adithram / inkpunk-diffusion
Replicate port of https://huggingface.co/Envvi/Inkpunk-Diffusion. Finetuned Stable Diffusion model trained on dreambooth. Vaguely inspired by Gorillaz, FLCL, and Yoji Shinkawa.
- Public
- 3.4K runs
-
A100 (80GB)
Prediction
adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1IDe5fkmdnkvna7tkq6grmozznjseStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- "512"
- height
- "512"
- prompt
- a photo of an astronaut riding a horse on mars nvinkpunk
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": "512", "height": "512", "prompt": "a photo of an astronaut riding a horse on mars nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", { input: { width: "512", height: "512", prompt: "a photo of an astronaut riding a horse on mars nvinkpunk", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", input={ "width": "512", "height": "512", "prompt": "a photo of an astronaut riding a horse on mars nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run adithram/inkpunk-diffusion 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": "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", "input": { "width": "512", "height": "512", "prompt": "a photo of an astronaut riding a horse on mars nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-03-15T14:53:03.249089Z", "created_at": "2023-03-15T14:52:57.271567Z", "data_removed": false, "error": null, "id": "e5fkmdnkvna7tkq6grmozznjse", "input": { "width": "512", "height": "512", "prompt": "a photo of an astronaut riding a horse on mars nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 10617\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:06, 8.16it/s]\n 4%|▍ | 2/50 [00:00<00:05, 8.42it/s]\n 8%|▊ | 4/50 [00:00<00:04, 9.46it/s]\n 12%|█▏ | 6/50 [00:00<00:04, 9.79it/s]\n 16%|█▌ | 8/50 [00:00<00:04, 9.93it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.92it/s]\n 22%|██▏ | 11/50 [00:01<00:03, 10.02it/s]\n 26%|██▌ | 13/50 [00:01<00:03, 10.09it/s]\n 30%|███ | 15/50 [00:01<00:03, 10.11it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 10.13it/s]\n 38%|███▊ | 19/50 [00:01<00:03, 10.16it/s]\n 42%|████▏ | 21/50 [00:02<00:02, 10.17it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 10.08it/s]\n 50%|█████ | 25/50 [00:02<00:02, 10.12it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 10.14it/s]\n 58%|█████▊ | 29/50 [00:02<00:02, 10.15it/s]\n 62%|██████▏ | 31/50 [00:03<00:01, 10.16it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 10.16it/s]\n 70%|███████ | 35/50 [00:03<00:01, 10.17it/s]\n 74%|███████▍ | 37/50 [00:03<00:01, 10.17it/s]\n 78%|███████▊ | 39/50 [00:03<00:01, 10.17it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 10.18it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 10.20it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 10.20it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 10.19it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 10.19it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.08it/s]", "metrics": { "predict_time": 5.901691, "total_time": 5.977522 }, "output": [ "https://replicate.delivery/pbxt/Vzni8TCl2CatNVDtTAsPJ6IxNBcgU2Y8Nn9KzseWW6Enb8TIA/out-0.png" ], "started_at": "2023-03-15T14:52:57.347398Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/e5fkmdnkvna7tkq6grmozznjse", "cancel": "https://api.replicate.com/v1/predictions/e5fkmdnkvna7tkq6grmozznjse/cancel" }, "version": "780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1" }Generated inUsing seed: 10617 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:06, 8.16it/s] 4%|▍ | 2/50 [00:00<00:05, 8.42it/s] 8%|▊ | 4/50 [00:00<00:04, 9.46it/s] 12%|█▏ | 6/50 [00:00<00:04, 9.79it/s] 16%|█▌ | 8/50 [00:00<00:04, 9.93it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.92it/s] 22%|██▏ | 11/50 [00:01<00:03, 10.02it/s] 26%|██▌ | 13/50 [00:01<00:03, 10.09it/s] 30%|███ | 15/50 [00:01<00:03, 10.11it/s] 34%|███▍ | 17/50 [00:01<00:03, 10.13it/s] 38%|███▊ | 19/50 [00:01<00:03, 10.16it/s] 42%|████▏ | 21/50 [00:02<00:02, 10.17it/s] 46%|████▌ | 23/50 [00:02<00:02, 10.08it/s] 50%|█████ | 25/50 [00:02<00:02, 10.12it/s] 54%|█████▍ | 27/50 [00:02<00:02, 10.14it/s] 58%|█████▊ | 29/50 [00:02<00:02, 10.15it/s] 62%|██████▏ | 31/50 [00:03<00:01, 10.16it/s] 66%|██████▌ | 33/50 [00:03<00:01, 10.16it/s] 70%|███████ | 35/50 [00:03<00:01, 10.17it/s] 74%|███████▍ | 37/50 [00:03<00:01, 10.17it/s] 78%|███████▊ | 39/50 [00:03<00:01, 10.17it/s] 82%|████████▏ | 41/50 [00:04<00:00, 10.18it/s] 86%|████████▌ | 43/50 [00:04<00:00, 10.20it/s] 90%|█████████ | 45/50 [00:04<00:00, 10.20it/s] 94%|█████████▍| 47/50 [00:04<00:00, 10.19it/s] 98%|█████████▊| 49/50 [00:04<00:00, 10.19it/s] 100%|██████████| 50/50 [00:04<00:00, 10.08it/s]Prediction
adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1Input
- width
- "512"
- height
- "512"
- prompt
- rocket ship in deep space nvinkpunk
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": "512", "height": "512", "prompt": "rocket ship in deep space nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", { input: { width: "512", height: "512", prompt: "rocket ship in deep space nvinkpunk", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", input={ "width": "512", "height": "512", "prompt": "rocket ship in deep space nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run adithram/inkpunk-diffusion 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": "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", "input": { "width": "512", "height": "512", "prompt": "rocket ship in deep space nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-03-15T14:56:58.859530Z", "created_at": "2023-03-15T14:56:52.896920Z", "data_removed": false, "error": null, "id": "bfqmzjs5zjd4rf7gzpe6nmjk2a", "input": { "width": "512", "height": "512", "prompt": "rocket ship in deep space nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 59494\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:05, 8.32it/s]\n 6%|▌ | 3/50 [00:00<00:04, 9.63it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.92it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 10.05it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 10.10it/s]\n 22%|██▏ | 11/50 [00:01<00:03, 10.13it/s]\n 26%|██▌ | 13/50 [00:01<00:03, 10.14it/s]\n 30%|███ | 15/50 [00:01<00:03, 10.17it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 10.17it/s]\n 38%|███▊ | 19/50 [00:01<00:03, 10.16it/s]\n 42%|████▏ | 21/50 [00:02<00:02, 10.17it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 10.17it/s]\n 50%|█████ | 25/50 [00:02<00:02, 10.18it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 10.19it/s]\n 58%|█████▊ | 29/50 [00:02<00:02, 10.19it/s]\n 62%|██████▏ | 31/50 [00:03<00:01, 10.18it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 10.18it/s]\n 70%|███████ | 35/50 [00:03<00:01, 10.17it/s]\n 74%|███████▍ | 37/50 [00:03<00:01, 10.19it/s]\n 78%|███████▊ | 39/50 [00:03<00:01, 10.20it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 10.19it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 10.19it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 10.19it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 10.19it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 10.20it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.14it/s]", "metrics": { "predict_time": 5.888449, "total_time": 5.96261 }, "output": [ "https://replicate.delivery/pbxt/TUatncdkaxpPKVPCZxeSlLXa2R9iFfmreUjK4mTedCkorjfEC/out-0.png" ], "started_at": "2023-03-15T14:56:52.971081Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bfqmzjs5zjd4rf7gzpe6nmjk2a", "cancel": "https://api.replicate.com/v1/predictions/bfqmzjs5zjd4rf7gzpe6nmjk2a/cancel" }, "version": "780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1" }Generated inUsing seed: 59494 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:05, 8.32it/s] 6%|▌ | 3/50 [00:00<00:04, 9.63it/s] 10%|█ | 5/50 [00:00<00:04, 9.92it/s] 14%|█▍ | 7/50 [00:00<00:04, 10.05it/s] 18%|█▊ | 9/50 [00:00<00:04, 10.10it/s] 22%|██▏ | 11/50 [00:01<00:03, 10.13it/s] 26%|██▌ | 13/50 [00:01<00:03, 10.14it/s] 30%|███ | 15/50 [00:01<00:03, 10.17it/s] 34%|███▍ | 17/50 [00:01<00:03, 10.17it/s] 38%|███▊ | 19/50 [00:01<00:03, 10.16it/s] 42%|████▏ | 21/50 [00:02<00:02, 10.17it/s] 46%|████▌ | 23/50 [00:02<00:02, 10.17it/s] 50%|█████ | 25/50 [00:02<00:02, 10.18it/s] 54%|█████▍ | 27/50 [00:02<00:02, 10.19it/s] 58%|█████▊ | 29/50 [00:02<00:02, 10.19it/s] 62%|██████▏ | 31/50 [00:03<00:01, 10.18it/s] 66%|██████▌ | 33/50 [00:03<00:01, 10.18it/s] 70%|███████ | 35/50 [00:03<00:01, 10.17it/s] 74%|███████▍ | 37/50 [00:03<00:01, 10.19it/s] 78%|███████▊ | 39/50 [00:03<00:01, 10.20it/s] 82%|████████▏ | 41/50 [00:04<00:00, 10.19it/s] 86%|████████▌ | 43/50 [00:04<00:00, 10.19it/s] 90%|█████████ | 45/50 [00:04<00:00, 10.19it/s] 94%|█████████▍| 47/50 [00:04<00:00, 10.19it/s] 98%|█████████▊| 49/50 [00:04<00:00, 10.20it/s] 100%|██████████| 50/50 [00:04<00:00, 10.14it/s]Prediction
adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1IDfr73fn4fmnhrddkfiryw77ggaeStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- "512"
- height
- "512"
- prompt
- lone soldier in a post apocalyptic city street nvinkpunk
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": "512", "height": "512", "prompt": "lone soldier in a post apocalyptic city street nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", { input: { width: "512", height: "512", prompt: "lone soldier in a post apocalyptic city street nvinkpunk", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", input={ "width": "512", "height": "512", "prompt": "lone soldier in a post apocalyptic city street nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run adithram/inkpunk-diffusion 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": "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", "input": { "width": "512", "height": "512", "prompt": "lone soldier in a post apocalyptic city street nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-03-15T14:52:41.154427Z", "created_at": "2023-03-15T14:52:35.096842Z", "data_removed": false, "error": null, "id": "fr73fn4fmnhrddkfiryw77ggae", "input": { "width": "512", "height": "512", "prompt": "lone soldier in a post apocalyptic city street nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 27239\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:06, 7.84it/s]\n 4%|▍ | 2/50 [00:00<00:05, 8.01it/s]\n 6%|▌ | 3/50 [00:00<00:05, 8.70it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.43it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 9.74it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.90it/s]\n 22%|██▏ | 11/50 [00:01<00:03, 9.99it/s]\n 26%|██▌ | 13/50 [00:01<00:03, 10.05it/s]\n 30%|███ | 15/50 [00:01<00:03, 10.08it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 10.10it/s]\n 38%|███▊ | 19/50 [00:01<00:03, 10.13it/s]\n 42%|████▏ | 21/50 [00:02<00:02, 10.14it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 10.14it/s]\n 50%|█████ | 25/50 [00:02<00:02, 10.14it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 10.14it/s]\n 58%|█████▊ | 29/50 [00:02<00:02, 10.15it/s]\n 62%|██████▏ | 31/50 [00:03<00:01, 10.15it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 10.16it/s]\n 70%|███████ | 35/50 [00:03<00:01, 10.15it/s]\n 74%|███████▍ | 37/50 [00:03<00:01, 10.14it/s]\n 78%|███████▊ | 39/50 [00:03<00:01, 10.15it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 10.14it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 10.14it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 10.13it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 10.13it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 10.13it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.02it/s]", "metrics": { "predict_time": 5.970233, "total_time": 6.057585 }, "output": [ "https://replicate.delivery/pbxt/dxf6penvKmh1okgMgyMcrWI54PcCkfe75BX5WgzQUhRjbjfEC/out-0.png" ], "started_at": "2023-03-15T14:52:35.184194Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fr73fn4fmnhrddkfiryw77ggae", "cancel": "https://api.replicate.com/v1/predictions/fr73fn4fmnhrddkfiryw77ggae/cancel" }, "version": "780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1" }Generated inUsing seed: 27239 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:06, 7.84it/s] 4%|▍ | 2/50 [00:00<00:05, 8.01it/s] 6%|▌ | 3/50 [00:00<00:05, 8.70it/s] 10%|█ | 5/50 [00:00<00:04, 9.43it/s] 14%|█▍ | 7/50 [00:00<00:04, 9.74it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.90it/s] 22%|██▏ | 11/50 [00:01<00:03, 9.99it/s] 26%|██▌ | 13/50 [00:01<00:03, 10.05it/s] 30%|███ | 15/50 [00:01<00:03, 10.08it/s] 34%|███▍ | 17/50 [00:01<00:03, 10.10it/s] 38%|███▊ | 19/50 [00:01<00:03, 10.13it/s] 42%|████▏ | 21/50 [00:02<00:02, 10.14it/s] 46%|████▌ | 23/50 [00:02<00:02, 10.14it/s] 50%|█████ | 25/50 [00:02<00:02, 10.14it/s] 54%|█████▍ | 27/50 [00:02<00:02, 10.14it/s] 58%|█████▊ | 29/50 [00:02<00:02, 10.15it/s] 62%|██████▏ | 31/50 [00:03<00:01, 10.15it/s] 66%|██████▌ | 33/50 [00:03<00:01, 10.16it/s] 70%|███████ | 35/50 [00:03<00:01, 10.15it/s] 74%|███████▍ | 37/50 [00:03<00:01, 10.14it/s] 78%|███████▊ | 39/50 [00:03<00:01, 10.15it/s] 82%|████████▏ | 41/50 [00:04<00:00, 10.14it/s] 86%|████████▌ | 43/50 [00:04<00:00, 10.14it/s] 90%|█████████ | 45/50 [00:04<00:00, 10.13it/s] 94%|█████████▍| 47/50 [00:04<00:00, 10.13it/s] 98%|█████████▊| 49/50 [00:04<00:00, 10.13it/s] 100%|██████████| 50/50 [00:04<00:00, 10.02it/s]Prediction
adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1IDxzn3p64jdzgu5l6pjv366hzxg4StatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- "512"
- height
- "512"
- prompt
- DJ on stage with large crowd in front of the disc jockey nvinkpunk
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": "512", "height": "512", "prompt": "DJ on stage with large crowd in front of the disc jockey nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", { input: { width: "512", height: "512", prompt: "DJ on stage with large crowd in front of the disc jockey nvinkpunk", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun adithram/inkpunk-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", input={ "width": "512", "height": "512", "prompt": "DJ on stage with large crowd in front of the disc jockey nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run adithram/inkpunk-diffusion 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": "adithram/inkpunk-diffusion:780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1", "input": { "width": "512", "height": "512", "prompt": "DJ on stage with large crowd in front of the disc jockey nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-03-15T14:54:51.456230Z", "created_at": "2023-03-15T14:54:45.367731Z", "data_removed": false, "error": null, "id": "xzn3p64jdzgu5l6pjv366hzxg4", "input": { "width": "512", "height": "512", "prompt": "DJ on stage with large crowd in front of the disc jockey nvinkpunk", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 8633\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:06, 8.11it/s]\n 4%|▍ | 2/50 [00:00<00:05, 8.44it/s]\n 8%|▊ | 4/50 [00:00<00:04, 9.39it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.56it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 9.78it/s]\n 16%|█▌ | 8/50 [00:00<00:04, 9.81it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.83it/s]\n 22%|██▏ | 11/50 [00:01<00:03, 9.96it/s]\n 24%|██▍ | 12/50 [00:01<00:03, 9.87it/s]\n 26%|██▌ | 13/50 [00:01<00:03, 9.87it/s]\n 30%|███ | 15/50 [00:01<00:03, 9.96it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 9.96it/s]\n 38%|███▊ | 19/50 [00:01<00:03, 10.02it/s]\n 42%|████▏ | 21/50 [00:02<00:02, 10.07it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 10.09it/s]\n 50%|█████ | 25/50 [00:02<00:02, 10.10it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 10.07it/s]\n 58%|█████▊ | 29/50 [00:02<00:02, 10.10it/s]\n 62%|██████▏ | 31/50 [00:03<00:01, 10.12it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 10.12it/s]\n 70%|███████ | 35/50 [00:03<00:01, 10.14it/s]\n 74%|███████▍ | 37/50 [00:03<00:01, 10.12it/s]\n 78%|███████▊ | 39/50 [00:03<00:01, 10.12it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 10.14it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 10.13it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 10.14it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 10.12it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 10.13it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.00it/s]", "metrics": { "predict_time": 6.010374, "total_time": 6.088499 }, "output": [ "https://replicate.delivery/pbxt/Jp05MqnemayQZizMpC2KhoV2MOjgYfsMopYSQGObYdp644nQA/out-0.png" ], "started_at": "2023-03-15T14:54:45.445856Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xzn3p64jdzgu5l6pjv366hzxg4", "cancel": "https://api.replicate.com/v1/predictions/xzn3p64jdzgu5l6pjv366hzxg4/cancel" }, "version": "780769de0312a5f8afd675d385d9ca06883112268b7d2724a79d9f9f96bfbbe1" }Generated inUsing seed: 8633 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:06, 8.11it/s] 4%|▍ | 2/50 [00:00<00:05, 8.44it/s] 8%|▊ | 4/50 [00:00<00:04, 9.39it/s] 10%|█ | 5/50 [00:00<00:04, 9.56it/s] 14%|█▍ | 7/50 [00:00<00:04, 9.78it/s] 16%|█▌ | 8/50 [00:00<00:04, 9.81it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.83it/s] 22%|██▏ | 11/50 [00:01<00:03, 9.96it/s] 24%|██▍ | 12/50 [00:01<00:03, 9.87it/s] 26%|██▌ | 13/50 [00:01<00:03, 9.87it/s] 30%|███ | 15/50 [00:01<00:03, 9.96it/s] 34%|███▍ | 17/50 [00:01<00:03, 9.96it/s] 38%|███▊ | 19/50 [00:01<00:03, 10.02it/s] 42%|████▏ | 21/50 [00:02<00:02, 10.07it/s] 46%|████▌ | 23/50 [00:02<00:02, 10.09it/s] 50%|█████ | 25/50 [00:02<00:02, 10.10it/s] 54%|█████▍ | 27/50 [00:02<00:02, 10.07it/s] 58%|█████▊ | 29/50 [00:02<00:02, 10.10it/s] 62%|██████▏ | 31/50 [00:03<00:01, 10.12it/s] 66%|██████▌ | 33/50 [00:03<00:01, 10.12it/s] 70%|███████ | 35/50 [00:03<00:01, 10.14it/s] 74%|███████▍ | 37/50 [00:03<00:01, 10.12it/s] 78%|███████▊ | 39/50 [00:03<00:01, 10.12it/s] 82%|████████▏ | 41/50 [00:04<00:00, 10.14it/s] 86%|████████▌ | 43/50 [00:04<00:00, 10.13it/s] 90%|█████████ | 45/50 [00:04<00:00, 10.14it/s] 94%|█████████▍| 47/50 [00:04<00:00, 10.12it/s] 98%|█████████▊| 49/50 [00:04<00:00, 10.13it/s] 100%|██████████| 50/50 [00:04<00:00, 10.00it/s]
Want to make some of these yourself?
Run this model