charlesmccarthy/terminus-xl-otaku-v1

Terminus XL Otaku is a latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

High quality image blending using Kandinsky 2.2 blending pipeline brought to you by your best friends at FullJourney.AI :)

Hotshot XL using SDXL for generating one second clips of high quality! Running on a40 Made by the greats at hotshot.co and brought to you by your friends at FullJourney! Thanks to LucaTaco for the MVP!

Add a watermark to your videos using the power of Replicate brought to you from your friends at FullJourney.AI

Terminus XL Gamma is a new state-of-the-art latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

Animagine XL 2.0 is an advanced latent text-to-image diffusion model designed to create high-resolution, detailed anime images.

The best Pony-SDXL models! Current one is based on Pony Realism.


blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1, The top ranked model on Civitai

epiCRealism v7-Final Destination. Top Realism Model on Civitai

MusicGen running on an a40 with 60 seconds max duration


Kolors is a SOTA base image model for high quality image generation

Take audio from one video and add it to a second video. Good for adding back audio to liveportrait.

Change the fps of a video without changing its length or speed

Terminus XL Otaku is a latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.
Prediction
charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bccaIDv4yarmdbozamrlwcgytylzuaseStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- joe biden eating a cheeeseburger at mcdonalds
- scheduler
- K_EULER
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- num_inference_steps
- 25
{ "width": 1024, "height": 1024, "prompt": "joe biden eating a cheeeseburger at mcdonalds", "scheduler": "K_EULER", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 25 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", { input: { width: 1024, height: 1024, prompt: "joe biden eating a cheeeseburger at mcdonalds", scheduler: "K_EULER", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "", num_inference_steps: 25 } } ); // 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 charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", input={ "width": 1024, "height": 1024, "prompt": "joe biden eating a cheeeseburger at mcdonalds", "scheduler": "K_EULER", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "", "num_inference_steps": 25 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run charlesmccarthy/terminus-xl-otaku-v1 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": "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", "input": { "width": 1024, "height": 1024, "prompt": "joe biden eating a cheeeseburger at mcdonalds", "scheduler": "K_EULER", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 25 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="joe biden eating a cheeeseburger at mcdonalds"' \ -i 'scheduler="K_EULER"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=25'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "joe biden eating a cheeeseburger at mcdonalds", "scheduler": "K_EULER", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 25 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-26T05:17:33.431718Z", "created_at": "2023-12-26T05:14:30.102887Z", "data_removed": false, "error": null, "id": "v4yarmdbozamrlwcgytylzuase", "input": { "width": 1024, "height": 1024, "prompt": "joe biden eating a cheeeseburger at mcdonalds", "scheduler": "K_EULER", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 25 }, "logs": "Using seed: 4177073\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:08, 2.98it/s]\n 8%|▊ | 2/25 [00:00<00:05, 3.93it/s]\n 12%|█▏ | 3/25 [00:00<00:05, 4.37it/s]\n 16%|█▌ | 4/25 [00:00<00:04, 4.61it/s]\n 20%|██ | 5/25 [00:01<00:04, 4.76it/s]\n 24%|██▍ | 6/25 [00:01<00:03, 4.84it/s]\n 28%|██▊ | 7/25 [00:01<00:03, 4.89it/s]\n 32%|███▏ | 8/25 [00:01<00:03, 4.93it/s]\n 36%|███▌ | 9/25 [00:01<00:03, 4.96it/s]\n 40%|████ | 10/25 [00:02<00:03, 4.97it/s]\n 44%|████▍ | 11/25 [00:02<00:02, 4.98it/s]\n 48%|████▊ | 12/25 [00:02<00:02, 4.99it/s]\n 52%|█████▏ | 13/25 [00:02<00:02, 4.98it/s]\n 56%|█████▌ | 14/25 [00:02<00:02, 4.99it/s]\n 60%|██████ | 15/25 [00:03<00:02, 4.99it/s]\n 64%|██████▍ | 16/25 [00:03<00:01, 4.99it/s]\n 68%|██████▊ | 17/25 [00:03<00:01, 5.00it/s]\n 72%|███████▏ | 18/25 [00:03<00:01, 4.99it/s]\n 76%|███████▌ | 19/25 [00:03<00:01, 5.00it/s]\n 80%|████████ | 20/25 [00:04<00:01, 5.00it/s]\n 84%|████████▍ | 21/25 [00:04<00:00, 5.00it/s]\n 88%|████████▊ | 22/25 [00:04<00:00, 5.00it/s]\n 92%|█████████▏| 23/25 [00:04<00:00, 5.00it/s]\n 96%|█████████▌| 24/25 [00:04<00:00, 5.00it/s]\n100%|██████████| 25/25 [00:05<00:00, 5.00it/s]\n100%|██████████| 25/25 [00:05<00:00, 4.87it/s]", "metrics": { "predict_time": 7.122212, "total_time": 183.328831 }, "output": [ "https://replicate.delivery/pbxt/IEYnPTueeWs9HUb2xtL2mR1CLasKcnFX5Dv6vDX0ERvsPBGSA/out-0.png" ], "started_at": "2023-12-26T05:17:26.309506Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/v4yarmdbozamrlwcgytylzuase", "cancel": "https://api.replicate.com/v1/predictions/v4yarmdbozamrlwcgytylzuase/cancel" }, "version": "7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca" }
Generated inUsing seed: 4177073 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:08, 2.98it/s] 8%|▊ | 2/25 [00:00<00:05, 3.93it/s] 12%|█▏ | 3/25 [00:00<00:05, 4.37it/s] 16%|█▌ | 4/25 [00:00<00:04, 4.61it/s] 20%|██ | 5/25 [00:01<00:04, 4.76it/s] 24%|██▍ | 6/25 [00:01<00:03, 4.84it/s] 28%|██▊ | 7/25 [00:01<00:03, 4.89it/s] 32%|███▏ | 8/25 [00:01<00:03, 4.93it/s] 36%|███▌ | 9/25 [00:01<00:03, 4.96it/s] 40%|████ | 10/25 [00:02<00:03, 4.97it/s] 44%|████▍ | 11/25 [00:02<00:02, 4.98it/s] 48%|████▊ | 12/25 [00:02<00:02, 4.99it/s] 52%|█████▏ | 13/25 [00:02<00:02, 4.98it/s] 56%|█████▌ | 14/25 [00:02<00:02, 4.99it/s] 60%|██████ | 15/25 [00:03<00:02, 4.99it/s] 64%|██████▍ | 16/25 [00:03<00:01, 4.99it/s] 68%|██████▊ | 17/25 [00:03<00:01, 5.00it/s] 72%|███████▏ | 18/25 [00:03<00:01, 4.99it/s] 76%|███████▌ | 19/25 [00:03<00:01, 5.00it/s] 80%|████████ | 20/25 [00:04<00:01, 5.00it/s] 84%|████████▍ | 21/25 [00:04<00:00, 5.00it/s] 88%|████████▊ | 22/25 [00:04<00:00, 5.00it/s] 92%|█████████▏| 23/25 [00:04<00:00, 5.00it/s] 96%|█████████▌| 24/25 [00:04<00:00, 5.00it/s] 100%|██████████| 25/25 [00:05<00:00, 5.00it/s] 100%|██████████| 25/25 [00:05<00:00, 4.87it/s]
Prediction
charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bccaIDdovjsu3bbeus5elbpcdvm7fecyStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- jlo as artwork
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 6.5
- apply_watermark
- negative_prompt
- num_inference_steps
- 33
{ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", { input: { width: 1024, height: 1024, prompt: "jlo as artwork", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 6.5, apply_watermark: true, negative_prompt: "", num_inference_steps: 33 } } ); // 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 charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", input={ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": True, "negative_prompt": "", "num_inference_steps": 33 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run charlesmccarthy/terminus-xl-otaku-v1 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": "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="jlo as artwork"' \ -i 'scheduler="DPMSolverMultistep"' \ -i 'num_outputs=1' \ -i 'guidance_scale=6.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=33'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-26T05:23:27.786839Z", "created_at": "2023-12-26T05:23:19.193719Z", "data_removed": false, "error": null, "id": "dovjsu3bbeus5elbpcdvm7fecy", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }, "logs": "Using seed: 11974137\n 0%| | 0/33 [00:00<?, ?it/s]\n 3%|▎ | 1/33 [00:00<00:06, 5.06it/s]\n 9%|▉ | 3/33 [00:00<00:04, 6.24it/s]\n 12%|█▏ | 4/33 [00:00<00:05, 5.76it/s]\n 15%|█▌ | 5/33 [00:00<00:05, 5.51it/s]\n 18%|█▊ | 6/33 [00:01<00:05, 5.34it/s]\n 21%|██ | 7/33 [00:01<00:04, 5.24it/s]\n 24%|██▍ | 8/33 [00:01<00:04, 5.18it/s]\n 27%|██▋ | 9/33 [00:01<00:04, 5.14it/s]\n 30%|███ | 10/33 [00:01<00:04, 5.11it/s]\n 33%|███▎ | 11/33 [00:02<00:04, 5.08it/s]\n 36%|███▋ | 12/33 [00:02<00:04, 5.07it/s]\n 39%|███▉ | 13/33 [00:02<00:03, 5.06it/s]\n 42%|████▏ | 14/33 [00:02<00:03, 5.03it/s]\n 45%|████▌ | 15/33 [00:02<00:03, 4.96it/s]\n 48%|████▊ | 16/33 [00:03<00:03, 4.98it/s]\n 52%|█████▏ | 17/33 [00:03<00:03, 4.99it/s]\n 55%|█████▍ | 18/33 [00:03<00:02, 5.00it/s]\n 58%|█████▊ | 19/33 [00:03<00:02, 5.01it/s]\n 61%|██████ | 20/33 [00:03<00:02, 5.01it/s]\n 64%|██████▎ | 21/33 [00:04<00:02, 5.02it/s]\n 67%|██████▋ | 22/33 [00:04<00:02, 5.02it/s]\n 70%|██████▉ | 23/33 [00:04<00:01, 5.02it/s]\n 73%|███████▎ | 24/33 [00:04<00:01, 5.02it/s]\n 76%|███████▌ | 25/33 [00:04<00:01, 5.02it/s]\n 79%|███████▉ | 26/33 [00:05<00:01, 5.02it/s]\n 82%|████████▏ | 27/33 [00:05<00:01, 5.02it/s]\n 85%|████████▍ | 28/33 [00:05<00:00, 5.01it/s]\n 88%|████████▊ | 29/33 [00:05<00:00, 5.01it/s]\n 91%|█████████ | 30/33 [00:05<00:00, 5.00it/s]\n 94%|█████████▍| 31/33 [00:06<00:00, 5.00it/s]\n 97%|█████████▋| 32/33 [00:06<00:00, 5.01it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.00it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.10it/s]", "metrics": { "predict_time": 8.55192, "total_time": 8.59312 }, "output": [ "https://replicate.delivery/pbxt/5LfQDeOcydhR3UIce0JP70V27VY62vZaGBEM95XSyRudqCMkA/out-0.png" ], "started_at": "2023-12-26T05:23:19.234919Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dovjsu3bbeus5elbpcdvm7fecy", "cancel": "https://api.replicate.com/v1/predictions/dovjsu3bbeus5elbpcdvm7fecy/cancel" }, "version": "7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca" }
Generated inUsing seed: 11974137 0%| | 0/33 [00:00<?, ?it/s] 3%|▎ | 1/33 [00:00<00:06, 5.06it/s] 9%|▉ | 3/33 [00:00<00:04, 6.24it/s] 12%|█▏ | 4/33 [00:00<00:05, 5.76it/s] 15%|█▌ | 5/33 [00:00<00:05, 5.51it/s] 18%|█▊ | 6/33 [00:01<00:05, 5.34it/s] 21%|██ | 7/33 [00:01<00:04, 5.24it/s] 24%|██▍ | 8/33 [00:01<00:04, 5.18it/s] 27%|██▋ | 9/33 [00:01<00:04, 5.14it/s] 30%|███ | 10/33 [00:01<00:04, 5.11it/s] 33%|███▎ | 11/33 [00:02<00:04, 5.08it/s] 36%|███▋ | 12/33 [00:02<00:04, 5.07it/s] 39%|███▉ | 13/33 [00:02<00:03, 5.06it/s] 42%|████▏ | 14/33 [00:02<00:03, 5.03it/s] 45%|████▌ | 15/33 [00:02<00:03, 4.96it/s] 48%|████▊ | 16/33 [00:03<00:03, 4.98it/s] 52%|█████▏ | 17/33 [00:03<00:03, 4.99it/s] 55%|█████▍ | 18/33 [00:03<00:02, 5.00it/s] 58%|█████▊ | 19/33 [00:03<00:02, 5.01it/s] 61%|██████ | 20/33 [00:03<00:02, 5.01it/s] 64%|██████▎ | 21/33 [00:04<00:02, 5.02it/s] 67%|██████▋ | 22/33 [00:04<00:02, 5.02it/s] 70%|██████▉ | 23/33 [00:04<00:01, 5.02it/s] 73%|███████▎ | 24/33 [00:04<00:01, 5.02it/s] 76%|███████▌ | 25/33 [00:04<00:01, 5.02it/s] 79%|███████▉ | 26/33 [00:05<00:01, 5.02it/s] 82%|████████▏ | 27/33 [00:05<00:01, 5.02it/s] 85%|████████▍ | 28/33 [00:05<00:00, 5.01it/s] 88%|████████▊ | 29/33 [00:05<00:00, 5.01it/s] 91%|█████████ | 30/33 [00:05<00:00, 5.00it/s] 94%|█████████▍| 31/33 [00:06<00:00, 5.00it/s] 97%|█████████▋| 32/33 [00:06<00:00, 5.01it/s] 100%|██████████| 33/33 [00:06<00:00, 5.00it/s] 100%|██████████| 33/33 [00:06<00:00, 5.10it/s]
Prediction
charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bccaIDnwndyklbyng3rnilchojoyg3biStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- The Joker, Cinematic still, vibrant, bokeh
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 6.5
- apply_watermark
- negative_prompt
- num_inference_steps
- 33
{ "width": 1024, "height": 1024, "prompt": "The Joker, Cinematic still, vibrant, bokeh", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", { input: { width: 1024, height: 1024, prompt: "The Joker, Cinematic still, vibrant, bokeh", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 6.5, apply_watermark: true, negative_prompt: "", num_inference_steps: 33 } } ); // 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 charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", input={ "width": 1024, "height": 1024, "prompt": "The Joker, Cinematic still, vibrant, bokeh", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": True, "negative_prompt": "", "num_inference_steps": 33 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run charlesmccarthy/terminus-xl-otaku-v1 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": "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", "input": { "width": 1024, "height": 1024, "prompt": "The Joker, Cinematic still, vibrant, bokeh", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="The Joker, Cinematic still, vibrant, bokeh"' \ -i 'scheduler="K_EULER_ANCESTRAL"' \ -i 'num_outputs=1' \ -i 'guidance_scale=6.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=33'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "The Joker, Cinematic still, vibrant, bokeh", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-26T05:28:00.493628Z", "created_at": "2023-12-26T05:27:51.924837Z", "data_removed": false, "error": null, "id": "nwndyklbyng3rnilchojoyg3bi", "input": { "width": 1024, "height": 1024, "prompt": "The Joker, Cinematic still, vibrant, bokeh", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }, "logs": "Using seed: 1899355\n 0%| | 0/33 [00:00<?, ?it/s]\n 6%|▌ | 2/33 [00:00<00:04, 6.81it/s]\n 9%|▉ | 3/33 [00:00<00:05, 5.94it/s]\n 12%|█▏ | 4/33 [00:00<00:05, 5.57it/s]\n 15%|█▌ | 5/33 [00:00<00:05, 5.37it/s]\n 18%|█▊ | 6/33 [00:01<00:05, 5.24it/s]\n 21%|██ | 7/33 [00:01<00:05, 5.17it/s]\n 24%|██▍ | 8/33 [00:01<00:04, 5.12it/s]\n 27%|██▋ | 9/33 [00:01<00:04, 5.09it/s]\n 30%|███ | 10/33 [00:01<00:04, 5.06it/s]\n 33%|███▎ | 11/33 [00:02<00:04, 5.04it/s]\n 36%|███▋ | 12/33 [00:02<00:04, 5.03it/s]\n 39%|███▉ | 13/33 [00:02<00:03, 5.02it/s]\n 42%|████▏ | 14/33 [00:02<00:03, 5.02it/s]\n 45%|████▌ | 15/33 [00:02<00:03, 5.01it/s]\n 48%|████▊ | 16/33 [00:03<00:03, 5.01it/s]\n 52%|█████▏ | 17/33 [00:03<00:03, 5.01it/s]\n 55%|█████▍ | 18/33 [00:03<00:02, 5.00it/s]\n 58%|█████▊ | 19/33 [00:03<00:02, 5.00it/s]\n 61%|██████ | 20/33 [00:03<00:02, 5.00it/s]\n 64%|██████▎ | 21/33 [00:04<00:02, 5.00it/s]\n 67%|██████▋ | 22/33 [00:04<00:02, 5.00it/s]\n 70%|██████▉ | 23/33 [00:04<00:02, 5.00it/s]\n 73%|███████▎ | 24/33 [00:04<00:01, 4.99it/s]\n 76%|███████▌ | 25/33 [00:04<00:01, 4.99it/s]\n 79%|███████▉ | 26/33 [00:05<00:01, 4.99it/s]\n 82%|████████▏ | 27/33 [00:05<00:01, 4.99it/s]\n 85%|████████▍ | 28/33 [00:05<00:01, 4.99it/s]\n 88%|████████▊ | 29/33 [00:05<00:00, 4.99it/s]\n 91%|█████████ | 30/33 [00:05<00:00, 4.98it/s]\n 94%|█████████▍| 31/33 [00:06<00:00, 4.98it/s]\n 97%|█████████▋| 32/33 [00:06<00:00, 4.98it/s]\n100%|██████████| 33/33 [00:06<00:00, 4.98it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.08it/s]", "metrics": { "predict_time": 8.529504, "total_time": 8.568791 }, "output": [ "https://replicate.delivery/pbxt/WL0lEwlzmR4fOyQoNDtI3kpY2OmDH9ypRf5KfxBkkdMflFYIB/out-0.png" ], "started_at": "2023-12-26T05:27:51.964124Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/nwndyklbyng3rnilchojoyg3bi", "cancel": "https://api.replicate.com/v1/predictions/nwndyklbyng3rnilchojoyg3bi/cancel" }, "version": "7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca" }
Generated inUsing seed: 1899355 0%| | 0/33 [00:00<?, ?it/s] 6%|▌ | 2/33 [00:00<00:04, 6.81it/s] 9%|▉ | 3/33 [00:00<00:05, 5.94it/s] 12%|█▏ | 4/33 [00:00<00:05, 5.57it/s] 15%|█▌ | 5/33 [00:00<00:05, 5.37it/s] 18%|█▊ | 6/33 [00:01<00:05, 5.24it/s] 21%|██ | 7/33 [00:01<00:05, 5.17it/s] 24%|██▍ | 8/33 [00:01<00:04, 5.12it/s] 27%|██▋ | 9/33 [00:01<00:04, 5.09it/s] 30%|███ | 10/33 [00:01<00:04, 5.06it/s] 33%|███▎ | 11/33 [00:02<00:04, 5.04it/s] 36%|███▋ | 12/33 [00:02<00:04, 5.03it/s] 39%|███▉ | 13/33 [00:02<00:03, 5.02it/s] 42%|████▏ | 14/33 [00:02<00:03, 5.02it/s] 45%|████▌ | 15/33 [00:02<00:03, 5.01it/s] 48%|████▊ | 16/33 [00:03<00:03, 5.01it/s] 52%|█████▏ | 17/33 [00:03<00:03, 5.01it/s] 55%|█████▍ | 18/33 [00:03<00:02, 5.00it/s] 58%|█████▊ | 19/33 [00:03<00:02, 5.00it/s] 61%|██████ | 20/33 [00:03<00:02, 5.00it/s] 64%|██████▎ | 21/33 [00:04<00:02, 5.00it/s] 67%|██████▋ | 22/33 [00:04<00:02, 5.00it/s] 70%|██████▉ | 23/33 [00:04<00:02, 5.00it/s] 73%|███████▎ | 24/33 [00:04<00:01, 4.99it/s] 76%|███████▌ | 25/33 [00:04<00:01, 4.99it/s] 79%|███████▉ | 26/33 [00:05<00:01, 4.99it/s] 82%|████████▏ | 27/33 [00:05<00:01, 4.99it/s] 85%|████████▍ | 28/33 [00:05<00:01, 4.99it/s] 88%|████████▊ | 29/33 [00:05<00:00, 4.99it/s] 91%|█████████ | 30/33 [00:05<00:00, 4.98it/s] 94%|█████████▍| 31/33 [00:06<00:00, 4.98it/s] 97%|█████████▋| 32/33 [00:06<00:00, 4.98it/s] 100%|██████████| 33/33 [00:06<00:00, 4.98it/s] 100%|██████████| 33/33 [00:06<00:00, 5.08it/s]
Prediction
charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bccaID35au3olbdn7ejhs7ipblddninuStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- jlo as artwork
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- num_inference_steps
- 33
{ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", { input: { width: 1024, height: 1024, prompt: "jlo as artwork", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "", num_inference_steps: 33 } } ); // 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 charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", input={ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "", "num_inference_steps": 33 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run charlesmccarthy/terminus-xl-otaku-v1 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": "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="jlo as artwork"' \ -i 'scheduler="DPMSolverMultistep"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=33'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-26T05:23:03.651623Z", "created_at": "2023-12-26T05:22:55.083057Z", "data_removed": false, "error": null, "id": "35au3olbdn7ejhs7ipblddninu", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }, "logs": "Using seed: 3751455\n 0%| | 0/33 [00:00<?, ?it/s]\n 3%|▎ | 1/33 [00:00<00:06, 5.07it/s]\n 9%|▉ | 3/33 [00:00<00:04, 6.26it/s]\n 12%|█▏ | 4/33 [00:00<00:05, 5.78it/s]\n 15%|█▌ | 5/33 [00:00<00:05, 5.51it/s]\n 18%|█▊ | 6/33 [00:01<00:05, 5.34it/s]\n 21%|██ | 7/33 [00:01<00:04, 5.23it/s]\n 24%|██▍ | 8/33 [00:01<00:04, 5.16it/s]\n 27%|██▋ | 9/33 [00:01<00:04, 5.13it/s]\n 30%|███ | 10/33 [00:01<00:04, 5.11it/s]\n 33%|███▎ | 11/33 [00:02<00:04, 5.09it/s]\n 36%|███▋ | 12/33 [00:02<00:04, 5.08it/s]\n 39%|███▉ | 13/33 [00:02<00:03, 5.07it/s]\n 42%|████▏ | 14/33 [00:02<00:03, 5.06it/s]\n 45%|████▌ | 15/33 [00:02<00:03, 5.05it/s]\n 48%|████▊ | 16/33 [00:03<00:03, 5.05it/s]\n 52%|█████▏ | 17/33 [00:03<00:03, 5.05it/s]\n 55%|█████▍ | 18/33 [00:03<00:02, 5.04it/s]\n 58%|█████▊ | 19/33 [00:03<00:02, 5.04it/s]\n 61%|██████ | 20/33 [00:03<00:02, 5.04it/s]\n 64%|██████▎ | 21/33 [00:04<00:02, 5.04it/s]\n 67%|██████▋ | 22/33 [00:04<00:02, 5.04it/s]\n 70%|██████▉ | 23/33 [00:04<00:01, 5.04it/s]\n 73%|███████▎ | 24/33 [00:04<00:01, 5.04it/s]\n 76%|███████▌ | 25/33 [00:04<00:01, 5.03it/s]\n 79%|███████▉ | 26/33 [00:05<00:01, 5.03it/s]\n 82%|████████▏ | 27/33 [00:05<00:01, 5.04it/s]\n 85%|████████▍ | 28/33 [00:05<00:00, 5.04it/s]\n 88%|████████▊ | 29/33 [00:05<00:00, 5.03it/s]\n 91%|█████████ | 30/33 [00:05<00:00, 5.03it/s]\n 94%|█████████▍| 31/33 [00:06<00:00, 5.03it/s]\n 97%|█████████▋| 32/33 [00:06<00:00, 5.03it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.03it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.12it/s]", "metrics": { "predict_time": 8.531742, "total_time": 8.568566 }, "output": [ "https://replicate.delivery/pbxt/s3QJiy5o4j6CGFQF0e2JvJLtmJGfnoaJhWEbvfYWb30tpCMkA/out-0.png" ], "started_at": "2023-12-26T05:22:55.119881Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/35au3olbdn7ejhs7ipblddninu", "cancel": "https://api.replicate.com/v1/predictions/35au3olbdn7ejhs7ipblddninu/cancel" }, "version": "7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca" }
Generated inUsing seed: 3751455 0%| | 0/33 [00:00<?, ?it/s] 3%|▎ | 1/33 [00:00<00:06, 5.07it/s] 9%|▉ | 3/33 [00:00<00:04, 6.26it/s] 12%|█▏ | 4/33 [00:00<00:05, 5.78it/s] 15%|█▌ | 5/33 [00:00<00:05, 5.51it/s] 18%|█▊ | 6/33 [00:01<00:05, 5.34it/s] 21%|██ | 7/33 [00:01<00:04, 5.23it/s] 24%|██▍ | 8/33 [00:01<00:04, 5.16it/s] 27%|██▋ | 9/33 [00:01<00:04, 5.13it/s] 30%|███ | 10/33 [00:01<00:04, 5.11it/s] 33%|███▎ | 11/33 [00:02<00:04, 5.09it/s] 36%|███▋ | 12/33 [00:02<00:04, 5.08it/s] 39%|███▉ | 13/33 [00:02<00:03, 5.07it/s] 42%|████▏ | 14/33 [00:02<00:03, 5.06it/s] 45%|████▌ | 15/33 [00:02<00:03, 5.05it/s] 48%|████▊ | 16/33 [00:03<00:03, 5.05it/s] 52%|█████▏ | 17/33 [00:03<00:03, 5.05it/s] 55%|█████▍ | 18/33 [00:03<00:02, 5.04it/s] 58%|█████▊ | 19/33 [00:03<00:02, 5.04it/s] 61%|██████ | 20/33 [00:03<00:02, 5.04it/s] 64%|██████▎ | 21/33 [00:04<00:02, 5.04it/s] 67%|██████▋ | 22/33 [00:04<00:02, 5.04it/s] 70%|██████▉ | 23/33 [00:04<00:01, 5.04it/s] 73%|███████▎ | 24/33 [00:04<00:01, 5.04it/s] 76%|███████▌ | 25/33 [00:04<00:01, 5.03it/s] 79%|███████▉ | 26/33 [00:05<00:01, 5.03it/s] 82%|████████▏ | 27/33 [00:05<00:01, 5.04it/s] 85%|████████▍ | 28/33 [00:05<00:00, 5.04it/s] 88%|████████▊ | 29/33 [00:05<00:00, 5.03it/s] 91%|█████████ | 30/33 [00:05<00:00, 5.03it/s] 94%|█████████▍| 31/33 [00:06<00:00, 5.03it/s] 97%|█████████▋| 32/33 [00:06<00:00, 5.03it/s] 100%|██████████| 33/33 [00:06<00:00, 5.03it/s] 100%|██████████| 33/33 [00:06<00:00, 5.12it/s]
Prediction
charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bccaIDz4f5ro3beaphl7etukvf7pzkimStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- jlo as artwork
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 6.5
- apply_watermark
- negative_prompt
- num_inference_steps
- 33
{ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", { input: { width: 1024, height: 1024, prompt: "jlo as artwork", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 6.5, apply_watermark: true, negative_prompt: "", num_inference_steps: 33 } } ); // 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 charlesmccarthy/terminus-xl-otaku-v1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", input={ "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": True, "negative_prompt": "", "num_inference_steps": 33 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run charlesmccarthy/terminus-xl-otaku-v1 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": "charlesmccarthy/terminus-xl-otaku-v1:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="jlo as artwork"' \ -i 'scheduler="K_EULER_ANCESTRAL"' \ -i 'num_outputs=1' \ -i 'guidance_scale=6.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=33'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/charlesmccarthy/terminus-xl-otaku-v1@sha256:7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-26T05:24:52.672850Z", "created_at": "2023-12-26T05:24:44.108746Z", "data_removed": false, "error": null, "id": "z4f5ro3beaphl7etukvf7pzkim", "input": { "width": 1024, "height": 1024, "prompt": "jlo as artwork", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 6.5, "apply_watermark": true, "negative_prompt": "", "num_inference_steps": 33 }, "logs": "Using seed: 6031873\n 0%| | 0/33 [00:00<?, ?it/s]\n 6%|▌ | 2/33 [00:00<00:04, 6.82it/s]\n 9%|▉ | 3/33 [00:00<00:05, 5.94it/s]\n 12%|█▏ | 4/33 [00:00<00:05, 5.57it/s]\n 15%|█▌ | 5/33 [00:00<00:05, 5.37it/s]\n 18%|█▊ | 6/33 [00:01<00:05, 5.23it/s]\n 21%|██ | 7/33 [00:01<00:05, 5.16it/s]\n 24%|██▍ | 8/33 [00:01<00:04, 5.12it/s]\n 27%|██▋ | 9/33 [00:01<00:04, 5.08it/s]\n 30%|███ | 10/33 [00:01<00:04, 5.06it/s]\n 33%|███▎ | 11/33 [00:02<00:04, 5.04it/s]\n 36%|███▋ | 12/33 [00:02<00:04, 5.03it/s]\n 39%|███▉ | 13/33 [00:02<00:03, 5.02it/s]\n 42%|████▏ | 14/33 [00:02<00:03, 5.02it/s]\n 45%|████▌ | 15/33 [00:02<00:03, 5.01it/s]\n 48%|████▊ | 16/33 [00:03<00:03, 5.01it/s]\n 52%|█████▏ | 17/33 [00:03<00:03, 5.00it/s]\n 55%|█████▍ | 18/33 [00:03<00:03, 5.00it/s]\n 58%|█████▊ | 19/33 [00:03<00:02, 4.99it/s]\n 61%|██████ | 20/33 [00:03<00:02, 4.99it/s]\n 64%|██████▎ | 21/33 [00:04<00:02, 4.99it/s]\n 67%|██████▋ | 22/33 [00:04<00:02, 4.99it/s]\n 70%|██████▉ | 23/33 [00:04<00:02, 4.98it/s]\n 73%|███████▎ | 24/33 [00:04<00:01, 4.98it/s]\n 76%|███████▌ | 25/33 [00:04<00:01, 4.98it/s]\n 79%|███████▉ | 26/33 [00:05<00:01, 4.98it/s]\n 82%|████████▏ | 27/33 [00:05<00:01, 4.98it/s]\n 85%|████████▍ | 28/33 [00:05<00:01, 4.98it/s]\n 88%|████████▊ | 29/33 [00:05<00:00, 4.97it/s]\n 91%|█████████ | 30/33 [00:05<00:00, 4.98it/s]\n 94%|█████████▍| 31/33 [00:06<00:00, 4.98it/s]\n 97%|█████████▋| 32/33 [00:06<00:00, 4.98it/s]\n100%|██████████| 33/33 [00:06<00:00, 4.98it/s]\n100%|██████████| 33/33 [00:06<00:00, 5.08it/s]", "metrics": { "predict_time": 8.527941, "total_time": 8.564104 }, "output": [ "https://replicate.delivery/pbxt/4yHLkENPZlLeISTt96eXjfMbDu2TUAelsai1G5h6r3fY0KwQC/out-0.png" ], "started_at": "2023-12-26T05:24:44.144909Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/z4f5ro3beaphl7etukvf7pzkim", "cancel": "https://api.replicate.com/v1/predictions/z4f5ro3beaphl7etukvf7pzkim/cancel" }, "version": "7a63fb93cb78f93bab3470e8042d256d2ea88c2a21d2df16e253ed4263b2bcca" }
Generated inUsing seed: 6031873 0%| | 0/33 [00:00<?, ?it/s] 6%|▌ | 2/33 [00:00<00:04, 6.82it/s] 9%|▉ | 3/33 [00:00<00:05, 5.94it/s] 12%|█▏ | 4/33 [00:00<00:05, 5.57it/s] 15%|█▌ | 5/33 [00:00<00:05, 5.37it/s] 18%|█▊ | 6/33 [00:01<00:05, 5.23it/s] 21%|██ | 7/33 [00:01<00:05, 5.16it/s] 24%|██▍ | 8/33 [00:01<00:04, 5.12it/s] 27%|██▋ | 9/33 [00:01<00:04, 5.08it/s] 30%|███ | 10/33 [00:01<00:04, 5.06it/s] 33%|███▎ | 11/33 [00:02<00:04, 5.04it/s] 36%|███▋ | 12/33 [00:02<00:04, 5.03it/s] 39%|███▉ | 13/33 [00:02<00:03, 5.02it/s] 42%|████▏ | 14/33 [00:02<00:03, 5.02it/s] 45%|████▌ | 15/33 [00:02<00:03, 5.01it/s] 48%|████▊ | 16/33 [00:03<00:03, 5.01it/s] 52%|█████▏ | 17/33 [00:03<00:03, 5.00it/s] 55%|█████▍ | 18/33 [00:03<00:03, 5.00it/s] 58%|█████▊ | 19/33 [00:03<00:02, 4.99it/s] 61%|██████ | 20/33 [00:03<00:02, 4.99it/s] 64%|██████▎ | 21/33 [00:04<00:02, 4.99it/s] 67%|██████▋ | 22/33 [00:04<00:02, 4.99it/s] 70%|██████▉ | 23/33 [00:04<00:02, 4.98it/s] 73%|███████▎ | 24/33 [00:04<00:01, 4.98it/s] 76%|███████▌ | 25/33 [00:04<00:01, 4.98it/s] 79%|███████▉ | 26/33 [00:05<00:01, 4.98it/s] 82%|████████▏ | 27/33 [00:05<00:01, 4.98it/s] 85%|████████▍ | 28/33 [00:05<00:01, 4.98it/s] 88%|████████▊ | 29/33 [00:05<00:00, 4.97it/s] 91%|█████████ | 30/33 [00:05<00:00, 4.98it/s] 94%|█████████▍| 31/33 [00:06<00:00, 4.98it/s] 97%|█████████▋| 32/33 [00:06<00:00, 4.98it/s] 100%|██████████| 33/33 [00:06<00:00, 4.98it/s] 100%|██████████| 33/33 [00:06<00:00, 5.08it/s]
Want to make some of these yourself?
Run this model