GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
Run this model in Node.js with one line of code:
npm install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run camenduru/geowizard using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"camenduru/geowizard:a27c42126bae3efbdc03f0f51c7b9d26549ff801bbb64097d393452438cb010c",
{
input: {
seed: 123,
domain: "indoor",
input_image: "https://replicate.delivery/pbxt/KdKJagGL6FVq0mz0pFsQsR1egZWvWlxcvVVh8KlyaeEbt0Es/basketball_dog.jpg",
ensemble_size: 4,
processing_res: 768,
denoising_steps: 10
}
}
);
// 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.
pip install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import replicateRun camenduru/geowizard using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"camenduru/geowizard:a27c42126bae3efbdc03f0f51c7b9d26549ff801bbb64097d393452438cb010c",
input={
"seed": 123,
"domain": "indoor",
"input_image": "https://replicate.delivery/pbxt/KdKJagGL6FVq0mz0pFsQsR1egZWvWlxcvVVh8KlyaeEbt0Es/basketball_dog.jpg",
"ensemble_size": 4,
"processing_res": 768,
"denoising_steps": 10
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run camenduru/geowizard 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": "camenduru/geowizard:a27c42126bae3efbdc03f0f51c7b9d26549ff801bbb64097d393452438cb010c",
"input": {
"seed": 123,
"domain": "indoor",
"input_image": "https://replicate.delivery/pbxt/KdKJagGL6FVq0mz0pFsQsR1egZWvWlxcvVVh8KlyaeEbt0Es/basketball_dog.jpg",
"ensemble_size": 4,
"processing_res": 768,
"denoising_steps": 10
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2024-03-25T21:23:30.282809Z",
"created_at": "2024-03-25T21:17:25.695486Z",
"data_removed": false,
"error": null,
"id": "53nnkkzbw4byvlqqirwcojd2hq",
"input": {
"seed": 123,
"domain": "indoor",
"input_image": "https://replicate.delivery/pbxt/KdKJagGL6FVq0mz0pFsQsR1egZWvWlxcvVVh8KlyaeEbt0Es/basketball_dog.jpg",
"ensemble_size": 4,
"processing_res": 768,
"denoising_steps": 10
},
"logs": "Inference batches: 0%| | 0/4 [00:00<?, ?it/s]\n Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]\u001b[A\n Diffusion denoising: 10%|█ | 1/10 [00:02<00:21, 2.42s/it]\u001b[A\n Diffusion denoising: 20%|██ | 2/10 [00:03<00:14, 1.87s/it]\u001b[A\n Diffusion denoising: 30%|███ | 3/10 [00:05<00:11, 1.70s/it]\u001b[A\n Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]\u001b[A\n Diffusion denoising: 50%|█████ | 5/10 [00:08<00:07, 1.58s/it]\u001b[A\n Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.56s/it]\u001b[A\n Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.54s/it]\u001b[A\n Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.53s/it]\u001b[A\n Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.53s/it]\u001b[A\n Diffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.53s/it]\u001b[A\n \u001b[A\n Inference batches: 25%|██▌ | 1/4 [00:19<00:59, 19.89s/it]\n Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]\u001b[A\n Diffusion denoising: 10%|█ | 1/10 [00:01<00:13, 1.52s/it]\u001b[A\n Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.53s/it]\u001b[A\n Diffusion denoising: 30%|███ | 3/10 [00:04<00:10, 1.53s/it]\u001b[A\n Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.53s/it]\u001b[A\n Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.53s/it]\u001b[A\n Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.54s/it]\u001b[A\n Diffusion denoising: 70%|███████ | 7/10 [00:10<00:04, 1.54s/it]\u001b[A\n Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.55s/it]\u001b[A\n Diffusion denoising: 90%|█████████ | 9/10 [00:13<00:01, 1.55s/it]\u001b[A\n Diffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.55s/it]\u001b[A\n \u001b[A\n Inference batches: 50%|█████ | 2/4 [00:35<00:35, 17.60s/it]\n Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]\u001b[A\n Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.57s/it]\u001b[A\n Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.58s/it]\u001b[A\n Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.58s/it]\u001b[A\n Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.57s/it]\u001b[A\n Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.58s/it]\u001b[A\n Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.58s/it]\u001b[A\n Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.59s/it]\u001b[A\n Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.59s/it]\u001b[A\n Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.59s/it]\u001b[A\nDiffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.60s/it]\u001b[A\n \u001b[A\n Inference batches: 75%|███████▌ | 3/4 [00:54<00:18, 18.05s/it]\n Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]\u001b[A\n Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.61s/it]\u001b[A\n Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.61s/it]\u001b[A\n Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.62s/it]\u001b[A\n Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]\u001b[A\n Diffusion denoising: 50%|█████ | 5/10 [00:08<00:08, 1.62s/it]\u001b[A\n Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.63s/it]\u001b[A\n Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.63s/it]\u001b[A\n Diffusion denoising: 80%|████████ | 8/10 [00:13<00:03, 1.64s/it]\u001b[A\n Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.64s/it]\u001b[A\nDiffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.65s/it]\u001b[A\n \u001b[A\nInference batches: 100%|██████████| 4/4 [01:13<00:00, 18.48s/it]",
"metrics": {
"predict_time": 78.992753,
"total_time": 364.587323
},
"output": [
"https://replicate.delivery/pbxt/YEkbOegeLfXN3p5fwEwpxskzuZhiDCJTftnLBD1byYZLqOfoE/depth.png",
"https://replicate.delivery/pbxt/3qM6jWFjwgqjPFTqlxvep54cJ0We41S3L5O21PEgfNXlqzHlA/normal.png"
],
"started_at": "2024-03-25T21:22:11.290056Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/53nnkkzbw4byvlqqirwcojd2hq",
"cancel": "https://api.replicate.com/v1/predictions/53nnkkzbw4byvlqqirwcojd2hq/cancel"
},
"version": "a27c42126bae3efbdc03f0f51c7b9d26549ff801bbb64097d393452438cb010c"
}Inference batches: 0%| | 0/4 [00:00<?, ?it/s]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:02<00:21, 2.42s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:14, 1.87s/it]
Diffusion denoising: 30%|███ | 3/10 [00:05<00:11, 1.70s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:08<00:07, 1.58s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.56s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.54s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.53s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.53s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.53s/it]
Inference batches: 25%|██▌ | 1/4 [00:19<00:59, 19.89s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:13, 1.52s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.53s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:10, 1.53s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.53s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.53s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.54s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:10<00:04, 1.54s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.55s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:13<00:01, 1.55s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.55s/it]
Inference batches: 50%|█████ | 2/4 [00:35<00:35, 17.60s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.57s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.58s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.58s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.57s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.58s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.58s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.59s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.59s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.59s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.60s/it]
Inference batches: 75%|███████▌ | 3/4 [00:54<00:18, 18.05s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.61s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.61s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.62s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:08<00:08, 1.62s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.63s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.63s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:13<00:03, 1.64s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.64s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.65s/it]
Inference batches: 100%|██████████| 4/4 [01:13<00:00, 18.48s/it]This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.
🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru
https://replicate.com/camenduru/geowizard
https://github.com/fuxiao0719/GeoWizard
https://arxiv.org/abs/2403.12013
https://fuxiao0719.github.io/projects/geowizard/
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input
Inference batches: 0%| | 0/4 [00:00<?, ?it/s]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:02<00:21, 2.42s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:14, 1.87s/it]
Diffusion denoising: 30%|███ | 3/10 [00:05<00:11, 1.70s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:08<00:07, 1.58s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.56s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.54s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.53s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.53s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.53s/it]
Inference batches: 25%|██▌ | 1/4 [00:19<00:59, 19.89s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:13, 1.52s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.53s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:10, 1.53s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.53s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.53s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.54s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:10<00:04, 1.54s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.55s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:13<00:01, 1.55s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.55s/it]
Inference batches: 50%|█████ | 2/4 [00:35<00:35, 17.60s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.57s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.58s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.58s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.57s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:07<00:07, 1.58s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.58s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.59s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:12<00:03, 1.59s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.59s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:15<00:00, 1.60s/it]
Inference batches: 75%|███████▌ | 3/4 [00:54<00:18, 18.05s/it]
Diffusion denoising: 0%| | 0/10 [00:00<?, ?it/s]
Diffusion denoising: 10%|█ | 1/10 [00:01<00:14, 1.61s/it]
Diffusion denoising: 20%|██ | 2/10 [00:03<00:12, 1.61s/it]
Diffusion denoising: 30%|███ | 3/10 [00:04<00:11, 1.62s/it]
Diffusion denoising: 40%|████ | 4/10 [00:06<00:09, 1.62s/it]
Diffusion denoising: 50%|█████ | 5/10 [00:08<00:08, 1.62s/it]
Diffusion denoising: 60%|██████ | 6/10 [00:09<00:06, 1.63s/it]
Diffusion denoising: 70%|███████ | 7/10 [00:11<00:04, 1.63s/it]
Diffusion denoising: 80%|████████ | 8/10 [00:13<00:03, 1.64s/it]
Diffusion denoising: 90%|█████████ | 9/10 [00:14<00:01, 1.64s/it]
Diffusion denoising: 100%|██████████| 10/10 [00:16<00:00, 1.65s/it]
Inference batches: 100%|██████████| 4/4 [01:13<00:00, 18.48s/it]