daanelson / stable-diffusion-speed-lab
Stable Diffusion, accelerated
- Public
- 3.1K runs
-
A100 (80GB)
Prediction
daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146IDrcia4uwu6bf7jbokhst44btubyStatusSucceededSourceWebHardware–Total durationCreatedInput
- prompt
- an illustration of a redwood grove, oil painting, detailed, ferns
- num_outputs
- 1
- guidance_scale
- 7.5
- num_inference_steps
- 50
{ "prompt": "an illustration of a redwood grove, oil painting, detailed, ferns", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", { input: { prompt: "an illustration of a redwood grove, oil painting, detailed, ferns", num_outputs: 1, guidance_scale: 7.5, 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 replicate
Import the client:import replicate
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", input={ "prompt": "an illustration of a redwood grove, oil painting, detailed, ferns", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run daanelson/stable-diffusion-speed-lab 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": "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", "input": { "prompt": "an illustration of a redwood grove, oil painting, detailed, ferns", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-02-08T22:25:06.750167Z", "created_at": "2023-02-08T22:25:04.822000Z", "data_removed": false, "error": null, "id": "rcia4uwu6bf7jbokhst44btuby", "input": { "prompt": "an illustration of a redwood grove, oil painting, detailed, ferns", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }, "logs": "Using seed: 40995\n 0%| | 0/50 [00:00<?, ?it/s]\n 10%|█ | 5/50 [00:00<00:01, 41.28it/s]\n 20%|██ | 10/50 [00:00<00:00, 43.13it/s]\n 32%|███▏ | 16/50 [00:00<00:00, 46.82it/s]\n 44%|████▍ | 22/50 [00:00<00:00, 48.48it/s]\n 56%|█████▌ | 28/50 [00:00<00:00, 49.68it/s]\n 68%|██████▊ | 34/50 [00:00<00:00, 50.30it/s]\n 80%|████████ | 40/50 [00:00<00:00, 50.76it/s]\n 92%|█████████▏| 46/50 [00:00<00:00, 51.10it/s]\n100%|██████████| 50/50 [00:01<00:00, 49.52it/s]", "metrics": { "predict_time": 1.869235, "total_time": 1.928167 }, "output": [ "https://replicate.delivery/pbxt/pZSfgENeV8tgeJsw2AQI76qEm1efD5Ej3bhP1KYPjqETopjDC/out-0.png" ], "started_at": "2023-02-08T22:25:04.880932Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rcia4uwu6bf7jbokhst44btuby", "cancel": "https://api.replicate.com/v1/predictions/rcia4uwu6bf7jbokhst44btuby/cancel" }, "version": "4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146" }
Generated inUsing seed: 40995 0%| | 0/50 [00:00<?, ?it/s] 10%|█ | 5/50 [00:00<00:01, 41.28it/s] 20%|██ | 10/50 [00:00<00:00, 43.13it/s] 32%|███▏ | 16/50 [00:00<00:00, 46.82it/s] 44%|████▍ | 22/50 [00:00<00:00, 48.48it/s] 56%|█████▌ | 28/50 [00:00<00:00, 49.68it/s] 68%|██████▊ | 34/50 [00:00<00:00, 50.30it/s] 80%|████████ | 40/50 [00:00<00:00, 50.76it/s] 92%|█████████▏| 46/50 [00:00<00:00, 51.10it/s] 100%|██████████| 50/50 [00:01<00:00, 49.52it/s]
Prediction
daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146IDrjne6sk3szbs7o2vthxnu356paStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 100
- prompt
- 👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic
- num_outputs
- 1
- guidance_scale
- 7.5
- num_inference_steps
- 50
{ "seed": 100, "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", { input: { seed: 100, prompt: "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", num_outputs: 1, guidance_scale: 7.5, 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 replicate
Import the client:import replicate
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", input={ "seed": 100, "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run daanelson/stable-diffusion-speed-lab 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": "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", "input": { "seed": 100, "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-02-08T22:31:59.329596Z", "created_at": "2023-02-08T22:31:57.346300Z", "data_removed": false, "error": null, "id": "rjne6sk3szbs7o2vthxnu356pa", "input": { "seed": 100, "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }, "logs": "Using seed: 100\n 0%| | 0/50 [00:00<?, ?it/s]\n 10%|█ | 5/50 [00:00<00:01, 41.97it/s]\n 20%|██ | 10/50 [00:00<00:00, 41.88it/s]\n 32%|███▏ | 16/50 [00:00<00:00, 45.80it/s]\n 44%|████▍ | 22/50 [00:00<00:00, 48.05it/s]\n 56%|█████▌ | 28/50 [00:00<00:00, 49.22it/s]\n 68%|██████▊ | 34/50 [00:00<00:00, 49.88it/s]\n 80%|████████ | 40/50 [00:00<00:00, 50.26it/s]\n 92%|█████████▏| 46/50 [00:00<00:00, 50.82it/s]\n100%|██████████| 50/50 [00:01<00:00, 49.11it/s]", "metrics": { "predict_time": 1.924939, "total_time": 1.983296 }, "output": [ "https://replicate.delivery/pbxt/jdp6RPFWZLaNI1bfPajeEqeos38qteXWMJzzfoTFKWU0bqjDC/out-0.png" ], "started_at": "2023-02-08T22:31:57.404657Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rjne6sk3szbs7o2vthxnu356pa", "cancel": "https://api.replicate.com/v1/predictions/rjne6sk3szbs7o2vthxnu356pa/cancel" }, "version": "4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146" }
Generated inUsing seed: 100 0%| | 0/50 [00:00<?, ?it/s] 10%|█ | 5/50 [00:00<00:01, 41.97it/s] 20%|██ | 10/50 [00:00<00:00, 41.88it/s] 32%|███▏ | 16/50 [00:00<00:00, 45.80it/s] 44%|████▍ | 22/50 [00:00<00:00, 48.05it/s] 56%|█████▌ | 28/50 [00:00<00:00, 49.22it/s] 68%|██████▊ | 34/50 [00:00<00:00, 49.88it/s] 80%|████████ | 40/50 [00:00<00:00, 50.26it/s] 92%|█████████▏| 46/50 [00:00<00:00, 50.82it/s] 100%|██████████| 50/50 [00:01<00:00, 49.11it/s]
Prediction
daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146IDwtl2het2lrfnjiemra7wzsp2dqStatusSucceededSourceAPIHardware–Total durationCreatedInput
- prompt
- landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful
- negative_prompt
- bad anatomy, low res, blurry, bad features, noisy
{ "prompt": "landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful", "negative_prompt": "bad anatomy, low res, blurry, bad features, noisy" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", { input: { prompt: "landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful", negative_prompt: "bad anatomy, low res, blurry, bad features, noisy" } } ); // 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 replicate
Import the client:import replicate
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", input={ "prompt": "landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful", "negative_prompt": "bad anatomy, low res, blurry, bad features, noisy" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run daanelson/stable-diffusion-speed-lab 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": "daanelson/stable-diffusion-speed-lab:4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146", "input": { "prompt": "landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful", "negative_prompt": "bad anatomy, low res, blurry, bad features, noisy" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-02-08T23:54:35.936119Z", "created_at": "2023-02-08T23:54:34.017502Z", "data_removed": false, "error": null, "id": "wtl2het2lrfnjiemra7wzsp2dq", "input": { "prompt": "landscape photography of fundatura ponorului by marc adamus, morning, mist, rays of light, beautiful", "negative_prompt": "bad anatomy, low res, blurry, bad features, noisy" }, "logs": "Using seed: 59594\n 0%| | 0/50 [00:00<?, ?it/s]\n 10%|█ | 5/50 [00:00<00:01, 41.70it/s]\n 20%|██ | 10/50 [00:00<00:00, 42.05it/s]\n 32%|███▏ | 16/50 [00:00<00:00, 46.64it/s]\n 44%|████▍ | 22/50 [00:00<00:00, 48.93it/s]\n 56%|█████▌ | 28/50 [00:00<00:00, 50.18it/s]\n 68%|██████▊ | 34/50 [00:00<00:00, 50.94it/s]\n 80%|████████ | 40/50 [00:00<00:00, 51.34it/s]\n 92%|█████████▏| 46/50 [00:00<00:00, 51.60it/s]\n100%|██████████| 50/50 [00:01<00:00, 49.85it/s]", "metrics": { "predict_time": 1.860448, "total_time": 1.918617 }, "output": [ "https://replicate.delivery/pbxt/pRnsWOemWD0QZqSy3NOZdCuOhYtd5BETyf7QYynq1Tp7ge4gA/out-0.png" ], "started_at": "2023-02-08T23:54:34.075671Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wtl2het2lrfnjiemra7wzsp2dq", "cancel": "https://api.replicate.com/v1/predictions/wtl2het2lrfnjiemra7wzsp2dq/cancel" }, "version": "4905500191572a49169c7b2eef219b3ac7a3da0beeaeb0f132e8df8766de6146" }
Generated inUsing seed: 59594 0%| | 0/50 [00:00<?, ?it/s] 10%|█ | 5/50 [00:00<00:01, 41.70it/s] 20%|██ | 10/50 [00:00<00:00, 42.05it/s] 32%|███▏ | 16/50 [00:00<00:00, 46.64it/s] 44%|████▍ | 22/50 [00:00<00:00, 48.93it/s] 56%|█████▌ | 28/50 [00:00<00:00, 50.18it/s] 68%|██████▊ | 34/50 [00:00<00:00, 50.94it/s] 80%|████████ | 40/50 [00:00<00:00, 51.34it/s] 92%|█████████▏| 46/50 [00:00<00:00, 51.60it/s] 100%|██████████| 50/50 [00:01<00:00, 49.85it/s]
Prediction
daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820IDli3j67gftna5xb7a3lin2tn7iqStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 100
- prompt
- A vision of paradise, Unreal Engine
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- num_inference_steps
- 50
{ "seed": 100, "prompt": "A vision of paradise, Unreal Engine", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", { input: { seed: 100, prompt: "A vision of paradise, Unreal Engine", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, 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 replicate
Import the client:import replicate
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", input={ "seed": 100, "prompt": "A vision of paradise, Unreal Engine", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run daanelson/stable-diffusion-speed-lab 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": "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", "input": { "seed": 100, "prompt": "A vision of paradise, Unreal Engine", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-02-09T05:51:44.876295Z", "created_at": "2023-02-09T05:51:42.982367Z", "data_removed": false, "error": null, "id": "li3j67gftna5xb7a3lin2tn7iq", "input": { "seed": 100, "prompt": "A vision of paradise, Unreal Engine", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }, "logs": "Using seed: 100\n 0%| | 0/50 [00:00<?, ?it/s]\n 10%|█ | 5/50 [00:00<00:01, 41.55it/s]\n 20%|██ | 10/50 [00:00<00:00, 42.96it/s]\n 32%|███▏ | 16/50 [00:00<00:00, 47.22it/s]\n 44%|████▍ | 22/50 [00:00<00:00, 49.23it/s]\n 56%|█████▌ | 28/50 [00:00<00:00, 50.39it/s]\n 68%|██████▊ | 34/50 [00:00<00:00, 51.09it/s]\n 80%|████████ | 40/50 [00:00<00:00, 51.17it/s]\n 92%|█████████▏| 46/50 [00:00<00:00, 51.55it/s]\n100%|██████████| 50/50 [00:01<00:00, 49.99it/s]", "metrics": { "predict_time": 1.821111, "total_time": 1.893928 }, "output": [ "https://replicate.delivery/pbxt/yXmTfKvgmA2WR6IJvsXIY0jFDOKq7YCr9tIeVIWc24vwvjcQA/out-0.png" ], "started_at": "2023-02-09T05:51:43.055184Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/li3j67gftna5xb7a3lin2tn7iq", "cancel": "https://api.replicate.com/v1/predictions/li3j67gftna5xb7a3lin2tn7iq/cancel" }, "version": "05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820" }
Generated inUsing seed: 100 0%| | 0/50 [00:00<?, ?it/s] 10%|█ | 5/50 [00:00<00:01, 41.55it/s] 20%|██ | 10/50 [00:00<00:00, 42.96it/s] 32%|███▏ | 16/50 [00:00<00:00, 47.22it/s] 44%|████▍ | 22/50 [00:00<00:00, 49.23it/s] 56%|█████▌ | 28/50 [00:00<00:00, 50.39it/s] 68%|██████▊ | 34/50 [00:00<00:00, 51.09it/s] 80%|████████ | 40/50 [00:00<00:00, 51.17it/s] 92%|█████████▏| 46/50 [00:00<00:00, 51.55it/s] 100%|██████████| 50/50 [00:01<00:00, 49.99it/s]
Prediction
daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820Input
- prompt
- 👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- num_inference_steps
- 50
{ "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", { input: { prompt: "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, 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 replicate
Import the client:import replicate
Run daanelson/stable-diffusion-speed-lab using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", input={ "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run daanelson/stable-diffusion-speed-lab 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": "daanelson/stable-diffusion-speed-lab:05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820", "input": { "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-02-09T05:54:14.652334Z", "created_at": "2023-02-09T05:54:12.733829Z", "data_removed": false, "error": null, "id": "dk6eqsktbnajzcbdwwy4vydqra", "input": { "prompt": "👨🚀🦅, digital Art, Greg rutkowski, Trending artstation,cinematographic", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }, "logs": "Using seed: 11744\n 0%| | 0/50 [00:00<?, ?it/s]\n 10%|█ | 5/50 [00:00<00:01, 41.67it/s]\n 22%|██▏ | 11/50 [00:00<00:00, 47.58it/s]\n 34%|███▍ | 17/50 [00:00<00:00, 49.75it/s]\n 46%|████▌ | 23/50 [00:00<00:00, 50.80it/s]\n 58%|█████▊ | 29/50 [00:00<00:00, 51.38it/s]\n 70%|███████ | 35/50 [00:00<00:00, 51.74it/s]\n 82%|████████▏ | 41/50 [00:00<00:00, 51.97it/s]\n 94%|█████████▍| 47/50 [00:00<00:00, 52.08it/s]\n100%|██████████| 50/50 [00:00<00:00, 51.02it/s]", "metrics": { "predict_time": 1.842167, "total_time": 1.918505 }, "output": [ "https://replicate.delivery/pbxt/OUCfLnZeb4ipLkABAvT05DFlIYzVuYXwmQWntyKfoXrNkH5gA/out-0.png" ], "started_at": "2023-02-09T05:54:12.810167Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dk6eqsktbnajzcbdwwy4vydqra", "cancel": "https://api.replicate.com/v1/predictions/dk6eqsktbnajzcbdwwy4vydqra/cancel" }, "version": "05aca4aea54103353540845627a4ac45412195df3b099f9f4d932f58a5ccb820" }
Generated inUsing seed: 11744 0%| | 0/50 [00:00<?, ?it/s] 10%|█ | 5/50 [00:00<00:01, 41.67it/s] 22%|██▏ | 11/50 [00:00<00:00, 47.58it/s] 34%|███▍ | 17/50 [00:00<00:00, 49.75it/s] 46%|████▌ | 23/50 [00:00<00:00, 50.80it/s] 58%|█████▊ | 29/50 [00:00<00:00, 51.38it/s] 70%|███████ | 35/50 [00:00<00:00, 51.74it/s] 82%|████████▏ | 41/50 [00:00<00:00, 51.97it/s] 94%|█████████▍| 47/50 [00:00<00:00, 52.08it/s] 100%|██████████| 50/50 [00:00<00:00, 51.02it/s]
Want to make some of these yourself?
Run this model