sliday
/
pooh
Illustration style inspired byt Winnie-the-P00h books
- Public
- 105 runs
-
H100
Prediction
sliday/pooh:327a4152ModelIDggrpxb3f39rm00cjgwma8yj1w4StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, two cats talkin
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 1:1
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "model": "dev", "prompt": "p00h, two cats talkin", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, two cats talkin", lora_scale: 1, num_outputs: 1, aspect_ratio: "1:1", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, two cats talkin", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, two cats talkin", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T18:33:59.317155Z", "created_at": "2024-10-13T18:33:47.034000Z", "data_removed": false, "error": null, "id": "ggrpxb3f39rm00cjgwma8yj1w4", "input": { "model": "dev", "prompt": "p00h, two cats talkin", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 37652\nPrompt: p00h, two cats talkin\n[!] txt2img mode\nUsing dev model\nfree=6529936289792\nDownloading weights\n2024-10-13T18:33:47Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpcnt4ybls/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\n2024-10-13T18:33:48Z | INFO | [ Complete ] dest=/tmp/tmpcnt4ybls/weights size=\"173 MB\" total_elapsed=1.468s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\nDownloaded weights in 1.51s\nLoaded LoRAs in 2.25s\n 0%| | 0/28 [00:00<?, ?it/s]\n 4%|▎ | 1/28 [00:00<00:09, 2.88it/s]\n 7%|▋ | 2/28 [00:00<00:08, 3.21it/s]\n 11%|█ | 3/28 [00:00<00:08, 3.05it/s]\n 14%|█▍ | 4/28 [00:01<00:08, 2.98it/s]\n 18%|█▊ | 5/28 [00:01<00:07, 2.94it/s]\n 21%|██▏ | 6/28 [00:02<00:07, 2.92it/s]\n 25%|██▌ | 7/28 [00:02<00:07, 2.91it/s]\n 29%|██▊ | 8/28 [00:02<00:06, 2.90it/s]\n 32%|███▏ | 9/28 [00:03<00:06, 2.89it/s]\n 36%|███▌ | 10/28 [00:03<00:06, 2.89it/s]\n 39%|███▉ | 11/28 [00:03<00:05, 2.88it/s]\n 43%|████▎ | 12/28 [00:04<00:05, 2.88it/s]\n 46%|████▋ | 13/28 [00:04<00:05, 2.88it/s]\n 50%|█████ | 14/28 [00:04<00:04, 2.88it/s]\n 54%|█████▎ | 15/28 [00:05<00:04, 2.88it/s]\n 57%|█████▋ | 16/28 [00:05<00:04, 2.88it/s]\n 61%|██████ | 17/28 [00:05<00:03, 2.88it/s]\n 64%|██████▍ | 18/28 [00:06<00:03, 2.88it/s]\n 68%|██████▊ | 19/28 [00:06<00:03, 2.88it/s]\n 71%|███████▏ | 20/28 [00:06<00:02, 2.88it/s]\n 75%|███████▌ | 21/28 [00:07<00:02, 2.88it/s]\n 79%|███████▊ | 22/28 [00:07<00:02, 2.88it/s]\n 82%|████████▏ | 23/28 [00:07<00:01, 2.88it/s]\n 86%|████████▌ | 24/28 [00:08<00:01, 2.88it/s]\n 89%|████████▉ | 25/28 [00:08<00:01, 2.88it/s]\n 93%|█████████▎| 26/28 [00:08<00:00, 2.88it/s]\n 96%|█████████▋| 27/28 [00:09<00:00, 2.88it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.88it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.90it/s]", "metrics": { "predict_time": 12.276350203, "total_time": 12.283155 }, "output": [ "https://replicate.delivery/yhqm/S4EQzMGELar7Cx0JQ7y2h1M55tfanBIX0nJyoBbAiZzLJOzJA/out-0.webp" ], "started_at": "2024-10-13T18:33:47.040805Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ggrpxb3f39rm00cjgwma8yj1w4", "cancel": "https://api.replicate.com/v1/predictions/ggrpxb3f39rm00cjgwma8yj1w4/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 37652 Prompt: p00h, two cats talkin [!] txt2img mode Using dev model free=6529936289792 Downloading weights 2024-10-13T18:33:47Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpcnt4ybls/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar 2024-10-13T18:33:48Z | INFO | [ Complete ] dest=/tmp/tmpcnt4ybls/weights size="173 MB" total_elapsed=1.468s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar Downloaded weights in 1.51s Loaded LoRAs in 2.25s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.88it/s] 7%|▋ | 2/28 [00:00<00:08, 3.21it/s] 11%|█ | 3/28 [00:00<00:08, 3.05it/s] 14%|█▍ | 4/28 [00:01<00:08, 2.98it/s] 18%|█▊ | 5/28 [00:01<00:07, 2.94it/s] 21%|██▏ | 6/28 [00:02<00:07, 2.92it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.91it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.90it/s] 32%|███▏ | 9/28 [00:03<00:06, 2.89it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.89it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.88it/s] 43%|████▎ | 12/28 [00:04<00:05, 2.88it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.88it/s] 50%|█████ | 14/28 [00:04<00:04, 2.88it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.88it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.88it/s] 61%|██████ | 17/28 [00:05<00:03, 2.88it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.88it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.88it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.88it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.88it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.88it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.88it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.88it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.88it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.88it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.88it/s] 100%|██████████| 28/28 [00:09<00:00, 2.88it/s] 100%|██████████| 28/28 [00:09<00:00, 2.90it/s]
Prediction
sliday/pooh:327a4152ModelIDcwgb8eveknrm00cjgwz84g8rtwStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, white bears, game of go in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 40
{ "model": "dev", "prompt": "p00h, white bears, game of go in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 40 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, white bears, game of go in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 40 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, white bears, game of go in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 40 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, white bears, game of go in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T18:58:09.139017Z", "created_at": "2024-10-13T18:57:48.701000Z", "data_removed": false, "error": null, "id": "cwgb8eveknrm00cjgwz84g8rtw", "input": { "model": "dev", "prompt": "p00h, white bears, game of go in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 40 }, "logs": "Using seed: 63735\nPrompt: p00h, white bears, game of go in style of p00h\n[!] txt2img mode\nUsing dev model\nLoaded LoRAs in 0.71s\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:13, 2.96it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.30it/s]\n 8%|▊ | 3/40 [00:00<00:11, 3.14it/s]\n 10%|█ | 4/40 [00:01<00:11, 3.07it/s]\n 12%|█▎ | 5/40 [00:01<00:11, 3.03it/s]\n 15%|█▌ | 6/40 [00:01<00:11, 3.01it/s]\n 18%|█▊ | 7/40 [00:02<00:11, 2.99it/s]\n 20%|██ | 8/40 [00:02<00:10, 2.98it/s]\n 22%|██▎ | 9/40 [00:02<00:10, 2.98it/s]\n 25%|██▌ | 10/40 [00:03<00:10, 2.97it/s]\n 28%|██▊ | 11/40 [00:03<00:09, 2.97it/s]\n 30%|███ | 12/40 [00:03<00:09, 2.97it/s]\n 32%|███▎ | 13/40 [00:04<00:09, 2.97it/s]\n 35%|███▌ | 14/40 [00:04<00:08, 2.97it/s]\n 38%|███▊ | 15/40 [00:05<00:08, 2.97it/s]\n 40%|████ | 16/40 [00:05<00:08, 2.96it/s]\n 42%|████▎ | 17/40 [00:05<00:07, 2.96it/s]\n 45%|████▌ | 18/40 [00:06<00:07, 2.96it/s]\n 48%|████▊ | 19/40 [00:06<00:07, 2.96it/s]\n 50%|█████ | 20/40 [00:06<00:06, 2.96it/s]\n 52%|█████▎ | 21/40 [00:07<00:06, 2.96it/s]\n 55%|█████▌ | 22/40 [00:07<00:06, 2.96it/s]\n 57%|█████▊ | 23/40 [00:07<00:05, 2.96it/s]\n 60%|██████ | 24/40 [00:08<00:05, 2.96it/s]\n 62%|██████▎ | 25/40 [00:08<00:05, 2.96it/s]\n 65%|██████▌ | 26/40 [00:08<00:04, 2.96it/s]\n 68%|██████▊ | 27/40 [00:09<00:04, 2.96it/s]\n 70%|███████ | 28/40 [00:09<00:04, 2.96it/s]\n 72%|███████▎ | 29/40 [00:09<00:03, 2.96it/s]\n 75%|███████▌ | 30/40 [00:10<00:03, 2.97it/s]\n 78%|███████▊ | 31/40 [00:10<00:03, 2.97it/s]\n 80%|████████ | 32/40 [00:10<00:02, 2.97it/s]\n 82%|████████▎ | 33/40 [00:11<00:02, 2.97it/s]\n 85%|████████▌ | 34/40 [00:11<00:02, 2.97it/s]\n 88%|████████▊ | 35/40 [00:11<00:01, 2.97it/s]\n 90%|█████████ | 36/40 [00:12<00:01, 2.97it/s]\n 92%|█████████▎| 37/40 [00:12<00:01, 2.97it/s]\n 95%|█████████▌| 38/40 [00:12<00:00, 2.97it/s]\n 98%|█████████▊| 39/40 [00:13<00:00, 2.97it/s]\n100%|██████████| 40/40 [00:13<00:00, 2.97it/s]\n100%|██████████| 40/40 [00:13<00:00, 2.98it/s]", "metrics": { "predict_time": 14.455774192, "total_time": 20.438017 }, "output": [ "https://replicate.delivery/yhqm/vcWeyCr1gTxnKqtnashleraIzXIegLAfpY2eiQ4JX8OJIlzcC/out-0.webp" ], "started_at": "2024-10-13T18:57:54.683242Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cwgb8eveknrm00cjgwz84g8rtw", "cancel": "https://api.replicate.com/v1/predictions/cwgb8eveknrm00cjgwz84g8rtw/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 63735 Prompt: p00h, white bears, game of go in style of p00h [!] txt2img mode Using dev model Loaded LoRAs in 0.71s 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:13, 2.96it/s] 5%|▌ | 2/40 [00:00<00:11, 3.30it/s] 8%|▊ | 3/40 [00:00<00:11, 3.14it/s] 10%|█ | 4/40 [00:01<00:11, 3.07it/s] 12%|█▎ | 5/40 [00:01<00:11, 3.03it/s] 15%|█▌ | 6/40 [00:01<00:11, 3.01it/s] 18%|█▊ | 7/40 [00:02<00:11, 2.99it/s] 20%|██ | 8/40 [00:02<00:10, 2.98it/s] 22%|██▎ | 9/40 [00:02<00:10, 2.98it/s] 25%|██▌ | 10/40 [00:03<00:10, 2.97it/s] 28%|██▊ | 11/40 [00:03<00:09, 2.97it/s] 30%|███ | 12/40 [00:03<00:09, 2.97it/s] 32%|███▎ | 13/40 [00:04<00:09, 2.97it/s] 35%|███▌ | 14/40 [00:04<00:08, 2.97it/s] 38%|███▊ | 15/40 [00:05<00:08, 2.97it/s] 40%|████ | 16/40 [00:05<00:08, 2.96it/s] 42%|████▎ | 17/40 [00:05<00:07, 2.96it/s] 45%|████▌ | 18/40 [00:06<00:07, 2.96it/s] 48%|████▊ | 19/40 [00:06<00:07, 2.96it/s] 50%|█████ | 20/40 [00:06<00:06, 2.96it/s] 52%|█████▎ | 21/40 [00:07<00:06, 2.96it/s] 55%|█████▌ | 22/40 [00:07<00:06, 2.96it/s] 57%|█████▊ | 23/40 [00:07<00:05, 2.96it/s] 60%|██████ | 24/40 [00:08<00:05, 2.96it/s] 62%|██████▎ | 25/40 [00:08<00:05, 2.96it/s] 65%|██████▌ | 26/40 [00:08<00:04, 2.96it/s] 68%|██████▊ | 27/40 [00:09<00:04, 2.96it/s] 70%|███████ | 28/40 [00:09<00:04, 2.96it/s] 72%|███████▎ | 29/40 [00:09<00:03, 2.96it/s] 75%|███████▌ | 30/40 [00:10<00:03, 2.97it/s] 78%|███████▊ | 31/40 [00:10<00:03, 2.97it/s] 80%|████████ | 32/40 [00:10<00:02, 2.97it/s] 82%|████████▎ | 33/40 [00:11<00:02, 2.97it/s] 85%|████████▌ | 34/40 [00:11<00:02, 2.97it/s] 88%|████████▊ | 35/40 [00:11<00:01, 2.97it/s] 90%|█████████ | 36/40 [00:12<00:01, 2.97it/s] 92%|█████████▎| 37/40 [00:12<00:01, 2.97it/s] 95%|█████████▌| 38/40 [00:12<00:00, 2.97it/s] 98%|█████████▊| 39/40 [00:13<00:00, 2.97it/s] 100%|██████████| 40/40 [00:13<00:00, 2.97it/s] 100%|██████████| 40/40 [00:13<00:00, 2.98it/s]
Prediction
sliday/pooh:327a4152ModelIDvafrg090kdrm40cjgwvbcnkk70StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, white bear and tiger, game of chess in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "model": "dev", "prompt": "p00h, white bear and tiger, game of chess in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, white bear and tiger, game of chess in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, white bear and tiger, game of chess in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, white bear and tiger, game of chess in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T18:50:20.553383Z", "created_at": "2024-10-13T18:48:44.443000Z", "data_removed": false, "error": null, "id": "vafrg090kdrm40cjgwvbcnkk70", "input": { "model": "dev", "prompt": "p00h, white bear and tiger, game of chess in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 43982\nPrompt: p00h, white bear and tiger, game of chess in style of p00h\n[!] txt2img mode\nUsing dev model\nfree=8633805922304\nDownloading weights\n2024-10-13T18:50:08Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4q0bxlo2/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\n2024-10-13T18:50:10Z | INFO | [ Complete ] dest=/tmp/tmp4q0bxlo2/weights size=\"173 MB\" total_elapsed=1.361s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\nDownloaded weights in 1.47s\nLoaded LoRAs in 2.18s\n 0%| | 0/28 [00:00<?, ?it/s]\n 4%|▎ | 1/28 [00:00<00:09, 2.95it/s]\n 7%|▋ | 2/28 [00:00<00:07, 3.29it/s]\n 11%|█ | 3/28 [00:00<00:07, 3.13it/s]\n 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s]\n 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s]\n 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s]\n 25%|██▌ | 7/28 [00:02<00:07, 2.99it/s]\n 29%|██▊ | 8/28 [00:02<00:06, 2.98it/s]\n 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s]\n 36%|███▌ | 10/28 [00:03<00:06, 2.97it/s]\n 39%|███▉ | 11/28 [00:03<00:05, 2.97it/s]\n 43%|████▎ | 12/28 [00:03<00:05, 2.96it/s]\n 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s]\n 50%|█████ | 14/28 [00:04<00:04, 2.96it/s]\n 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s]\n 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s]\n 61%|██████ | 17/28 [00:05<00:03, 2.96it/s]\n 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s]\n 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s]\n 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s]\n 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s]\n 79%|███████▊ | 22/28 [00:07<00:02, 2.96it/s]\n 82%|████████▏ | 23/28 [00:07<00:01, 2.96it/s]\n 86%|████████▌ | 24/28 [00:08<00:01, 2.96it/s]\n 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s]\n 93%|█████████▎| 26/28 [00:08<00:00, 2.96it/s]\n 96%|█████████▋| 27/28 [00:09<00:00, 2.96it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.96it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.98it/s]", "metrics": { "predict_time": 11.915190386999999, "total_time": 96.110383 }, "output": [ "https://replicate.delivery/yhqm/HCYc7qQu2zZ0C5pSIfXG7zLEyK9bSLrWSd57JgHWVKJ2QOzJA/out-0.webp" ], "started_at": "2024-10-13T18:50:08.638193Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vafrg090kdrm40cjgwvbcnkk70", "cancel": "https://api.replicate.com/v1/predictions/vafrg090kdrm40cjgwvbcnkk70/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 43982 Prompt: p00h, white bear and tiger, game of chess in style of p00h [!] txt2img mode Using dev model free=8633805922304 Downloading weights 2024-10-13T18:50:08Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4q0bxlo2/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar 2024-10-13T18:50:10Z | INFO | [ Complete ] dest=/tmp/tmp4q0bxlo2/weights size="173 MB" total_elapsed=1.361s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar Downloaded weights in 1.47s Loaded LoRAs in 2.18s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.95it/s] 7%|▋ | 2/28 [00:00<00:07, 3.29it/s] 11%|█ | 3/28 [00:00<00:07, 3.13it/s] 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s] 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s] 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.99it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.98it/s] 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.97it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.97it/s] 43%|████▎ | 12/28 [00:03<00:05, 2.96it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s] 50%|█████ | 14/28 [00:04<00:04, 2.96it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s] 61%|██████ | 17/28 [00:05<00:03, 2.96it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.96it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.96it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.96it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.96it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.96it/s] 100%|██████████| 28/28 [00:09<00:00, 2.96it/s] 100%|██████████| 28/28 [00:09<00:00, 2.98it/s]
Prediction
sliday/pooh:327a4152ModelID03j456e3j5rm40cjgx0r4wa5scStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, angry bear with air balloon and bees
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 35
{ "model": "dev", "prompt": "p00h, angry bear with air balloon and bees", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, angry bear with air balloon and bees", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 35 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, angry bear with air balloon and bees", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, angry bear with air balloon and bees", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:02:23.542259Z", "created_at": "2024-10-13T19:01:27.057000Z", "data_removed": false, "error": null, "id": "03j456e3j5rm40cjgx0r4wa5sc", "input": { "model": "dev", "prompt": "p00h, angry bear with air balloon and bees", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 }, "logs": "Using seed: 9160\nPrompt: p00h, angry bear with air balloon and bees\n[!] txt2img mode\nUsing dev model\nLoaded LoRAs in 0.59s\n 0%| | 0/35 [00:00<?, ?it/s]\n 3%|▎ | 1/35 [00:00<00:11, 2.95it/s]\n 6%|▌ | 2/35 [00:00<00:10, 3.30it/s]\n 9%|▊ | 3/35 [00:00<00:10, 3.13it/s]\n 11%|█▏ | 4/35 [00:01<00:10, 3.06it/s]\n 14%|█▍ | 5/35 [00:01<00:09, 3.02it/s]\n 17%|█▋ | 6/35 [00:01<00:09, 3.00it/s]\n 20%|██ | 7/35 [00:02<00:09, 2.99it/s]\n 23%|██▎ | 8/35 [00:02<00:09, 2.98it/s]\n 26%|██▌ | 9/35 [00:02<00:08, 2.97it/s]\n 29%|██▊ | 10/35 [00:03<00:08, 2.97it/s]\n 31%|███▏ | 11/35 [00:03<00:08, 2.97it/s]\n 34%|███▍ | 12/35 [00:03<00:07, 2.96it/s]\n 37%|███▋ | 13/35 [00:04<00:07, 2.96it/s]\n 40%|████ | 14/35 [00:04<00:07, 2.96it/s]\n 43%|████▎ | 15/35 [00:05<00:06, 2.96it/s]\n 46%|████▌ | 16/35 [00:05<00:06, 2.96it/s]\n 49%|████▊ | 17/35 [00:05<00:06, 2.96it/s]\n 51%|█████▏ | 18/35 [00:06<00:05, 2.96it/s]\n 54%|█████▍ | 19/35 [00:06<00:05, 2.96it/s]\n 57%|█████▋ | 20/35 [00:06<00:05, 2.96it/s]\n 60%|██████ | 21/35 [00:07<00:04, 2.96it/s]\n 63%|██████▎ | 22/35 [00:07<00:04, 2.96it/s]\n 66%|██████▌ | 23/35 [00:07<00:04, 2.96it/s]\n 69%|██████▊ | 24/35 [00:08<00:03, 2.96it/s]\n 71%|███████▏ | 25/35 [00:08<00:03, 2.96it/s]\n 74%|███████▍ | 26/35 [00:08<00:03, 2.96it/s]\n 77%|███████▋ | 27/35 [00:09<00:02, 2.96it/s]\n 80%|████████ | 28/35 [00:09<00:02, 2.96it/s]\n 83%|████████▎ | 29/35 [00:09<00:02, 2.96it/s]\n 86%|████████▌ | 30/35 [00:10<00:01, 2.96it/s]\n 89%|████████▊ | 31/35 [00:10<00:01, 2.96it/s]\n 91%|█████████▏| 32/35 [00:10<00:01, 2.96it/s]\n 94%|█████████▍| 33/35 [00:11<00:00, 2.96it/s]\n 97%|█████████▋| 34/35 [00:11<00:00, 2.96it/s]\n100%|██████████| 35/35 [00:11<00:00, 2.96it/s]\n100%|██████████| 35/35 [00:11<00:00, 2.97it/s]", "metrics": { "predict_time": 12.69454344, "total_time": 56.485259 }, "output": [ "https://replicate.delivery/yhqm/AxvZtkq1VJL5JZnbrkCHjMed1v6aaPvdcZZahnQYrbefZ5MnA/out-0.webp" ], "started_at": "2024-10-13T19:02:10.847716Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/03j456e3j5rm40cjgx0r4wa5sc", "cancel": "https://api.replicate.com/v1/predictions/03j456e3j5rm40cjgx0r4wa5sc/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 9160 Prompt: p00h, angry bear with air balloon and bees [!] txt2img mode Using dev model Loaded LoRAs in 0.59s 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:00<00:11, 2.95it/s] 6%|▌ | 2/35 [00:00<00:10, 3.30it/s] 9%|▊ | 3/35 [00:00<00:10, 3.13it/s] 11%|█▏ | 4/35 [00:01<00:10, 3.06it/s] 14%|█▍ | 5/35 [00:01<00:09, 3.02it/s] 17%|█▋ | 6/35 [00:01<00:09, 3.00it/s] 20%|██ | 7/35 [00:02<00:09, 2.99it/s] 23%|██▎ | 8/35 [00:02<00:09, 2.98it/s] 26%|██▌ | 9/35 [00:02<00:08, 2.97it/s] 29%|██▊ | 10/35 [00:03<00:08, 2.97it/s] 31%|███▏ | 11/35 [00:03<00:08, 2.97it/s] 34%|███▍ | 12/35 [00:03<00:07, 2.96it/s] 37%|███▋ | 13/35 [00:04<00:07, 2.96it/s] 40%|████ | 14/35 [00:04<00:07, 2.96it/s] 43%|████▎ | 15/35 [00:05<00:06, 2.96it/s] 46%|████▌ | 16/35 [00:05<00:06, 2.96it/s] 49%|████▊ | 17/35 [00:05<00:06, 2.96it/s] 51%|█████▏ | 18/35 [00:06<00:05, 2.96it/s] 54%|█████▍ | 19/35 [00:06<00:05, 2.96it/s] 57%|█████▋ | 20/35 [00:06<00:05, 2.96it/s] 60%|██████ | 21/35 [00:07<00:04, 2.96it/s] 63%|██████▎ | 22/35 [00:07<00:04, 2.96it/s] 66%|██████▌ | 23/35 [00:07<00:04, 2.96it/s] 69%|██████▊ | 24/35 [00:08<00:03, 2.96it/s] 71%|███████▏ | 25/35 [00:08<00:03, 2.96it/s] 74%|███████▍ | 26/35 [00:08<00:03, 2.96it/s] 77%|███████▋ | 27/35 [00:09<00:02, 2.96it/s] 80%|████████ | 28/35 [00:09<00:02, 2.96it/s] 83%|████████▎ | 29/35 [00:09<00:02, 2.96it/s] 86%|████████▌ | 30/35 [00:10<00:01, 2.96it/s] 89%|████████▊ | 31/35 [00:10<00:01, 2.96it/s] 91%|█████████▏| 32/35 [00:10<00:01, 2.96it/s] 94%|█████████▍| 33/35 [00:11<00:00, 2.96it/s] 97%|█████████▋| 34/35 [00:11<00:00, 2.96it/s] 100%|██████████| 35/35 [00:11<00:00, 2.96it/s] 100%|██████████| 35/35 [00:11<00:00, 2.97it/s]
Prediction
sliday/pooh:327a4152ModelIDpt74k33cz5rm20cjgx2r06k87wStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, white bear and brown bear playing with sticks in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "model": "dev", "prompt": "p00h, white bear and brown bear playing with sticks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, white bear and brown bear playing with sticks in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, white bear and brown bear playing with sticks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, white bear and brown bear playing with sticks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:05:50.671211Z", "created_at": "2024-10-13T19:05:27.033000Z", "data_removed": false, "error": null, "id": "pt74k33cz5rm20cjgx2r06k87w", "input": { "model": "dev", "prompt": "p00h, white bear and brown bear playing with sticks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 4055\nPrompt: p00h, white bear and brown bear playing with sticks in style of p00h\n[!] txt2img mode\nUsing dev model\nfree=6665608224768\nDownloading weights\n2024-10-13T19:05:39Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4i1s80j4/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\n2024-10-13T19:05:40Z | INFO | [ Complete ] dest=/tmp/tmp4i1s80j4/weights size=\"173 MB\" total_elapsed=1.164s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\nDownloaded weights in 1.20s\nLoaded LoRAs in 1.94s\n 0%| | 0/28 [00:00<?, ?it/s]\n 4%|▎ | 1/28 [00:00<00:09, 2.95it/s]\n 7%|▋ | 2/28 [00:00<00:07, 3.30it/s]\n 11%|█ | 3/28 [00:00<00:07, 3.13it/s]\n 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s]\n 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s]\n 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s]\n 25%|██▌ | 7/28 [00:02<00:07, 2.98it/s]\n 29%|██▊ | 8/28 [00:02<00:06, 2.97it/s]\n 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s]\n 36%|███▌ | 10/28 [00:03<00:06, 2.96it/s]\n 39%|███▉ | 11/28 [00:03<00:05, 2.96it/s]\n 43%|████▎ | 12/28 [00:04<00:05, 2.96it/s]\n 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s]\n 50%|█████ | 14/28 [00:04<00:04, 2.96it/s]\n 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s]\n 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s]\n 61%|██████ | 17/28 [00:05<00:03, 2.95it/s]\n 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s]\n 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s]\n 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s]\n 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s]\n 79%|███████▊ | 22/28 [00:07<00:02, 2.95it/s]\n 82%|████████▏ | 23/28 [00:07<00:01, 2.95it/s]\n 86%|████████▌ | 24/28 [00:08<00:01, 2.95it/s]\n 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s]\n 93%|█████████▎| 26/28 [00:08<00:00, 2.95it/s]\n 96%|█████████▋| 27/28 [00:09<00:00, 2.95it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.95it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.97it/s]", "metrics": { "predict_time": 11.704360364, "total_time": 23.638211 }, "output": [ "https://replicate.delivery/yhqm/yeN8RubS6BQJQyGidvZHUjcBvXfEMisiK4EXKUOe3fM6AzZOB/out-0.webp" ], "started_at": "2024-10-13T19:05:38.966851Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/pt74k33cz5rm20cjgx2r06k87w", "cancel": "https://api.replicate.com/v1/predictions/pt74k33cz5rm20cjgx2r06k87w/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 4055 Prompt: p00h, white bear and brown bear playing with sticks in style of p00h [!] txt2img mode Using dev model free=6665608224768 Downloading weights 2024-10-13T19:05:39Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4i1s80j4/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar 2024-10-13T19:05:40Z | INFO | [ Complete ] dest=/tmp/tmp4i1s80j4/weights size="173 MB" total_elapsed=1.164s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar Downloaded weights in 1.20s Loaded LoRAs in 1.94s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.95it/s] 7%|▋ | 2/28 [00:00<00:07, 3.30it/s] 11%|█ | 3/28 [00:00<00:07, 3.13it/s] 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s] 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s] 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.98it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.97it/s] 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.96it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.96it/s] 43%|████▎ | 12/28 [00:04<00:05, 2.96it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s] 50%|█████ | 14/28 [00:04<00:04, 2.96it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s] 61%|██████ | 17/28 [00:05<00:03, 2.95it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.95it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.95it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.95it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.95it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.95it/s] 100%|██████████| 28/28 [00:09<00:00, 2.95it/s] 100%|██████████| 28/28 [00:09<00:00, 2.97it/s]
Prediction
sliday/pooh:327a4152ModelID9x7qykjrwhrm40cjgx3aefwm8wStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, rabbits playing with bricks in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "model": "dev", "prompt": "p00h, rabbits playing with bricks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, rabbits playing with bricks in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, rabbits playing with bricks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, rabbits playing with bricks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:06:37.947901Z", "created_at": "2024-10-13T19:06:27.428000Z", "data_removed": false, "error": null, "id": "9x7qykjrwhrm40cjgx3aefwm8w", "input": { "model": "dev", "prompt": "p00h, rabbits playing with bricks in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 31409\nPrompt: p00h, rabbits playing with bricks in style of p00h\n[!] txt2img mode\nUsing dev model\nLoaded LoRAs in 0.77s\n 0%| | 0/28 [00:00<?, ?it/s]\n 4%|▎ | 1/28 [00:00<00:09, 2.95it/s]\n 7%|▋ | 2/28 [00:00<00:07, 3.29it/s]\n 11%|█ | 3/28 [00:00<00:07, 3.13it/s]\n 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s]\n 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s]\n 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s]\n 25%|██▌ | 7/28 [00:02<00:07, 2.98it/s]\n 29%|██▊ | 8/28 [00:02<00:06, 2.97it/s]\n 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s]\n 36%|███▌ | 10/28 [00:03<00:06, 2.97it/s]\n 39%|███▉ | 11/28 [00:03<00:05, 2.96it/s]\n 43%|████▎ | 12/28 [00:04<00:05, 2.96it/s]\n 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s]\n 50%|█████ | 14/28 [00:04<00:04, 2.96it/s]\n 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s]\n 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s]\n 61%|██████ | 17/28 [00:05<00:03, 2.96it/s]\n 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s]\n 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s]\n 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s]\n 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s]\n 79%|███████▊ | 22/28 [00:07<00:02, 2.96it/s]\n 82%|████████▏ | 23/28 [00:07<00:01, 2.96it/s]\n 86%|████████▌ | 24/28 [00:08<00:01, 2.96it/s]\n 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s]\n 93%|█████████▎| 26/28 [00:08<00:00, 2.96it/s]\n 96%|█████████▋| 27/28 [00:09<00:00, 2.96it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.96it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.97it/s]", "metrics": { "predict_time": 10.51097278, "total_time": 10.519901 }, "output": [ "https://replicate.delivery/yhqm/WclRageyuAV5BCfhxnWv0zio6fJhu4QwJ4puuwlMr0v7h5MnA/out-0.webp" ], "started_at": "2024-10-13T19:06:27.436928Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/9x7qykjrwhrm40cjgx3aefwm8w", "cancel": "https://api.replicate.com/v1/predictions/9x7qykjrwhrm40cjgx3aefwm8w/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 31409 Prompt: p00h, rabbits playing with bricks in style of p00h [!] txt2img mode Using dev model Loaded LoRAs in 0.77s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.95it/s] 7%|▋ | 2/28 [00:00<00:07, 3.29it/s] 11%|█ | 3/28 [00:00<00:07, 3.13it/s] 14%|█▍ | 4/28 [00:01<00:07, 3.06it/s] 18%|█▊ | 5/28 [00:01<00:07, 3.02it/s] 21%|██▏ | 6/28 [00:01<00:07, 3.00it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.98it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.97it/s] 32%|███▏ | 9/28 [00:02<00:06, 2.97it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.97it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.96it/s] 43%|████▎ | 12/28 [00:04<00:05, 2.96it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.96it/s] 50%|█████ | 14/28 [00:04<00:04, 2.96it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.96it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.96it/s] 61%|██████ | 17/28 [00:05<00:03, 2.96it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.96it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.96it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.96it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.96it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.96it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.96it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.96it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.96it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.96it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.96it/s] 100%|██████████| 28/28 [00:09<00:00, 2.96it/s] 100%|██████████| 28/28 [00:09<00:00, 2.97it/s]
Prediction
sliday/pooh:327a4152ModelIDnzk8yv23w5rm20cjgx5r972by4StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, young boy character in a cafe, book illustration in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "image": "https://replicate.delivery/pbxt/LmzrtIDxaOtuIsJHsQg0ksWfBD8hmfde1ddmea9CimqP4RZV/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { image: "https://replicate.delivery/pbxt/LmzrtIDxaOtuIsJHsQg0ksWfBD8hmfde1ddmea9CimqP4RZV/IMG_6940.jpeg", model: "dev", prompt: "p00h, young boy character in a cafe, book illustration in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "image": "https://replicate.delivery/pbxt/LmzrtIDxaOtuIsJHsQg0ksWfBD8hmfde1ddmea9CimqP4RZV/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "image": "https://replicate.delivery/pbxt/LmzrtIDxaOtuIsJHsQg0ksWfBD8hmfde1ddmea9CimqP4RZV/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:12:01.790831Z", "created_at": "2024-10-13T19:11:49.729000Z", "data_removed": false, "error": null, "id": "nzk8yv23w5rm20cjgx5r972by4", "input": { "image": "https://replicate.delivery/pbxt/LmzrtIDxaOtuIsJHsQg0ksWfBD8hmfde1ddmea9CimqP4RZV/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 45858\nPrompt: p00h, young boy character in a cafe, book illustration in style of p00h\n[!] Resizing input image from 1024x1365 to 1024x1376\n[!] img2img mode\n[!] Using dev model for img2img\nUsing dev model\nLoaded LoRAs in 0.77s\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:08, 2.65it/s]\n 9%|▊ | 2/23 [00:00<00:08, 2.35it/s]\n 13%|█▎ | 3/23 [00:01<00:08, 2.27it/s]\n 17%|█▋ | 4/23 [00:01<00:08, 2.23it/s]\n 22%|██▏ | 5/23 [00:02<00:08, 2.22it/s]\n 26%|██▌ | 6/23 [00:02<00:07, 2.20it/s]\n 30%|███ | 7/23 [00:03<00:07, 2.20it/s]\n 35%|███▍ | 8/23 [00:03<00:06, 2.19it/s]\n 39%|███▉ | 9/23 [00:04<00:06, 2.19it/s]\n 43%|████▎ | 10/23 [00:04<00:05, 2.19it/s]\n 48%|████▊ | 11/23 [00:04<00:05, 2.18it/s]\n 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s]\n 57%|█████▋ | 13/23 [00:05<00:04, 2.18it/s]\n 61%|██████ | 14/23 [00:06<00:04, 2.18it/s]\n 65%|██████▌ | 15/23 [00:06<00:03, 2.18it/s]\n 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s]\n 74%|███████▍ | 17/23 [00:07<00:02, 2.18it/s]\n 78%|███████▊ | 18/23 [00:08<00:02, 2.18it/s]\n 83%|████████▎ | 19/23 [00:08<00:01, 2.18it/s]\n 87%|████████▋ | 20/23 [00:09<00:01, 2.18it/s]\n 91%|█████████▏| 21/23 [00:09<00:00, 2.18it/s]\n 96%|█████████▌| 22/23 [00:10<00:00, 2.18it/s]\n100%|██████████| 23/23 [00:10<00:00, 2.18it/s]\n100%|██████████| 23/23 [00:10<00:00, 2.20it/s]", "metrics": { "predict_time": 12.052602744, "total_time": 12.061831 }, "output": [ "https://replicate.delivery/yhqm/eNzEfkcYrGkj5018qvM7VbD3KW10bFxqGYt3RwEdZvvB2cmTA/out-0.webp" ], "started_at": "2024-10-13T19:11:49.738228Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/nzk8yv23w5rm20cjgx5r972by4", "cancel": "https://api.replicate.com/v1/predictions/nzk8yv23w5rm20cjgx5r972by4/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 45858 Prompt: p00h, young boy character in a cafe, book illustration in style of p00h [!] Resizing input image from 1024x1365 to 1024x1376 [!] img2img mode [!] Using dev model for img2img Using dev model Loaded LoRAs in 0.77s 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:08, 2.65it/s] 9%|▊ | 2/23 [00:00<00:08, 2.35it/s] 13%|█▎ | 3/23 [00:01<00:08, 2.27it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.23it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.22it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.20it/s] 30%|███ | 7/23 [00:03<00:07, 2.20it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.19it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.19it/s] 43%|████▎ | 10/23 [00:04<00:05, 2.19it/s] 48%|████▊ | 11/23 [00:04<00:05, 2.18it/s] 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.18it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.18it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.18it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.18it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.18it/s] 87%|████████▋ | 20/23 [00:09<00:01, 2.18it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.18it/s] 96%|█████████▌| 22/23 [00:10<00:00, 2.18it/s] 100%|██████████| 23/23 [00:10<00:00, 2.18it/s] 100%|██████████| 23/23 [00:10<00:00, 2.20it/s]
Prediction
sliday/pooh:327a4152ModelIDq5zthsqycxrm00cjgx6bgv4k88StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "image": "https://replicate.delivery/pbxt/Lmztgdpx9X4tssksSYX6JuWoEwdOKsmNgV2enA0VN3oqtEgi/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { image: "https://replicate.delivery/pbxt/Lmztgdpx9X4tssksSYX6JuWoEwdOKsmNgV2enA0VN3oqtEgi/IMG_6940.jpeg", model: "dev", prompt: "p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "image": "https://replicate.delivery/pbxt/Lmztgdpx9X4tssksSYX6JuWoEwdOKsmNgV2enA0VN3oqtEgi/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "image": "https://replicate.delivery/pbxt/Lmztgdpx9X4tssksSYX6JuWoEwdOKsmNgV2enA0VN3oqtEgi/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:14:06.439351Z", "created_at": "2024-10-13T19:13:43.015000Z", "data_removed": false, "error": null, "id": "q5zthsqycxrm00cjgx6bgv4k88", "input": { "image": "https://replicate.delivery/pbxt/Lmztgdpx9X4tssksSYX6JuWoEwdOKsmNgV2enA0VN3oqtEgi/IMG_6940.jpeg", "model": "dev", "prompt": "p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 52541\nPrompt: p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h\n[!] Resizing input image from 1024x1365 to 1024x1376\n[!] img2img mode\n[!] Using dev model for img2img\nUsing dev model\nLoaded LoRAs in 0.70s\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:08, 2.66it/s]\n 9%|▊ | 2/23 [00:00<00:08, 2.35it/s]\n 13%|█▎ | 3/23 [00:01<00:08, 2.27it/s]\n 17%|█▋ | 4/23 [00:01<00:08, 2.24it/s]\n 22%|██▏ | 5/23 [00:02<00:08, 2.22it/s]\n 26%|██▌ | 6/23 [00:02<00:07, 2.20it/s]\n 30%|███ | 7/23 [00:03<00:07, 2.20it/s]\n 35%|███▍ | 8/23 [00:03<00:06, 2.19it/s]\n 39%|███▉ | 9/23 [00:04<00:06, 2.19it/s]\n 43%|████▎ | 10/23 [00:04<00:05, 2.19it/s]\n 48%|████▊ | 11/23 [00:04<00:05, 2.18it/s]\n 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s]\n 57%|█████▋ | 13/23 [00:05<00:04, 2.18it/s]\n 61%|██████ | 14/23 [00:06<00:04, 2.18it/s]\n 65%|██████▌ | 15/23 [00:06<00:03, 2.18it/s]\n 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s]\n 74%|███████▍ | 17/23 [00:07<00:02, 2.18it/s]\n 78%|███████▊ | 18/23 [00:08<00:02, 2.18it/s]\n 83%|████████▎ | 19/23 [00:08<00:01, 2.18it/s]\n 87%|████████▋ | 20/23 [00:09<00:01, 2.18it/s]\n 91%|█████████▏| 21/23 [00:09<00:00, 2.18it/s]\n 96%|█████████▌| 22/23 [00:10<00:00, 2.18it/s]\n100%|██████████| 23/23 [00:10<00:00, 2.18it/s]\n100%|██████████| 23/23 [00:10<00:00, 2.20it/s]", "metrics": { "predict_time": 11.99352753, "total_time": 23.424351 }, "output": [ "https://replicate.delivery/yhqm/o4afID7v53ScCqF7IlQpq3LteBPTjg0gv4X4Eea6nTy9v5MnA/out-0.webp" ], "started_at": "2024-10-13T19:13:54.445823Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/q5zthsqycxrm00cjgx6bgv4k88", "cancel": "https://api.replicate.com/v1/predictions/q5zthsqycxrm00cjgx6bgv4k88/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 52541 Prompt: p00h, a european classic book illustration of a young boy character in a cafe, book illustration in style of p00h [!] Resizing input image from 1024x1365 to 1024x1376 [!] img2img mode [!] Using dev model for img2img Using dev model Loaded LoRAs in 0.70s 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:08, 2.66it/s] 9%|▊ | 2/23 [00:00<00:08, 2.35it/s] 13%|█▎ | 3/23 [00:01<00:08, 2.27it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.24it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.22it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.20it/s] 30%|███ | 7/23 [00:03<00:07, 2.20it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.19it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.19it/s] 43%|████▎ | 10/23 [00:04<00:05, 2.19it/s] 48%|████▊ | 11/23 [00:04<00:05, 2.18it/s] 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.18it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.18it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.18it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.18it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.18it/s] 87%|████████▋ | 20/23 [00:09<00:01, 2.18it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.18it/s] 96%|█████████▌| 22/23 [00:10<00:00, 2.18it/s] 100%|██████████| 23/23 [00:10<00:00, 2.18it/s] 100%|██████████| 23/23 [00:10<00:00, 2.20it/s]
Prediction
sliday/pooh:327a4152ModelIDn8kah76d71rm40cjgx9ab33b1mStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, a european book illustration of a bear with glass of wine
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 1:1
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 28
{ "model": "dev", "prompt": "p00h, a european book illustration of a bear with glass of wine", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, a european book illustration of a bear with glass of wine", lora_scale: 1, num_outputs: 1, aspect_ratio: "1:1", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 28 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, a european book illustration of a bear with glass of wine", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, a european book illustration of a bear with glass of wine", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:20:15.523288Z", "created_at": "2024-10-13T19:20:03.640000Z", "data_removed": false, "error": null, "id": "n8kah76d71rm40cjgx9ab33b1m", "input": { "model": "dev", "prompt": "p00h, a european book illustration of a bear with glass of wine", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 28 }, "logs": "Using seed: 50953\nPrompt: p00h, a european book illustration of a bear with glass of wine\n[!] txt2img mode\nUsing dev model\nfree=9279556395008\nDownloading weights\n2024-10-13T19:20:03Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpep8z06h8/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\n2024-10-13T19:20:04Z | INFO | [ Complete ] dest=/tmp/tmpep8z06h8/weights size=\"173 MB\" total_elapsed=1.107s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar\nDownloaded weights in 1.14s\nLoaded LoRAs in 1.89s\n 0%| | 0/28 [00:00<?, ?it/s]\n 4%|▎ | 1/28 [00:00<00:09, 2.88it/s]\n 7%|▋ | 2/28 [00:00<00:08, 3.22it/s]\n 11%|█ | 3/28 [00:00<00:08, 3.06it/s]\n 14%|█▍ | 4/28 [00:01<00:08, 2.99it/s]\n 18%|█▊ | 5/28 [00:01<00:07, 2.95it/s]\n 21%|██▏ | 6/28 [00:02<00:07, 2.93it/s]\n 25%|██▌ | 7/28 [00:02<00:07, 2.91it/s]\n 29%|██▊ | 8/28 [00:02<00:06, 2.91it/s]\n 32%|███▏ | 9/28 [00:03<00:06, 2.90it/s]\n 36%|███▌ | 10/28 [00:03<00:06, 2.89it/s]\n 39%|███▉ | 11/28 [00:03<00:05, 2.89it/s]\n 43%|████▎ | 12/28 [00:04<00:05, 2.89it/s]\n 46%|████▋ | 13/28 [00:04<00:05, 2.89it/s]\n 50%|█████ | 14/28 [00:04<00:04, 2.89it/s]\n 54%|█████▎ | 15/28 [00:05<00:04, 2.89it/s]\n 57%|█████▋ | 16/28 [00:05<00:04, 2.89it/s]\n 61%|██████ | 17/28 [00:05<00:03, 2.89it/s]\n 64%|██████▍ | 18/28 [00:06<00:03, 2.89it/s]\n 68%|██████▊ | 19/28 [00:06<00:03, 2.88it/s]\n 71%|███████▏ | 20/28 [00:06<00:02, 2.88it/s]\n 75%|███████▌ | 21/28 [00:07<00:02, 2.88it/s]\n 79%|███████▊ | 22/28 [00:07<00:02, 2.88it/s]\n 82%|████████▏ | 23/28 [00:07<00:01, 2.88it/s]\n 86%|████████▌ | 24/28 [00:08<00:01, 2.88it/s]\n 89%|████████▉ | 25/28 [00:08<00:01, 2.88it/s]\n 93%|█████████▎| 26/28 [00:08<00:00, 2.88it/s]\n 96%|█████████▋| 27/28 [00:09<00:00, 2.88it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.88it/s]\n100%|██████████| 28/28 [00:09<00:00, 2.90it/s]", "metrics": { "predict_time": 11.873435774, "total_time": 11.883288 }, "output": [ "https://replicate.delivery/yhqm/3x8SQEYY5aZpNdRqS6mjBfivmgiNbFgBTggyBZGlBgg3ecmTA/out-0.webp" ], "started_at": "2024-10-13T19:20:03.649852Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/n8kah76d71rm40cjgx9ab33b1m", "cancel": "https://api.replicate.com/v1/predictions/n8kah76d71rm40cjgx9ab33b1m/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 50953 Prompt: p00h, a european book illustration of a bear with glass of wine [!] txt2img mode Using dev model free=9279556395008 Downloading weights 2024-10-13T19:20:03Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpep8z06h8/weights url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar 2024-10-13T19:20:04Z | INFO | [ Complete ] dest=/tmp/tmpep8z06h8/weights size="173 MB" total_elapsed=1.107s url=https://replicate.delivery/yhqm/JG4gFPubJA5jJh7ba5TnKn4e3aHlfI3e4IRswWlkeNFo7uZOB/trained_model.tar Downloaded weights in 1.14s Loaded LoRAs in 1.89s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.88it/s] 7%|▋ | 2/28 [00:00<00:08, 3.22it/s] 11%|█ | 3/28 [00:00<00:08, 3.06it/s] 14%|█▍ | 4/28 [00:01<00:08, 2.99it/s] 18%|█▊ | 5/28 [00:01<00:07, 2.95it/s] 21%|██▏ | 6/28 [00:02<00:07, 2.93it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.91it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.91it/s] 32%|███▏ | 9/28 [00:03<00:06, 2.90it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.89it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.89it/s] 43%|████▎ | 12/28 [00:04<00:05, 2.89it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.89it/s] 50%|█████ | 14/28 [00:04<00:04, 2.89it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.89it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.89it/s] 61%|██████ | 17/28 [00:05<00:03, 2.89it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.89it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.88it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.88it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.88it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.88it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.88it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.88it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.88it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.88it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.88it/s] 100%|██████████| 28/28 [00:09<00:00, 2.88it/s] 100%|██████████| 28/28 [00:09<00:00, 2.90it/s]
Prediction
sliday/pooh:327a4152ModelIDrvakvkdh0drm00cjgx9rbbz36mStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- model
- dev
- prompt
- p00h, a european book illustration of a bear with bottle of lemonade
- lora_scale
- 1
- num_outputs
- 1
- aspect_ratio
- 3:2
- output_format
- webp
- guidance_scale
- 3.5
- output_quality
- 90
- prompt_strength
- 0.8
- extra_lora_scale
- 1
- num_inference_steps
- 35
{ "model": "dev", "prompt": "p00h, a european book illustration of a bear with bottle of lemonade", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 }
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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", { input: { model: "dev", prompt: "p00h, a european book illustration of a bear with bottle of lemonade", lora_scale: 1, num_outputs: 1, aspect_ratio: "3:2", output_format: "webp", guidance_scale: 3.5, output_quality: 90, prompt_strength: 0.8, extra_lora_scale: 1, num_inference_steps: 35 } } ); 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 sliday/pooh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "sliday/pooh:327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", input={ "model": "dev", "prompt": "p00h, a european book illustration of a bear with bottle of lemonade", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 } ) 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 sliday/pooh 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": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23", "input": { "model": "dev", "prompt": "p00h, a european book illustration of a bear with bottle of lemonade", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-13T19:21:14.721673Z", "created_at": "2024-10-13T19:21:01.955000Z", "data_removed": false, "error": null, "id": "rvakvkdh0drm00cjgx9rbbz36m", "input": { "model": "dev", "prompt": "p00h, a european book illustration of a bear with bottle of lemonade", "lora_scale": 1, "num_outputs": 1, "aspect_ratio": "3:2", "output_format": "webp", "guidance_scale": 3.5, "output_quality": 90, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 35 }, "logs": "Using seed: 46222\nPrompt: p00h, a european book illustration of a bear with bottle of lemonade\n[!] txt2img mode\nUsing dev model\nLoaded LoRAs in 0.69s\n 0%| | 0/35 [00:00<?, ?it/s]\n 3%|▎ | 1/35 [00:00<00:11, 2.97it/s]\n 6%|▌ | 2/35 [00:00<00:09, 3.31it/s]\n 9%|▊ | 3/35 [00:00<00:10, 3.15it/s]\n 11%|█▏ | 4/35 [00:01<00:10, 3.07it/s]\n 14%|█▍ | 5/35 [00:01<00:09, 3.03it/s]\n 17%|█▋ | 6/35 [00:01<00:09, 3.01it/s]\n 20%|██ | 7/35 [00:02<00:09, 3.00it/s]\n 23%|██▎ | 8/35 [00:02<00:09, 2.99it/s]\n 26%|██▌ | 9/35 [00:02<00:08, 2.98it/s]\n 29%|██▊ | 10/35 [00:03<00:08, 2.98it/s]\n 31%|███▏ | 11/35 [00:03<00:08, 2.97it/s]\n 34%|███▍ | 12/35 [00:03<00:07, 2.97it/s]\n 37%|███▋ | 13/35 [00:04<00:07, 2.97it/s]\n 40%|████ | 14/35 [00:04<00:07, 2.97it/s]\n 43%|████▎ | 15/35 [00:04<00:06, 2.97it/s]\n 46%|████▌ | 16/35 [00:05<00:06, 2.97it/s]\n 49%|████▊ | 17/35 [00:05<00:06, 2.97it/s]\n 51%|█████▏ | 18/35 [00:06<00:05, 2.97it/s]\n 54%|█████▍ | 19/35 [00:06<00:05, 2.97it/s]\n 57%|█████▋ | 20/35 [00:06<00:05, 2.97it/s]\n 60%|██████ | 21/35 [00:07<00:04, 2.97it/s]\n 63%|██████▎ | 22/35 [00:07<00:04, 2.97it/s]\n 66%|██████▌ | 23/35 [00:07<00:04, 2.97it/s]\n 69%|██████▊ | 24/35 [00:08<00:03, 2.97it/s]\n 71%|███████▏ | 25/35 [00:08<00:03, 2.97it/s]\n 74%|███████▍ | 26/35 [00:08<00:03, 2.97it/s]\n 77%|███████▋ | 27/35 [00:09<00:02, 2.97it/s]\n 80%|████████ | 28/35 [00:09<00:02, 2.97it/s]\n 83%|████████▎ | 29/35 [00:09<00:02, 2.97it/s]\n 86%|████████▌ | 30/35 [00:10<00:01, 2.97it/s]\n 89%|████████▊ | 31/35 [00:10<00:01, 2.97it/s]\n 91%|█████████▏| 32/35 [00:10<00:01, 2.97it/s]\n 94%|█████████▍| 33/35 [00:11<00:00, 2.97it/s]\n 97%|█████████▋| 34/35 [00:11<00:00, 2.97it/s]\n100%|██████████| 35/35 [00:11<00:00, 2.97it/s]\n100%|██████████| 35/35 [00:11<00:00, 2.98it/s]", "metrics": { "predict_time": 12.759992087, "total_time": 12.766673 }, "output": [ "https://replicate.delivery/yhqm/nbpugIkqDJoeYSHM3Kafbo2d8eY4M7OUzmNSkyh2B9VU95MnA/out-0.webp" ], "started_at": "2024-10-13T19:21:01.961681Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rvakvkdh0drm00cjgx9rbbz36m", "cancel": "https://api.replicate.com/v1/predictions/rvakvkdh0drm00cjgx9rbbz36m/cancel" }, "version": "327a4152a80ceae280c8f84532d91f003fdc2c78810144734f314b0101a70b23" }
Generated inUsing seed: 46222 Prompt: p00h, a european book illustration of a bear with bottle of lemonade [!] txt2img mode Using dev model Loaded LoRAs in 0.69s 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:00<00:11, 2.97it/s] 6%|▌ | 2/35 [00:00<00:09, 3.31it/s] 9%|▊ | 3/35 [00:00<00:10, 3.15it/s] 11%|█▏ | 4/35 [00:01<00:10, 3.07it/s] 14%|█▍ | 5/35 [00:01<00:09, 3.03it/s] 17%|█▋ | 6/35 [00:01<00:09, 3.01it/s] 20%|██ | 7/35 [00:02<00:09, 3.00it/s] 23%|██▎ | 8/35 [00:02<00:09, 2.99it/s] 26%|██▌ | 9/35 [00:02<00:08, 2.98it/s] 29%|██▊ | 10/35 [00:03<00:08, 2.98it/s] 31%|███▏ | 11/35 [00:03<00:08, 2.97it/s] 34%|███▍ | 12/35 [00:03<00:07, 2.97it/s] 37%|███▋ | 13/35 [00:04<00:07, 2.97it/s] 40%|████ | 14/35 [00:04<00:07, 2.97it/s] 43%|████▎ | 15/35 [00:04<00:06, 2.97it/s] 46%|████▌ | 16/35 [00:05<00:06, 2.97it/s] 49%|████▊ | 17/35 [00:05<00:06, 2.97it/s] 51%|█████▏ | 18/35 [00:06<00:05, 2.97it/s] 54%|█████▍ | 19/35 [00:06<00:05, 2.97it/s] 57%|█████▋ | 20/35 [00:06<00:05, 2.97it/s] 60%|██████ | 21/35 [00:07<00:04, 2.97it/s] 63%|██████▎ | 22/35 [00:07<00:04, 2.97it/s] 66%|██████▌ | 23/35 [00:07<00:04, 2.97it/s] 69%|██████▊ | 24/35 [00:08<00:03, 2.97it/s] 71%|███████▏ | 25/35 [00:08<00:03, 2.97it/s] 74%|███████▍ | 26/35 [00:08<00:03, 2.97it/s] 77%|███████▋ | 27/35 [00:09<00:02, 2.97it/s] 80%|████████ | 28/35 [00:09<00:02, 2.97it/s] 83%|████████▎ | 29/35 [00:09<00:02, 2.97it/s] 86%|████████▌ | 30/35 [00:10<00:01, 2.97it/s] 89%|████████▊ | 31/35 [00:10<00:01, 2.97it/s] 91%|█████████▏| 32/35 [00:10<00:01, 2.97it/s] 94%|█████████▍| 33/35 [00:11<00:00, 2.97it/s] 97%|█████████▋| 34/35 [00:11<00:00, 2.97it/s] 100%|██████████| 35/35 [00:11<00:00, 2.97it/s] 100%|██████████| 35/35 [00:11<00:00, 2.98it/s]
Want to make some of these yourself?
Run this model