ | 86/150 [00:05<00:04, 14.69it/s]\n 59%|█████▊ | 88/150 [00:06<00:04, 14.69it/s]\n 60%|██████ | 90/150 [00:06<00:04, 14.74it/s]\n 61%|██████▏ | 92/150 [00:06<00:03, 14.75it/s]\n 63%|██████▎ | 94/150 [00:06<00:03, 14.74it/s]\n 64%|██████▍ | 96/150 [00:06<00:03, 14.74it/s]\n 65%|██████▌ | 98/150 [00:06<00:03, 14.72it/s]\n 67%|██████▋ | 100/150 [00:06<00:03, 14.65it/s]\n 68%|██████▊ | 102/150 [00:06<00:03, 14.67it/s]\n 69%|██████▉ | 104/150 [00:07<00:03, 14.71it/s]\n 71%|███████ | 106/150 [00:07<00:02, 14.71it/s]\n 72%|███████▏ | 108/150 [00:07<00:02, 14.69it/s]\n 73%|███████▎ | 110/150 [00:07<00:02, 14.67it/s]\n 75%|███████▍ | 112/150 [00:07<00:02, 14.65it/s]\n 76%|███████▌ | 114/150 [00:07<00:02, 14.57it/s]\n 77%|███████▋ | 116/150 [00:07<00:02, 14.59it/s]\n 79%|███████▊ | 118/150 [00:08<00:02, 14.59it/s]\n 80%|████████ | 120/150 [00:08<00:02, 14.59it/s]\n 81%|████████▏ | 122/150 [00:08<00:01, 14.47it/s]\n 83%|████████▎ | 124/150 [00:08<00:01, 14.50it/s]\n 84%|████████▍ | 126/150 [00:08<00:01, 13.94it/s]\n 85%|████████▌ | 128/150 [00:08<00:01, 13.95it/s]\n 87%|████████▋ | 130/150 [00:08<00:01, 14.14it/s]\n 88%|████████▊ | 132/150 [00:09<00:01, 14.16it/s]\n 89%|████████▉ | 134/150 [00:09<00:01, 14.16it/s]\n 91%|█████████ | 136/150 [00:09<00:00, 14.31it/s]\n 92%|█████████▏| 138/150 [00:09<00:00, 14.42it/s]\n 93%|█████████▎| 140/150 [00:09<00:00, 14.50it/s]\n 95%|█████████▍| 142/150 [00:09<00:00, 14.53it/s]\n 96%|█████████▌| 144/150 [00:09<00:00, 14.58it/s]\n 97%|█████████▋| 146/150 [00:10<00:00, 14.41it/s]\n 99%|█████████▊| 148/150 [00:10<00:00, 14.37it/s]\n100%|██████████| 150/150 [00:10<00:00, 14.38it/s]\n100%|██████████| 150/150 [00:10<00:00, 14.54it/s]", "metrics": { "predict_time": 10.773877, "total_time": 10.810623 }, "output": [ "https://replicate.delivery/pbxt/LYci3SkbnCJMKdkjwBEYbXGGnE9x3Mn03xQkaXqq1NRRhACE/out-0.png" ], "started_at": "2022-12-08T23:11:54.798791Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fya7kywy6ralheknzkcgxrkixy", "cancel": "https://api.replicate.com/v1/predictions/fya7kywy6ralheknzkcgxrkixy/cancel" }, "version": "afd0956c8dd6a67cbf163411fa9507475e92bd956d473d10751a49b67fb79522" }
Generated inUsing seed: 50078 Global seed set to 50078 0%| | 0/150 [00:00<?, ?it/s] 1%|▏ | 2/150 [00:00<00:10, 13.46it/s] 3%|▎ | 4/150 [00:00<00:10, 13.81it/s] 4%|▍ | 6/150 [00:00<00:10, 14.23it/s] 5%|▌ | 8/150 [00:00<00:09, 14.49it/s] 7%|▋ | 10/150 [00:00<00:09, 14.61it/s] 8%|▊ | 12/150 [00:00<00:09, 14.60it/s] 9%|▉ | 14/150 [00:00<00:09, 14.57it/s] 11%|█ | 16/150 [00:01<00:09, 14.60it/s] 12%|█▏ | 18/150 [00:01<00:09, 14.61it/s] 13%|█▎ | 20/150 [00:01<00:08, 14.60it/s] 15%|█▍ | 22/150 [00:01<00:08, 14.67it/s] 16%|█▌ | 24/150 [00:01<00:08, 14.70it/s] 17%|█▋ | 26/150 [00:01<00:08, 14.64it/s] 19%|█▊ | 28/150 [00:01<00:08, 14.53it/s] 20%|██ | 30/150 [00:02<00:08, 14.52it/s] 21%|██▏ | 32/150 [00:02<00:08, 14.59it/s] 23%|██▎ | 34/150 [00:02<00:07, 14.66it/s] 24%|██▍ | 36/150 [00:02<00:07, 14.72it/s] 25%|██▌ | 38/150 [00:02<00:07, 14.71it/s] 27%|██▋ | 40/150 [00:02<00:07, 14.75it/s] 28%|██▊ | 42/150 [00:02<00:07, 14.62it/s] 29%|██▉ | 44/150 [00:03<00:07, 14.60it/s] 31%|███ | 46/150 [00:03<00:07, 14.59it/s] 32%|███▏ | 48/150 [00:03<00:06, 14.63it/s] 33%|███▎ | 50/150 [00:03<00:06, 14.68it/s] 35%|███▍ | 52/150 [00:03<00:06, 14.70it/s] 36%|███▌ | 54/150 [00:03<00:06, 14.72it/s] 37%|███▋ | 56/150 [00:03<00:06, 14.58it/s] 39%|███▊ | 58/150 [00:03<00:06, 14.63it/s] 40%|████ | 60/150 [00:04<00:06, 14.45it/s] 41%|████▏ | 62/150 [00:04<00:06, 14.48it/s] 43%|████▎ | 64/150 [00:04<00:05, 14.47it/s] 44%|████▍ | 66/150 [00:04<00:05, 14.51it/s] 45%|████▌ | 68/150 [00:04<00:05, 14.53it/s] 47%|████▋ | 70/150 [00:04<00:05, 14.52it/s] 48%|████▊ | 72/150 [00:04<00:05, 14.56it/s] 49%|████▉ | 74/150 [00:05<00:05, 14.60it/s] 51%|█████ | 76/150 [00:05<00:05, 14.46it/s] 52%|█████▏ | 78/150 [00:05<00:04, 14.48it/s] 53%|█████▎ | 80/150 [00:05<00:04, 14.54it/s] 55%|█████▍ | 82/150 [00:05<00:04, 14.59it/s] 56%|█████▌ | 84/150 [00:05<00:04, 14.62it/s] 57%|█████▋ | 86/150 [00:05<00:04, 14.69it/s] 59%|█████▊ | 88/150 [00:06<00:04, 14.69it/s] 60%|██████ | 90/150 [00:06<00:04, 14.74it/s] 61%|██████▏ | 92/150 [00:06<00:03, 14.75it/s] 63%|██████▎ | 94/150 [00:06<00:03, 14.74it/s] 64%|██████▍ | 96/150 [00:06<00:03, 14.74it/s] 65%|██████▌ | 98/150 [00:06<00:03, 14.72it/s] 67%|██████▋ | 100/150 [00:06<00:03, 14.65it/s] 68%|██████▊ | 102/150 [00:06<00:03, 14.67it/s] 69%|██████▉ | 104/150 [00:07<00:03, 14.71it/s] 71%|███████ | 106/150 [00:07<00:02, 14.71it/s] 72%|███████▏ | 108/150 [00:07<00:02, 14.69it/s] 73%|███████▎ | 110/150 [00:07<00:02, 14.67it/s] 75%|███████▍ | 112/150 [00:07<00:02, 14.65it/s] 76%|███████▌ | 114/150 [00:07<00:02, 14.57it/s] 77%|███████▋ | 116/150 [00:07<00:02, 14.59it/s] 79%|███████▊ | 118/150 [00:08<00:02, 14.59it/s] 80%|████████ | 120/150 [00:08<00:02, 14.59it/s] 81%|████████▏ | 122/150 [00:08<00:01, 14.47it/s] 83%|████████▎ | 124/150 [00:08<00:01, 14.50it/s] 84%|████████▍ | 126/150 [00:08<00:01, 13.94it/s] 85%|████████▌ | 128/150 [00:08<00:01, 13.95it/s] 87%|████████▋ | 130/150 [00:08<00:01, 14.14it/s] 88%|████████▊ | 132/150 [00:09<00:01, 14.16it/s] 89%|████████▉ | 134/150 [00:09<00:01, 14.16it/s] 91%|█████████ | 136/150 [00:09<00:00, 14.31it/s] 92%|█████████▏| 138/150 [00:09<00:00, 14.42it/s] 93%|█████████▎| 140/150 [00:09<00:00, 14.50it/s] 95%|█████████▍| 142/150 [00:09<00:00, 14.53it/s] 96%|█████████▌| 144/150 [00:09<00:00, 14.58it/s] 97%|█████████▋| 146/150 [00:10<00:00, 14.41it/s] 99%|█████████▊| 148/150 [00:10<00:00, 14.37it/s] 100%|██████████| 150/150 [00:10<00:00, 14.38it/s] 100%|██████████| 150/150 [00:10<00:00, 14.54it/s]
Want to make some of these yourself?
Run this model