Versions
03914a0c
Latest
You're looking at a specific version of this model. Jump to the model overview.
grandlineai /instant-id-photorealistic:03914a0c
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=grandlineai/instant-id-photorealistic
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run grandlineai/instant-id-photorealistic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"grandlineai/instant-id-photorealistic:03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279",
{
input: {
image: "https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png",
width: 640,
height: 640,
prompt: "Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality",
guidance_scale: 5,
negative_prompt: "older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands",
ip_adapter_scale: 0.8,
num_inference_steps: 30,
controlnet_conditioning_scale: 0.8
}
}
);
// To access the file URL:
console.log(output.url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:
pip install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:
import replicateRun grandlineai/instant-id-photorealistic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"grandlineai/instant-id-photorealistic:03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279",
input={
"image": "https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png",
"width": 640,
"height": 640,
"prompt": "Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality",
"guidance_scale": 5,
"negative_prompt": "older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands",
"ip_adapter_scale": 0.8,
"num_inference_steps": 30,
"controlnet_conditioning_scale": 0.8
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
Set the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run grandlineai/instant-id-photorealistic 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": "03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279",
"input": {
"image": "https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png",
"width": 640,
"height": 640,
"prompt": "Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality",
"guidance_scale": 5,
"negative_prompt": "older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands",
"ip_adapter_scale": 0.8,
"num_inference_steps": 30,
"controlnet_conditioning_scale": 0.8
}
}' \
https://api.replicate.com/v1/predictionsTo 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 cogIf 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/grandlineai/instant-id-photorealistic@sha256:03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279 \
-i 'image="https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png"' \
-i 'width=640' \
-i 'height=640' \
-i 'prompt="Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality"' \
-i 'guidance_scale=5' \
-i 'negative_prompt="older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands"' \
-i 'ip_adapter_scale=0.8' \
-i 'num_inference_steps=30' \
-i 'controlnet_conditioning_scale=0.8'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/grandlineai/instant-id-photorealistic@sha256:03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "image": "https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png", "width": 640, "height": 640, "prompt": "Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality", "guidance_scale": 5, "negative_prompt": "older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands", "ip_adapter_scale": 0.8, "num_inference_steps": 30, "controlnet_conditioning_scale": 0.8 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Add a payment method to run this model.
Each run costs approximately $0.038. Alternatively, try out our featured models for free.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2024-01-24T08:28:26.011023Z",
"created_at": "2024-01-24T08:25:02.088377Z",
"data_removed": false,
"error": null,
"id": "r4hhsklbyp5opajiuvh5mho7ae",
"input": {
"image": "https://replicate.delivery/pbxt/KHU47j4Ad3rbq6TVxRuwFhyyX6HYmWrCSlUuVOM3q3ORKgVt/demo.png",
"width": 640,
"height": 640,
"prompt": "Create an image of a happy woman in soft pastel clothes under blooming cherry blossom trees. The scene is filled with soft high_key lighting, highlighting the gentle rose petals and happy expressions on their faces. The composition should have a shallow depth of field and a romantic spring atmosphere, high quality",
"guidance_scale": 5,
"negative_prompt": "older, eyes, crowfoot, crows feet, crows foot, old, wrinkles, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, bad hands",
"ip_adapter_scale": 0.8,
"num_inference_steps": 30,
"controlnet_conditioning_scale": 0.8
},
"logs": "/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/insightface/utils/transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.\nTo use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.\nP = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:28, 1.01it/s]\n 7%|▋ | 2/30 [00:01<00:22, 1.23it/s]\n 10%|█ | 3/30 [00:02<00:20, 1.33it/s]\n 13%|█▎ | 4/30 [00:03<00:18, 1.37it/s]\n 17%|█▋ | 5/30 [00:03<00:17, 1.40it/s]\n 20%|██ | 6/30 [00:04<00:16, 1.42it/s]\n 23%|██▎ | 7/30 [00:05<00:16, 1.43it/s]\n 27%|██▋ | 8/30 [00:05<00:15, 1.44it/s]\n 30%|███ | 9/30 [00:06<00:14, 1.44it/s]\n 33%|███▎ | 10/30 [00:07<00:13, 1.45it/s]\n 37%|███▋ | 11/30 [00:07<00:13, 1.45it/s]\n 40%|████ | 12/30 [00:08<00:12, 1.45it/s]\n 43%|████▎ | 13/30 [00:09<00:11, 1.45it/s]\n 47%|████▋ | 14/30 [00:09<00:10, 1.46it/s]\n 50%|█████ | 15/30 [00:10<00:10, 1.46it/s]\n 53%|█████▎ | 16/30 [00:11<00:09, 1.46it/s]\n 57%|█████▋ | 17/30 [00:11<00:08, 1.46it/s]\n 60%|██████ | 18/30 [00:12<00:08, 1.46it/s]\n 63%|██████▎ | 19/30 [00:13<00:07, 1.46it/s]\n 67%|██████▋ | 20/30 [00:14<00:06, 1.46it/s]\n 70%|███████ | 21/30 [00:14<00:06, 1.46it/s]\n 73%|███████▎ | 22/30 [00:15<00:05, 1.45it/s]\n 77%|███████▋ | 23/30 [00:16<00:04, 1.46it/s]\n 80%|████████ | 24/30 [00:16<00:04, 1.46it/s]\n 83%|████████▎ | 25/30 [00:17<00:03, 1.46it/s]\n 87%|████████▋ | 26/30 [00:18<00:02, 1.46it/s]\n 90%|█████████ | 27/30 [00:18<00:02, 1.45it/s]\n 93%|█████████▎| 28/30 [00:19<00:01, 1.45it/s]\n 97%|█████████▋| 29/30 [00:20<00:00, 1.45it/s]\n100%|██████████| 30/30 [00:20<00:00, 1.45it/s]\n100%|██████████| 30/30 [00:20<00:00, 1.43it/s]",
"metrics": {
"predict_time": 37.338348,
"total_time": 203.922646
},
"output": "https://replicate.delivery/pbxt/80mpaXLe0m3CBKrK3FRAolhffkCezB0cq0fVeT17Aa4SK85jE/result.jpg",
"started_at": "2024-01-24T08:27:48.672675Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/r4hhsklbyp5opajiuvh5mho7ae",
"cancel": "https://api.replicate.com/v1/predictions/r4hhsklbyp5opajiuvh5mho7ae/cancel"
},
"version": "03914a0c3326bf44383d0cd84b06822618af879229ce5d1d53bef38d93b68279"
}Generated in
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/insightface/utils/transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
0%| | 0/30 [00:00<?, ?it/s]
3%|▎ | 1/30 [00:00<00:28, 1.01it/s]
7%|▋ | 2/30 [00:01<00:22, 1.23it/s]
10%|█ | 3/30 [00:02<00:20, 1.33it/s]
13%|█▎ | 4/30 [00:03<00:18, 1.37it/s]
17%|█▋ | 5/30 [00:03<00:17, 1.40it/s]
20%|██ | 6/30 [00:04<00:16, 1.42it/s]
23%|██▎ | 7/30 [00:05<00:16, 1.43it/s]
27%|██▋ | 8/30 [00:05<00:15, 1.44it/s]
30%|███ | 9/30 [00:06<00:14, 1.44it/s]
33%|███▎ | 10/30 [00:07<00:13, 1.45it/s]
37%|███▋ | 11/30 [00:07<00:13, 1.45it/s]
40%|████ | 12/30 [00:08<00:12, 1.45it/s]
43%|████▎ | 13/30 [00:09<00:11, 1.45it/s]
47%|████▋ | 14/30 [00:09<00:10, 1.46it/s]
50%|█████ | 15/30 [00:10<00:10, 1.46it/s]
53%|█████▎ | 16/30 [00:11<00:09, 1.46it/s]
57%|█████▋ | 17/30 [00:11<00:08, 1.46it/s]
60%|██████ | 18/30 [00:12<00:08, 1.46it/s]
63%|██████▎ | 19/30 [00:13<00:07, 1.46it/s]
67%|██████▋ | 20/30 [00:14<00:06, 1.46it/s]
70%|███████ | 21/30 [00:14<00:06, 1.46it/s]
73%|███████▎ | 22/30 [00:15<00:05, 1.45it/s]
77%|███████▋ | 23/30 [00:16<00:04, 1.46it/s]
80%|████████ | 24/30 [00:16<00:04, 1.46it/s]
83%|████████▎ | 25/30 [00:17<00:03, 1.46it/s]
87%|████████▋ | 26/30 [00:18<00:02, 1.46it/s]
90%|█████████ | 27/30 [00:18<00:02, 1.45it/s]
93%|█████████▎| 28/30 [00:19<00:01, 1.45it/s]
97%|█████████▋| 29/30 [00:20<00:00, 1.45it/s]
100%|██████████| 30/30 [00:20<00:00, 1.45it/s]
100%|██████████| 30/30 [00:20<00:00, 1.43it/s]