chigozienri/visual-anagrams

Generates multi-view optical illusions

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt




batch or individual face detection with mediapipe
Animate Your Personalized Text-to-Image Diffusion Models (Long boot times!)

Take a list of image URLs as frames and output a video

Extracts motion from video

Create driving poses for magic-animate

Depth Controlnet, but fuzzier
Prediction
chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111adIDccgcpilbvmdxlnnk4tvk7xje5yStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 0
- style
- an oil painting of
- video
- views
- identity, jigsaw
- prompts
- a rabbit, a coffee cup
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "seed": 0, "style": "an oil painting of ", "video": true, "views": "identity, jigsaw", "prompts": "a rabbit, a coffee cup", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", { input: { seed: 0, style: "an oil painting of ", video: true, views: "identity, jigsaw", prompts: "a rabbit, a coffee cup", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", input={ "seed": 0, "style": "an oil painting of ", "video": True, "views": "identity, jigsaw", "prompts": "a rabbit, a coffee cup", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", "input": { "seed": 0, "style": "an oil painting of ", "video": true, "views": "identity, jigsaw", "prompts": "a rabbit, a coffee cup", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad \ -i 'seed=0' \ -i 'style="an oil painting of "' \ -i 'video=true' \ -i 'views="identity, jigsaw"' \ -i 'prompts="a rabbit, a coffee cup"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 0, "style": "an oil painting of ", "video": true, "views": "identity, jigsaw", "prompts": "a rabbit, a coffee cup", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:11:12.357938Z", "created_at": "2023-12-01T15:10:31.907791Z", "data_removed": false, "error": null, "id": "ccgcpilbvmdxlnnk4tvk7xje5y", "input": { "seed": 0, "style": "an oil painting of ", "video": true, "views": "identity, jigsaw", "prompts": "a rabbit, a coffee cup", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:22, 1.28it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 5.67it/s]\n 23%|██▎ | 7/30 [00:00<00:02, 9.94it/s]\n 33%|███▎ | 10/30 [00:01<00:01, 13.79it/s]\n 43%|████▎ | 13/30 [00:01<00:00, 17.13it/s]\n 53%|█████▎ | 16/30 [00:01<00:00, 19.95it/s]\n 63%|██████▎ | 19/30 [00:01<00:00, 22.06it/s]\n 73%|███████▎ | 22/30 [00:01<00:00, 23.68it/s]\n 83%|████████▎ | 25/30 [00:01<00:00, 25.04it/s]\n 93%|█████████▎| 28/30 [00:01<00:00, 25.83it/s]\n100%|██████████| 30/30 [00:01<00:00, 16.58it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:05, 5.44it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.08it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.31it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 6.44it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.52it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.56it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.58it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.58it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.58it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.58it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.59it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.61it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.61it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.62it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.62it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.62it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.62it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.63it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.63it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.63it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.61it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.60it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.58it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.59it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.61it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.61it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.62it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.61it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.61it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.72it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.58it/s]\n['sample_256.png', 'sample_256.views.png']\n 0%| | 0/45 [00:00<?, ?it/s]\n 4%|▍ | 2/45 [00:00<00:03, 12.93it/s]\n 9%|▉ | 4/45 [00:00<00:03, 12.98it/s]\n 13%|█▎ | 6/45 [00:00<00:03, 12.93it/s]\n 18%|█▊ | 8/45 [00:00<00:02, 12.80it/s]\n 22%|██▏ | 10/45 [00:00<00:02, 12.85it/s]\n 27%|██▋ | 12/45 [00:00<00:02, 12.87it/s]\n 31%|███ | 14/45 [00:01<00:02, 12.79it/s]\n 36%|███▌ | 16/45 [00:01<00:02, 12.79it/s]\n 40%|████ | 18/45 [00:01<00:02, 12.74it/s]\n 44%|████▍ | 20/45 [00:01<00:01, 12.65it/s]\n 49%|████▉ | 22/45 [00:01<00:01, 12.51it/s]\n 53%|█████▎ | 24/45 [00:01<00:01, 12.37it/s]\n 58%|█████▊ | 26/45 [00:02<00:01, 12.31it/s]\n 62%|██████▏ | 28/45 [00:02<00:01, 12.34it/s]\n 67%|██████▋ | 30/45 [00:02<00:01, 12.46it/s]\n 71%|███████ | 32/45 [00:02<00:01, 12.56it/s]\n 76%|███████▌ | 34/45 [00:02<00:00, 12.65it/s]\n 80%|████████ | 36/45 [00:02<00:00, 12.74it/s]\n 84%|████████▍ | 38/45 [00:02<00:00, 12.80it/s]\n 89%|████████▉ | 40/45 [00:03<00:00, 12.82it/s]\n 93%|█████████▎| 42/45 [00:03<00:00, 12.85it/s]\n 98%|█████████▊| 44/45 [00:03<00:00, 12.87it/s]\n100%|██████████| 45/45 [00:03<00:00, 12.71it/s]\nMaking video...", "metrics": { "predict_time": 14.484609, "total_time": 40.450147 }, "output": [ "https://replicate.delivery/pbxt/sPu0nDgiLNaMBNHKkb9sOGPq2SPbwarQ7vQ5zceZXxIHT9eRA/sample_256.png", "https://replicate.delivery/pbxt/6ixQniHGvzoAABokrBq69ZgWQCROw8FNvZ7VURxtIfnHT9eRA/sample_256.views.png", "https://replicate.delivery/pbxt/48CpFwa9KfTkXyrRJ6G4miix87br5zFrIo0b6hlGmm5HT9eRA/video.mp4" ], "started_at": "2023-12-01T15:10:57.873329Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ccgcpilbvmdxlnnk4tvk7xje5y", "cancel": "https://api.replicate.com/v1/predictions/ccgcpilbvmdxlnnk4tvk7xje5y/cancel" }, "version": "100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:22, 1.28it/s] 13%|█▎ | 4/30 [00:00<00:04, 5.67it/s] 23%|██▎ | 7/30 [00:00<00:02, 9.94it/s] 33%|███▎ | 10/30 [00:01<00:01, 13.79it/s] 43%|████▎ | 13/30 [00:01<00:00, 17.13it/s] 53%|█████▎ | 16/30 [00:01<00:00, 19.95it/s] 63%|██████▎ | 19/30 [00:01<00:00, 22.06it/s] 73%|███████▎ | 22/30 [00:01<00:00, 23.68it/s] 83%|████████▎ | 25/30 [00:01<00:00, 25.04it/s] 93%|█████████▎| 28/30 [00:01<00:00, 25.83it/s] 100%|██████████| 30/30 [00:01<00:00, 16.58it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:05, 5.44it/s] 7%|▋ | 2/30 [00:00<00:04, 6.08it/s] 10%|█ | 3/30 [00:00<00:04, 6.31it/s] 13%|█▎ | 4/30 [00:00<00:04, 6.44it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.52it/s] 20%|██ | 6/30 [00:00<00:03, 6.56it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.58it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.58it/s] 30%|███ | 9/30 [00:01<00:03, 6.58it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.58it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.59it/s] 40%|████ | 12/30 [00:01<00:02, 6.61it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.61it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.62it/s] 50%|█████ | 15/30 [00:02<00:02, 6.62it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.62it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.62it/s] 60%|██████ | 18/30 [00:02<00:01, 6.63it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.63it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.63it/s] 70%|███████ | 21/30 [00:03<00:01, 6.61it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.60it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.58it/s] 80%|████████ | 24/30 [00:03<00:00, 6.59it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.61it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.61it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.62it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.61it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.61it/s] 100%|██████████| 30/30 [00:04<00:00, 6.72it/s] 100%|██████████| 30/30 [00:04<00:00, 6.58it/s] ['sample_256.png', 'sample_256.views.png'] 0%| | 0/45 [00:00<?, ?it/s] 4%|▍ | 2/45 [00:00<00:03, 12.93it/s] 9%|▉ | 4/45 [00:00<00:03, 12.98it/s] 13%|█▎ | 6/45 [00:00<00:03, 12.93it/s] 18%|█▊ | 8/45 [00:00<00:02, 12.80it/s] 22%|██▏ | 10/45 [00:00<00:02, 12.85it/s] 27%|██▋ | 12/45 [00:00<00:02, 12.87it/s] 31%|███ | 14/45 [00:01<00:02, 12.79it/s] 36%|███▌ | 16/45 [00:01<00:02, 12.79it/s] 40%|████ | 18/45 [00:01<00:02, 12.74it/s] 44%|████▍ | 20/45 [00:01<00:01, 12.65it/s] 49%|████▉ | 22/45 [00:01<00:01, 12.51it/s] 53%|█████▎ | 24/45 [00:01<00:01, 12.37it/s] 58%|█████▊ | 26/45 [00:02<00:01, 12.31it/s] 62%|██████▏ | 28/45 [00:02<00:01, 12.34it/s] 67%|██████▋ | 30/45 [00:02<00:01, 12.46it/s] 71%|███████ | 32/45 [00:02<00:01, 12.56it/s] 76%|███████▌ | 34/45 [00:02<00:00, 12.65it/s] 80%|████████ | 36/45 [00:02<00:00, 12.74it/s] 84%|████████▍ | 38/45 [00:02<00:00, 12.80it/s] 89%|████████▉ | 40/45 [00:03<00:00, 12.82it/s] 93%|█████████▎| 42/45 [00:03<00:00, 12.85it/s] 98%|█████████▊| 44/45 [00:03<00:00, 12.87it/s] 100%|██████████| 45/45 [00:03<00:00, 12.71it/s] Making video...
Prediction
chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111adIDyy26pedbkxaac3owmpzoug35rmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 2
- style
- an oil painting of
- video
- views
- identity, inner_circle
- prompts
- albert einstein, marilyn monroe
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "seed": 2, "style": "an oil painting of ", "video": true, "views": "identity, inner_circle", "prompts": "albert einstein, marilyn monroe", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", { input: { seed: 2, style: "an oil painting of ", video: true, views: "identity, inner_circle", prompts: "albert einstein, marilyn monroe", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", input={ "seed": 2, "style": "an oil painting of ", "video": True, "views": "identity, inner_circle", "prompts": "albert einstein, marilyn monroe", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad", "input": { "seed": 2, "style": "an oil painting of ", "video": true, "views": "identity, inner_circle", "prompts": "albert einstein, marilyn monroe", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad \ -i 'seed=2' \ -i 'style="an oil painting of "' \ -i 'video=true' \ -i 'views="identity, inner_circle"' \ -i 'prompts="albert einstein, marilyn monroe"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 2, "style": "an oil painting of ", "video": true, "views": "identity, inner_circle", "prompts": "albert einstein, marilyn monroe", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:22:59.839887Z", "created_at": "2023-12-01T15:22:50.983615Z", "data_removed": false, "error": null, "id": "yy26pedbkxaac3owmpzoug35rm", "input": { "seed": 2, "style": "an oil painting of ", "video": true, "views": "identity, inner_circle", "prompts": "albert einstein, marilyn monroe", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 10%|█ | 3/30 [00:00<00:00, 27.70it/s]\n 20%|██ | 6/30 [00:00<00:00, 28.03it/s]\n 30%|███ | 9/30 [00:00<00:00, 28.08it/s]\n 40%|████ | 12/30 [00:00<00:00, 27.91it/s]\n 50%|█████ | 15/30 [00:00<00:00, 27.96it/s]\n 60%|██████ | 18/30 [00:00<00:00, 28.18it/s]\n 70%|███████ | 21/30 [00:00<00:00, 28.25it/s]\n 80%|████████ | 24/30 [00:00<00:00, 28.28it/s]\n 90%|█████████ | 27/30 [00:00<00:00, 28.01it/s]\n100%|██████████| 30/30 [00:01<00:00, 28.17it/s]\n100%|██████████| 30/30 [00:01<00:00, 28.10it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.66it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.64it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.62it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.61it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.60it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.59it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.59it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.58it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.57it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.58it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.60it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.61it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.61it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.60it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.58it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.59it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.60it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.59it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.60it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.61it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.61it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.59it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.59it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.58it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.59it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.59it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.61it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.61it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.62it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.74it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.61it/s]\n['sample_256.png', 'sample_256.views.png']\n 0%| | 0/45 [00:00<?, ?it/s]\n 40%|████ | 18/45 [00:00<00:00, 174.20it/s]\n 80%|████████ | 36/45 [00:00<00:00, 151.17it/s]\n100%|██████████| 45/45 [00:00<00:00, 149.63it/s]\nMaking video...", "metrics": { "predict_time": 8.816108, "total_time": 8.856272 }, "output": [ "https://replicate.delivery/pbxt/DO4eA6hiVcxacqH8LhU3FEe0ZWKMaBaufNSesgWjO2QLFr3HB/sample_256.png", "https://replicate.delivery/pbxt/Z6K83uU612ZUOxW2cLDKjhGn1qyaRkJ4aLBP00eSTX4pY9eRA/sample_256.views.png", "https://replicate.delivery/pbxt/1ow1z7EsVa4IEx5WnXwSpml2hw1bFiXeDQ6izB8gfZiTx69RA/video.mp4" ], "started_at": "2023-12-01T15:22:51.023779Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yy26pedbkxaac3owmpzoug35rm", "cancel": "https://api.replicate.com/v1/predictions/yy26pedbkxaac3owmpzoug35rm/cancel" }, "version": "100c73f4ba9aa10844639e97a471f5f3065963eccb9e7a7cb4d2dc48c2d111ad" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 10%|█ | 3/30 [00:00<00:00, 27.70it/s] 20%|██ | 6/30 [00:00<00:00, 28.03it/s] 30%|███ | 9/30 [00:00<00:00, 28.08it/s] 40%|████ | 12/30 [00:00<00:00, 27.91it/s] 50%|█████ | 15/30 [00:00<00:00, 27.96it/s] 60%|██████ | 18/30 [00:00<00:00, 28.18it/s] 70%|███████ | 21/30 [00:00<00:00, 28.25it/s] 80%|████████ | 24/30 [00:00<00:00, 28.28it/s] 90%|█████████ | 27/30 [00:00<00:00, 28.01it/s] 100%|██████████| 30/30 [00:01<00:00, 28.17it/s] 100%|██████████| 30/30 [00:01<00:00, 28.10it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.66it/s] 7%|▋ | 2/30 [00:00<00:04, 6.64it/s] 10%|█ | 3/30 [00:00<00:04, 6.62it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.61it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.60it/s] 20%|██ | 6/30 [00:00<00:03, 6.59it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.59it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.58it/s] 30%|███ | 9/30 [00:01<00:03, 6.57it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.58it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.60it/s] 40%|████ | 12/30 [00:01<00:02, 6.61it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.61it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.60it/s] 50%|█████ | 15/30 [00:02<00:02, 6.58it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.59it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.60it/s] 60%|██████ | 18/30 [00:02<00:01, 6.59it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.60it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.61it/s] 70%|███████ | 21/30 [00:03<00:01, 6.61it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.59it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.59it/s] 80%|████████ | 24/30 [00:03<00:00, 6.58it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.59it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.59it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.61it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.61it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.62it/s] 100%|██████████| 30/30 [00:04<00:00, 6.74it/s] 100%|██████████| 30/30 [00:04<00:00, 6.61it/s] ['sample_256.png', 'sample_256.views.png'] 0%| | 0/45 [00:00<?, ?it/s] 40%|████ | 18/45 [00:00<00:00, 174.20it/s] 80%|████████ | 36/45 [00:00<00:00, 151.17it/s] 100%|██████████| 45/45 [00:00<00:00, 149.63it/s] Making video...
Prediction
chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3IDdx3nia3b26gyddc7mptwv45ejyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 3000
- style
- an lithograph of
- video
- views
- identity, negate
- prompts
- a landscape, houseplants
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "seed": 3000, "style": "an lithograph of ", "video": true, "views": "identity, negate", "prompts": "a landscape, houseplants", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", { input: { seed: 3000, style: "an lithograph of ", video: true, views: "identity, negate", prompts: "a landscape, houseplants", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", input={ "seed": 3000, "style": "an lithograph of ", "video": True, "views": "identity, negate", "prompts": "a landscape, houseplants", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", "input": { "seed": 3000, "style": "an lithograph of ", "video": true, "views": "identity, negate", "prompts": "a landscape, houseplants", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3 \ -i 'seed=3000' \ -i 'style="an lithograph of "' \ -i 'video=true' \ -i 'views="identity, negate"' \ -i 'prompts="a landscape, houseplants"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 3000, "style": "an lithograph of ", "video": true, "views": "identity, negate", "prompts": "a landscape, houseplants", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:31:28.886307Z", "created_at": "2023-12-01T15:31:20.391517Z", "data_removed": false, "error": null, "id": "dx3nia3b26gyddc7mptwv45ejy", "input": { "seed": 3000, "style": "an lithograph of ", "video": true, "views": "identity, negate", "prompts": "a landscape, houseplants", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 10%|█ | 3/30 [00:00<00:00, 27.31it/s]\n 20%|██ | 6/30 [00:00<00:00, 27.38it/s]\n 30%|███ | 9/30 [00:00<00:00, 27.53it/s]\n 40%|████ | 12/30 [00:00<00:00, 27.78it/s]\n 50%|█████ | 15/30 [00:00<00:00, 27.62it/s]\n 60%|██████ | 18/30 [00:00<00:00, 27.56it/s]\n 70%|███████ | 21/30 [00:00<00:00, 27.86it/s]\n 80%|████████ | 24/30 [00:00<00:00, 28.05it/s]\n 90%|█████████ | 27/30 [00:00<00:00, 28.13it/s]\n100%|██████████| 30/30 [00:01<00:00, 28.00it/s]\n100%|██████████| 30/30 [00:01<00:00, 27.82it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.61it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.59it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.59it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.58it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.58it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.58it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.58it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.57it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.57it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.57it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.57it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.56it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.56it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.56it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.56it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.55it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.55it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.55it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.57it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.57it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.58it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.59it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.59it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.59it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.59it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.60it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.60it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.60it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.60it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.71it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.59it/s]\n['sample_256.png', 'sample_256.views.png']\n 0%| | 0/45 [00:00<?, ?it/s]\n100%|██████████| 45/45 [00:00<00:00, 1253.56it/s]\nMaking video...", "metrics": { "predict_time": 8.458147, "total_time": 8.49479 }, "output": [ "https://replicate.delivery/pbxt/LwH44knzenV1IqaYnyGKi51dlFU14inYfU0f1nSFwklfkr3HB/sample_256.png", "https://replicate.delivery/pbxt/JoQ962UrqgrzDZXdUei8BGePEoqA2i2uo8NACKperWahy17jA/sample_256.views.png", "https://replicate.delivery/pbxt/9x3FWun0LwJzDxZ6zI9Zm8jQNpLywF1DlTRYodgAZoFUueeRA/video.mp4" ], "started_at": "2023-12-01T15:31:20.428160Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dx3nia3b26gyddc7mptwv45ejy", "cancel": "https://api.replicate.com/v1/predictions/dx3nia3b26gyddc7mptwv45ejy/cancel" }, "version": "8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 10%|█ | 3/30 [00:00<00:00, 27.31it/s] 20%|██ | 6/30 [00:00<00:00, 27.38it/s] 30%|███ | 9/30 [00:00<00:00, 27.53it/s] 40%|████ | 12/30 [00:00<00:00, 27.78it/s] 50%|█████ | 15/30 [00:00<00:00, 27.62it/s] 60%|██████ | 18/30 [00:00<00:00, 27.56it/s] 70%|███████ | 21/30 [00:00<00:00, 27.86it/s] 80%|████████ | 24/30 [00:00<00:00, 28.05it/s] 90%|█████████ | 27/30 [00:00<00:00, 28.13it/s] 100%|██████████| 30/30 [00:01<00:00, 28.00it/s] 100%|██████████| 30/30 [00:01<00:00, 27.82it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.61it/s] 7%|▋ | 2/30 [00:00<00:04, 6.59it/s] 10%|█ | 3/30 [00:00<00:04, 6.59it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.58it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.58it/s] 20%|██ | 6/30 [00:00<00:03, 6.58it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.58it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.57it/s] 30%|███ | 9/30 [00:01<00:03, 6.57it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.57it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.57it/s] 40%|████ | 12/30 [00:01<00:02, 6.56it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.56it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.56it/s] 50%|█████ | 15/30 [00:02<00:02, 6.56it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.55it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.55it/s] 60%|██████ | 18/30 [00:02<00:01, 6.55it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.57it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.57it/s] 70%|███████ | 21/30 [00:03<00:01, 6.58it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.59it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.59it/s] 80%|████████ | 24/30 [00:03<00:00, 6.59it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.59it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.60it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.60it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.60it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.60it/s] 100%|██████████| 30/30 [00:04<00:00, 6.71it/s] 100%|██████████| 30/30 [00:04<00:00, 6.59it/s] ['sample_256.png', 'sample_256.views.png'] 0%| | 0/45 [00:00<?, ?it/s] 100%|██████████| 45/45 [00:00<00:00, 1253.56it/s] Making video...
Prediction
chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3IDkzmjagdbsljosvdekzaofdx6gqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- style
- an oil painting of
- video
- views
- identity, skew
- prompts
- a tudor portrait, a skull
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "style": "an oil painting of ", "video": true, "views": "identity, skew", "prompts": "a tudor portrait, a skull", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", { input: { style: "an oil painting of ", video: true, views: "identity, skew", prompts: "a tudor portrait, a skull", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", input={ "style": "an oil painting of ", "video": True, "views": "identity, skew", "prompts": "a tudor portrait, a skull", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3", "input": { "style": "an oil painting of ", "video": true, "views": "identity, skew", "prompts": "a tudor portrait, a skull", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3 \ -i 'style="an oil painting of "' \ -i 'video=true' \ -i 'views="identity, skew"' \ -i 'prompts="a tudor portrait, a skull"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "style": "an oil painting of ", "video": true, "views": "identity, skew", "prompts": "a tudor portrait, a skull", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:44:57.575374Z", "created_at": "2023-12-01T15:44:48.446975Z", "data_removed": false, "error": null, "id": "kzmjagdbsljosvdekzaofdx6gq", "input": { "style": "an oil painting of ", "video": true, "views": "identity, skew", "prompts": "a tudor portrait, a skull", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 10%|█ | 3/30 [00:00<00:01, 25.17it/s]\n 20%|██ | 6/30 [00:00<00:00, 25.35it/s]\n 30%|███ | 9/30 [00:00<00:00, 25.97it/s]\n 40%|████ | 12/30 [00:00<00:00, 26.27it/s]\n 50%|█████ | 15/30 [00:00<00:00, 26.12it/s]\n 60%|██████ | 18/30 [00:00<00:00, 26.37it/s]\n 70%|███████ | 21/30 [00:00<00:00, 26.25it/s]\n 80%|████████ | 24/30 [00:00<00:00, 26.39it/s]\n 90%|█████████ | 27/30 [00:01<00:00, 26.56it/s]\n100%|██████████| 30/30 [00:01<00:00, 26.54it/s]\n100%|██████████| 30/30 [00:01<00:00, 26.28it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.25it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.25it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.25it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 6.23it/s]\n 17%|█▋ | 5/30 [00:00<00:04, 6.24it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.25it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.26it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.24it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.24it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.24it/s]\n 37%|███▋ | 11/30 [00:01<00:03, 6.25it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.23it/s]\n 43%|████▎ | 13/30 [00:02<00:02, 6.24it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.24it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.25it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.24it/s]\n 57%|█████▋ | 17/30 [00:02<00:02, 6.25it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.26it/s]\n 63%|██████▎ | 19/30 [00:03<00:01, 6.27it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.26it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.27it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.26it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.26it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.25it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.26it/s]\n 87%|████████▋ | 26/30 [00:04<00:00, 6.26it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.27it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.26it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.26it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.37it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.26it/s]\n['sample_256.png', 'sample_256.views.png']\n 0%| | 0/45 [00:00<?, ?it/s]\n 27%|██▋ | 12/45 [00:00<00:00, 116.56it/s]\n 60%|██████ | 27/45 [00:00<00:00, 135.27it/s]\n 93%|█████████▎| 42/45 [00:00<00:00, 141.01it/s]\n100%|██████████| 45/45 [00:00<00:00, 138.03it/s]\nMaking video...", "metrics": { "predict_time": 9.093037, "total_time": 9.128399 }, "output": [ "https://replicate.delivery/pbxt/LOi4RUWN6BJUJFXuIvL6dpx40A7hxiud2ItkZ9HHCeC8i9eRA/sample_256.png", "https://replicate.delivery/pbxt/Ee1elGsY4Bluq0ALnSa3VyhS6xfiHrZRUCofZ0EDfmxCvYvPC/sample_256.views.png", "https://replicate.delivery/pbxt/0yU3CohDAf0kJC32S4MrVG7FcHFUISnRiZ1ktRInuu48i9eRA/video.mp4" ], "started_at": "2023-12-01T15:44:48.482337Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/kzmjagdbsljosvdekzaofdx6gq", "cancel": "https://api.replicate.com/v1/predictions/kzmjagdbsljosvdekzaofdx6gq/cancel" }, "version": "8fae0986b91add9ad648a80fd48e41d8903cd4397bf12ed0067828cbc4cfb0b3" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 10%|█ | 3/30 [00:00<00:01, 25.17it/s] 20%|██ | 6/30 [00:00<00:00, 25.35it/s] 30%|███ | 9/30 [00:00<00:00, 25.97it/s] 40%|████ | 12/30 [00:00<00:00, 26.27it/s] 50%|█████ | 15/30 [00:00<00:00, 26.12it/s] 60%|██████ | 18/30 [00:00<00:00, 26.37it/s] 70%|███████ | 21/30 [00:00<00:00, 26.25it/s] 80%|████████ | 24/30 [00:00<00:00, 26.39it/s] 90%|█████████ | 27/30 [00:01<00:00, 26.56it/s] 100%|██████████| 30/30 [00:01<00:00, 26.54it/s] 100%|██████████| 30/30 [00:01<00:00, 26.28it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.25it/s] 7%|▋ | 2/30 [00:00<00:04, 6.25it/s] 10%|█ | 3/30 [00:00<00:04, 6.25it/s] 13%|█▎ | 4/30 [00:00<00:04, 6.23it/s] 17%|█▋ | 5/30 [00:00<00:04, 6.24it/s] 20%|██ | 6/30 [00:00<00:03, 6.25it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.26it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.24it/s] 30%|███ | 9/30 [00:01<00:03, 6.24it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.24it/s] 37%|███▋ | 11/30 [00:01<00:03, 6.25it/s] 40%|████ | 12/30 [00:01<00:02, 6.23it/s] 43%|████▎ | 13/30 [00:02<00:02, 6.24it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.24it/s] 50%|█████ | 15/30 [00:02<00:02, 6.25it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.24it/s] 57%|█████▋ | 17/30 [00:02<00:02, 6.25it/s] 60%|██████ | 18/30 [00:02<00:01, 6.26it/s] 63%|██████▎ | 19/30 [00:03<00:01, 6.27it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.26it/s] 70%|███████ | 21/30 [00:03<00:01, 6.27it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.26it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.26it/s] 80%|████████ | 24/30 [00:03<00:00, 6.25it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.26it/s] 87%|████████▋ | 26/30 [00:04<00:00, 6.26it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.27it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.26it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.26it/s] 100%|██████████| 30/30 [00:04<00:00, 6.37it/s] 100%|██████████| 30/30 [00:04<00:00, 6.26it/s] ['sample_256.png', 'sample_256.views.png'] 0%| | 0/45 [00:00<?, ?it/s] 27%|██▋ | 12/45 [00:00<00:00, 116.56it/s] 60%|██████ | 27/45 [00:00<00:00, 135.27it/s] 93%|█████████▎| 42/45 [00:00<00:00, 141.01it/s] 100%|██████████| 45/45 [00:00<00:00, 138.03it/s] Making video...
Prediction
chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5IDtevxgfdbhc3ynz6vrv4d2cns6uStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 5000
- style
- an oil painting of
- video
- views
- identity, rotate_cw, rotate_ccw
- prompts
- a waterfall, a teddy bear, a rabbit
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "seed": 5000, "style": "an oil painting of ", "video": false, "views": "identity, rotate_cw, rotate_ccw", "prompts": "a waterfall, a teddy bear, a rabbit", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", { input: { seed: 5000, style: "an oil painting of ", video: false, views: "identity, rotate_cw, rotate_ccw", prompts: "a waterfall, a teddy bear, a rabbit", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", input={ "seed": 5000, "style": "an oil painting of ", "video": False, "views": "identity, rotate_cw, rotate_ccw", "prompts": "a waterfall, a teddy bear, a rabbit", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", "input": { "seed": 5000, "style": "an oil painting of ", "video": false, "views": "identity, rotate_cw, rotate_ccw", "prompts": "a waterfall, a teddy bear, a rabbit", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5 \ -i 'seed=5000' \ -i 'style="an oil painting of "' \ -i 'video=false' \ -i 'views="identity, rotate_cw, rotate_ccw"' \ -i 'prompts="a waterfall, a teddy bear, a rabbit"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 5000, "style": "an oil painting of ", "video": false, "views": "identity, rotate_cw, rotate_ccw", "prompts": "a waterfall, a teddy bear, a rabbit", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:51:15.907229Z", "created_at": "2023-12-01T15:51:06.223818Z", "data_removed": false, "error": null, "id": "tevxgfdbhc3ynz6vrv4d2cns6u", "input": { "seed": 5000, "style": "an oil painting of ", "video": false, "views": "identity, rotate_cw, rotate_ccw", "prompts": "a waterfall, a teddy bear, a rabbit", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 10%|█ | 3/30 [00:00<00:01, 23.87it/s]\n 20%|██ | 6/30 [00:00<00:00, 24.00it/s]\n 30%|███ | 9/30 [00:00<00:00, 24.22it/s]\n 40%|████ | 12/30 [00:00<00:00, 24.23it/s]\n 50%|█████ | 15/30 [00:00<00:00, 24.36it/s]\n 60%|██████ | 18/30 [00:00<00:00, 24.41it/s]\n 70%|███████ | 21/30 [00:00<00:00, 24.40it/s]\n 80%|████████ | 24/30 [00:00<00:00, 24.48it/s]\n 90%|█████████ | 27/30 [00:01<00:00, 24.39it/s]\n100%|██████████| 30/30 [00:01<00:00, 24.35it/s]\n100%|██████████| 30/30 [00:01<00:00, 24.32it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:06, 4.61it/s]\n 7%|▋ | 2/30 [00:00<00:06, 4.65it/s]\n 10%|█ | 3/30 [00:00<00:05, 4.67it/s]\n 13%|█▎ | 4/30 [00:00<00:05, 4.69it/s]\n 17%|█▋ | 5/30 [00:01<00:05, 4.69it/s]\n 20%|██ | 6/30 [00:01<00:05, 4.69it/s]\n 23%|██▎ | 7/30 [00:01<00:04, 4.70it/s]\n 27%|██▋ | 8/30 [00:01<00:04, 4.70it/s]\n 30%|███ | 9/30 [00:01<00:04, 4.70it/s]\n 33%|███▎ | 10/30 [00:02<00:04, 4.70it/s]\n 37%|███▋ | 11/30 [00:02<00:04, 4.70it/s]\n 40%|████ | 12/30 [00:02<00:03, 4.70it/s]\n 43%|████▎ | 13/30 [00:02<00:03, 4.70it/s]\n 47%|████▋ | 14/30 [00:02<00:03, 4.70it/s]\n 50%|█████ | 15/30 [00:03<00:03, 4.71it/s]\n 53%|█████▎ | 16/30 [00:03<00:02, 4.70it/s]\n 57%|█████▋ | 17/30 [00:03<00:02, 4.71it/s]\n 60%|██████ | 18/30 [00:03<00:02, 4.70it/s]\n 63%|██████▎ | 19/30 [00:04<00:02, 4.70it/s]\n 67%|██████▋ | 20/30 [00:04<00:02, 4.69it/s]\n 70%|███████ | 21/30 [00:04<00:01, 4.69it/s]\n 73%|███████▎ | 22/30 [00:04<00:01, 4.70it/s]\n 77%|███████▋ | 23/30 [00:04<00:01, 4.70it/s]\n 80%|████████ | 24/30 [00:05<00:01, 4.70it/s]\n 83%|████████▎ | 25/30 [00:05<00:01, 4.70it/s]\n 87%|████████▋ | 26/30 [00:05<00:00, 4.70it/s]\n 90%|█████████ | 27/30 [00:05<00:00, 4.69it/s]\n 93%|█████████▎| 28/30 [00:05<00:00, 4.70it/s]\n 97%|█████████▋| 29/30 [00:06<00:00, 4.70it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.76it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.70it/s]\n['sample_256.png', 'sample_256.views.png']", "metrics": { "predict_time": 9.629808, "total_time": 9.683411 }, "output": [ "https://replicate.delivery/pbxt/LJuN4eroKLSYcazU6OETK1Hu150V0xejMe8M54CmNukkX27jA/sample_256.png", "https://replicate.delivery/pbxt/B1aphVf12TQ6ZaBveWKLgVnfoNaQBd0Np8ariY7gOdlmX27jA/sample_256.views.png" ], "started_at": "2023-12-01T15:51:06.277421Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/tevxgfdbhc3ynz6vrv4d2cns6u", "cancel": "https://api.replicate.com/v1/predictions/tevxgfdbhc3ynz6vrv4d2cns6u/cancel" }, "version": "5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 10%|█ | 3/30 [00:00<00:01, 23.87it/s] 20%|██ | 6/30 [00:00<00:00, 24.00it/s] 30%|███ | 9/30 [00:00<00:00, 24.22it/s] 40%|████ | 12/30 [00:00<00:00, 24.23it/s] 50%|█████ | 15/30 [00:00<00:00, 24.36it/s] 60%|██████ | 18/30 [00:00<00:00, 24.41it/s] 70%|███████ | 21/30 [00:00<00:00, 24.40it/s] 80%|████████ | 24/30 [00:00<00:00, 24.48it/s] 90%|█████████ | 27/30 [00:01<00:00, 24.39it/s] 100%|██████████| 30/30 [00:01<00:00, 24.35it/s] 100%|██████████| 30/30 [00:01<00:00, 24.32it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:06, 4.61it/s] 7%|▋ | 2/30 [00:00<00:06, 4.65it/s] 10%|█ | 3/30 [00:00<00:05, 4.67it/s] 13%|█▎ | 4/30 [00:00<00:05, 4.69it/s] 17%|█▋ | 5/30 [00:01<00:05, 4.69it/s] 20%|██ | 6/30 [00:01<00:05, 4.69it/s] 23%|██▎ | 7/30 [00:01<00:04, 4.70it/s] 27%|██▋ | 8/30 [00:01<00:04, 4.70it/s] 30%|███ | 9/30 [00:01<00:04, 4.70it/s] 33%|███▎ | 10/30 [00:02<00:04, 4.70it/s] 37%|███▋ | 11/30 [00:02<00:04, 4.70it/s] 40%|████ | 12/30 [00:02<00:03, 4.70it/s] 43%|████▎ | 13/30 [00:02<00:03, 4.70it/s] 47%|████▋ | 14/30 [00:02<00:03, 4.70it/s] 50%|█████ | 15/30 [00:03<00:03, 4.71it/s] 53%|█████▎ | 16/30 [00:03<00:02, 4.70it/s] 57%|█████▋ | 17/30 [00:03<00:02, 4.71it/s] 60%|██████ | 18/30 [00:03<00:02, 4.70it/s] 63%|██████▎ | 19/30 [00:04<00:02, 4.70it/s] 67%|██████▋ | 20/30 [00:04<00:02, 4.69it/s] 70%|███████ | 21/30 [00:04<00:01, 4.69it/s] 73%|███████▎ | 22/30 [00:04<00:01, 4.70it/s] 77%|███████▋ | 23/30 [00:04<00:01, 4.70it/s] 80%|████████ | 24/30 [00:05<00:01, 4.70it/s] 83%|████████▎ | 25/30 [00:05<00:01, 4.70it/s] 87%|████████▋ | 26/30 [00:05<00:00, 4.70it/s] 90%|█████████ | 27/30 [00:05<00:00, 4.69it/s] 93%|█████████▎| 28/30 [00:05<00:00, 4.70it/s] 97%|█████████▋| 29/30 [00:06<00:00, 4.70it/s] 100%|██████████| 30/30 [00:06<00:00, 4.76it/s] 100%|██████████| 30/30 [00:06<00:00, 4.70it/s] ['sample_256.png', 'sample_256.views.png']
Prediction
chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5IDl4j77hdbrcowmxgdcsjfyrga64StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @chigozienriInput
- seed
- 5000
- style
- a gouache painting of
- video
- views
- identity, flip
- prompts
- batman, robin
- noise_level
- 50
- num_samples
- 1
- guidance_scale_1
- 10
- guidance_scale_2
- 10
- num_inference_steps_1
- 30
- num_inference_steps_2
- 30
{ "seed": 5000, "style": "a gouache painting of ", "video": true, "views": "identity, flip", "prompts": "batman, robin", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }
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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", { input: { seed: 5000, style: "a gouache painting of ", video: true, views: "identity, flip", prompts: "batman, robin", noise_level: 50, num_samples: 1, guidance_scale_1: 10, guidance_scale_2: 10, num_inference_steps_1: 30, num_inference_steps_2: 30 } } ); // 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 chigozienri/visual-anagrams using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", input={ "seed": 5000, "style": "a gouache painting of ", "video": True, "views": "identity, flip", "prompts": "batman, robin", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } ) # 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 chigozienri/visual-anagrams 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": "chigozienri/visual-anagrams:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5", "input": { "seed": 5000, "style": "a gouache painting of ", "video": true, "views": "identity, flip", "prompts": "batman, robin", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ 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/chigozienri/visual-anagrams@sha256:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5 \ -i 'seed=5000' \ -i 'style="a gouache painting of "' \ -i 'video=true' \ -i 'views="identity, flip"' \ -i 'prompts="batman, robin"' \ -i 'noise_level=50' \ -i 'num_samples=1' \ -i 'guidance_scale_1=10' \ -i 'guidance_scale_2=10' \ -i 'num_inference_steps_1=30' \ -i 'num_inference_steps_2=30'
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/chigozienri/visual-anagrams@sha256:5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 5000, "style": "a gouache painting of ", "video": true, "views": "identity, flip", "prompts": "batman, robin", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T15:53:23.301300Z", "created_at": "2023-12-01T15:53:14.860778Z", "data_removed": false, "error": null, "id": "l4j77hdbrcowmxgdcsjfyrga64", "input": { "seed": 5000, "style": "a gouache painting of ", "video": true, "views": "identity, flip", "prompts": "batman, robin", "noise_level": 50, "num_samples": 1, "guidance_scale_1": 10, "guidance_scale_2": 10, "num_inference_steps_1": 30, "num_inference_steps_2": 30 }, "logs": "0%| | 0/30 [00:00<?, ?it/s]\n 10%|█ | 3/30 [00:00<00:00, 28.49it/s]\n 20%|██ | 6/30 [00:00<00:00, 28.92it/s]\n 30%|███ | 9/30 [00:00<00:00, 28.67it/s]\n 40%|████ | 12/30 [00:00<00:00, 28.41it/s]\n 50%|█████ | 15/30 [00:00<00:00, 28.69it/s]\n 60%|██████ | 18/30 [00:00<00:00, 28.82it/s]\n 70%|███████ | 21/30 [00:00<00:00, 28.94it/s]\n 80%|████████ | 24/30 [00:00<00:00, 29.01it/s]\n 90%|█████████ | 27/30 [00:00<00:00, 28.83it/s]\n100%|██████████| 30/30 [00:01<00:00, 28.52it/s]\n100%|██████████| 30/30 [00:01<00:00, 28.69it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.74it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.72it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.70it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.69it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.69it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.68it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.69it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.69it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.69it/s]\n 33%|███▎ | 10/30 [00:01<00:02, 6.70it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.69it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.69it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.68it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.68it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.67it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.68it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.67it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.68it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.68it/s]\n 67%|██████▋ | 20/30 [00:02<00:01, 6.68it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.67it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.66it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.66it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.63it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.62it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.63it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.64it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.64it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.65it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.78it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.68it/s]\n['sample_256.png', 'sample_256.views.png']\n 0%| | 0/45 [00:00<?, ?it/s]\n 76%|███████▌ | 34/45 [00:00<00:00, 339.45it/s]\n100%|██████████| 45/45 [00:00<00:00, 337.94it/s]\nMaking video...", "metrics": { "predict_time": 8.401923, "total_time": 8.440522 }, "output": [ "https://replicate.delivery/pbxt/PKwhAY417jYWOpP6e8uDjMlUdU96BKUKpP1RXzZcbqr4m9eRA/sample_256.png", "https://replicate.delivery/pbxt/NRRCQlTClbLKJtm8hiUf6dVTL193CV7Q6VqNZQXG8sfyN79RA/sample_256.views.png", "https://replicate.delivery/pbxt/tA1R4dMO9YaPHFyZ4JgE6P2gFVykhj3nKHL6a8cecv15m9eRA/video.mp4" ], "started_at": "2023-12-01T15:53:14.899377Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/l4j77hdbrcowmxgdcsjfyrga64", "cancel": "https://api.replicate.com/v1/predictions/l4j77hdbrcowmxgdcsjfyrga64/cancel" }, "version": "5c61f70ae59284244dc509018a3d7f50f257eab5eeb064e670028a54a4ef8dd5" }
Generated in0%| | 0/30 [00:00<?, ?it/s] 10%|█ | 3/30 [00:00<00:00, 28.49it/s] 20%|██ | 6/30 [00:00<00:00, 28.92it/s] 30%|███ | 9/30 [00:00<00:00, 28.67it/s] 40%|████ | 12/30 [00:00<00:00, 28.41it/s] 50%|█████ | 15/30 [00:00<00:00, 28.69it/s] 60%|██████ | 18/30 [00:00<00:00, 28.82it/s] 70%|███████ | 21/30 [00:00<00:00, 28.94it/s] 80%|████████ | 24/30 [00:00<00:00, 29.01it/s] 90%|█████████ | 27/30 [00:00<00:00, 28.83it/s] 100%|██████████| 30/30 [00:01<00:00, 28.52it/s] 100%|██████████| 30/30 [00:01<00:00, 28.69it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.74it/s] 7%|▋ | 2/30 [00:00<00:04, 6.72it/s] 10%|█ | 3/30 [00:00<00:04, 6.70it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.69it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.69it/s] 20%|██ | 6/30 [00:00<00:03, 6.68it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.69it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.69it/s] 30%|███ | 9/30 [00:01<00:03, 6.69it/s] 33%|███▎ | 10/30 [00:01<00:02, 6.70it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.69it/s] 40%|████ | 12/30 [00:01<00:02, 6.69it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.68it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.68it/s] 50%|█████ | 15/30 [00:02<00:02, 6.67it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.68it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.67it/s] 60%|██████ | 18/30 [00:02<00:01, 6.68it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.68it/s] 67%|██████▋ | 20/30 [00:02<00:01, 6.68it/s] 70%|███████ | 21/30 [00:03<00:01, 6.67it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.66it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.66it/s] 80%|████████ | 24/30 [00:03<00:00, 6.63it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.62it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.63it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.64it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.64it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.65it/s] 100%|██████████| 30/30 [00:04<00:00, 6.78it/s] 100%|██████████| 30/30 [00:04<00:00, 6.68it/s] ['sample_256.png', 'sample_256.views.png'] 0%| | 0/45 [00:00<?, ?it/s] 76%|███████▌ | 34/45 [00:00<00:00, 339.45it/s] 100%|██████████| 45/45 [00:00<00:00, 337.94it/s] Making video...
Want to make some of these yourself?
Run this model