Versions
Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
moayedhajiali /elasticdiffusion:bddc0936
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=moayedhajiali/elasticdiffusion
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 moayedhajiali/elasticdiffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"moayedhajiali/elasticdiffusion:bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88",
{
input: {
seed: 0,
prompt: "A dramatic photo of a volcanic eruption, high details, sharp.",
img_width: 768,
rrg_scale: 1000,
img_height: 2048,
cosine_scale: 10,
guidance_scale: 10,
view_batch_size: 16,
negative_prompts: "blurry, ugly, poorly drawn, deformed",
resampling_new_p: 0.3,
resampling_steps: 7,
num_inference_steps: 50
}
}
);
// 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 moayedhajiali/elasticdiffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"moayedhajiali/elasticdiffusion:bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88",
input={
"seed": 0,
"prompt": "A dramatic photo of a volcanic eruption, high details, sharp.",
"img_width": 768,
"rrg_scale": 1000,
"img_height": 2048,
"cosine_scale": 10,
"guidance_scale": 10,
"view_batch_size": 16,
"negative_prompts": "blurry, ugly, poorly drawn, deformed",
"resampling_new_p": 0.3,
"resampling_steps": 7,
"num_inference_steps": 50
}
)
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 moayedhajiali/elasticdiffusion 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": "bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88",
"input": {
"seed": 0,
"prompt": "A dramatic photo of a volcanic eruption, high details, sharp.",
"img_width": 768,
"rrg_scale": 1000,
"img_height": 2048,
"cosine_scale": 10,
"guidance_scale": 10,
"view_batch_size": 16,
"negative_prompts": "blurry, ugly, poorly drawn, deformed",
"resampling_new_p": 0.3,
"resampling_steps": 7,
"num_inference_steps": 50
}
}' \
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.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2023-12-28T03:44:57.895991Z",
"created_at": "2023-12-28T03:37:07.869743Z",
"data_removed": false,
"error": null,
"id": "rkktb63b7awabxgq6ic6dkqmbq",
"input": {
"seed": 0,
"prompt": "A dramatic photo of a volcanic eruption, high details, sharp.",
"img_width": 768,
"rrg_scale": 1000,
"img_height": 2048,
"cosine_scale": 10,
"guidance_scale": 10,
"view_batch_size": 16,
"negative_prompts": "blurry, ugly, poorly drawn, deformed",
"resampling_new_p": 0.3,
"resampling_steps": 7,
"num_inference_steps": 50
},
"logs": "0%| | 0/50 [00:00<?, ?it/s]/src/elastic_diffusion.py:502: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').\nsampled_h = (idx_h * downsample_factor + random_indices.reshape(idx_h.shape[0], idx_h.shape[1]) // downsample_factor).view(-1)\n 2%|▏ | 1/50 [00:06<05:06, 6.25s/it]\n 4%|▍ | 2/50 [00:12<04:59, 6.23s/it]\n 6%|▌ | 3/50 [00:18<04:52, 6.23s/it]\n 8%|▊ | 4/50 [00:24<04:46, 6.23s/it]\n 10%|█ | 5/50 [00:31<04:40, 6.23s/it]\n 12%|█▏ | 6/50 [00:37<04:34, 6.23s/it]\n 14%|█▍ | 7/50 [00:43<04:28, 6.24s/it]\n 16%|█▌ | 8/50 [00:49<04:22, 6.26s/it]\n 18%|█▊ | 9/50 [00:56<04:16, 6.26s/it]\n 20%|██ | 10/50 [01:02<04:10, 6.27s/it]\n 22%|██▏ | 11/50 [01:08<04:04, 6.28s/it]\n 24%|██▍ | 12/50 [01:15<03:58, 6.28s/it]\n 26%|██▌ | 13/50 [01:21<03:52, 6.28s/it]\n 28%|██▊ | 14/50 [01:27<03:46, 6.28s/it]\n 30%|███ | 15/50 [01:34<03:40, 6.30s/it]\n 32%|███▏ | 16/50 [01:40<03:34, 6.30s/it]\n 34%|███▍ | 17/50 [01:46<03:27, 6.29s/it]\n 36%|███▌ | 18/50 [01:52<03:21, 6.29s/it]\n 38%|███▊ | 19/50 [01:59<03:15, 6.30s/it]\n 40%|████ | 20/50 [02:05<03:08, 6.30s/it]\n 42%|████▏ | 21/50 [02:11<03:02, 6.31s/it]\n 44%|████▍ | 22/50 [02:18<02:56, 6.31s/it]\n 46%|████▌ | 23/50 [02:24<02:50, 6.31s/it]\n 48%|████▊ | 24/50 [02:30<02:43, 6.31s/it]\n 50%|█████ | 25/50 [02:37<02:37, 6.30s/it]\n 52%|█████▏ | 26/50 [02:43<02:31, 6.30s/it]\n 54%|█████▍ | 27/50 [02:49<02:24, 6.30s/it]\n 56%|█████▌ | 28/50 [02:55<02:18, 6.30s/it]\n 58%|█████▊ | 29/50 [03:02<02:12, 6.30s/it]\n 60%|██████ | 30/50 [03:08<02:05, 6.29s/it]\n 62%|██████▏ | 31/50 [03:14<01:59, 6.28s/it]\n 64%|██████▍ | 32/50 [03:21<01:52, 6.28s/it]\n 66%|██████▌ | 33/50 [03:27<01:46, 6.27s/it]\n 68%|██████▊ | 34/50 [03:33<01:40, 6.27s/it]\n 70%|███████ | 35/50 [03:39<01:34, 6.27s/it]\n 72%|███████▏ | 36/50 [03:46<01:27, 6.27s/it]\n 74%|███████▍ | 37/50 [03:52<01:21, 6.26s/it]\n 76%|███████▌ | 38/50 [03:58<01:15, 6.26s/it]\n 78%|███████▊ | 39/50 [04:04<01:08, 6.26s/it]\n 80%|████████ | 40/50 [04:11<01:02, 6.26s/it]\n 82%|████████▏ | 41/50 [04:17<00:56, 6.26s/it]\n 84%|████████▍ | 42/50 [04:23<00:50, 6.27s/it]\n 86%|████████▌ | 43/50 [04:29<00:43, 6.28s/it]\n 88%|████████▊ | 44/50 [04:36<00:37, 6.27s/it]\n 90%|█████████ | 45/50 [04:42<00:31, 6.27s/it]\n 92%|█████████▏| 46/50 [04:48<00:25, 6.27s/it]\n 94%|█████████▍| 47/50 [04:55<00:18, 6.27s/it]\n 96%|█████████▌| 48/50 [05:01<00:12, 6.27s/it]\n 98%|█████████▊| 49/50 [05:07<00:06, 6.27s/it]\n100%|██████████| 50/50 [05:12<00:00, 5.87s/it]\n100%|██████████| 50/50 [05:12<00:00, 6.25s/it]\n[INFO] Time taken: 313.1778419017792 seconds.",
"metrics": {
"predict_time": 314.820496,
"total_time": 470.026248
},
"output": "https://replicate.delivery/pbxt/qu6eBa5zVB2tD6GMydVo7DmMPP6VtvnDUgDEwLZ4gXxcCVDJA/result.png",
"started_at": "2023-12-28T03:39:43.075495Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/rkktb63b7awabxgq6ic6dkqmbq",
"cancel": "https://api.replicate.com/v1/predictions/rkktb63b7awabxgq6ic6dkqmbq/cancel"
},
"version": "bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88"
}Generated in
0%| | 0/50 [00:00<?, ?it/s]/src/elastic_diffusion.py:502: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
sampled_h = (idx_h * downsample_factor + random_indices.reshape(idx_h.shape[0], idx_h.shape[1]) // downsample_factor).view(-1)
2%|▏ | 1/50 [00:06<05:06, 6.25s/it]
4%|▍ | 2/50 [00:12<04:59, 6.23s/it]
6%|▌ | 3/50 [00:18<04:52, 6.23s/it]
8%|▊ | 4/50 [00:24<04:46, 6.23s/it]
10%|█ | 5/50 [00:31<04:40, 6.23s/it]
12%|█▏ | 6/50 [00:37<04:34, 6.23s/it]
14%|█▍ | 7/50 [00:43<04:28, 6.24s/it]
16%|█▌ | 8/50 [00:49<04:22, 6.26s/it]
18%|█▊ | 9/50 [00:56<04:16, 6.26s/it]
20%|██ | 10/50 [01:02<04:10, 6.27s/it]
22%|██▏ | 11/50 [01:08<04:04, 6.28s/it]
24%|██▍ | 12/50 [01:15<03:58, 6.28s/it]
26%|██▌ | 13/50 [01:21<03:52, 6.28s/it]
28%|██▊ | 14/50 [01:27<03:46, 6.28s/it]
30%|███ | 15/50 [01:34<03:40, 6.30s/it]
32%|███▏ | 16/50 [01:40<03:34, 6.30s/it]
34%|███▍ | 17/50 [01:46<03:27, 6.29s/it]
36%|███▌ | 18/50 [01:52<03:21, 6.29s/it]
38%|███▊ | 19/50 [01:59<03:15, 6.30s/it]
40%|████ | 20/50 [02:05<03:08, 6.30s/it]
42%|████▏ | 21/50 [02:11<03:02, 6.31s/it]
44%|████▍ | 22/50 [02:18<02:56, 6.31s/it]
46%|████▌ | 23/50 [02:24<02:50, 6.31s/it]
48%|████▊ | 24/50 [02:30<02:43, 6.31s/it]
50%|█████ | 25/50 [02:37<02:37, 6.30s/it]
52%|█████▏ | 26/50 [02:43<02:31, 6.30s/it]
54%|█████▍ | 27/50 [02:49<02:24, 6.30s/it]
56%|█████▌ | 28/50 [02:55<02:18, 6.30s/it]
58%|█████▊ | 29/50 [03:02<02:12, 6.30s/it]
60%|██████ | 30/50 [03:08<02:05, 6.29s/it]
62%|██████▏ | 31/50 [03:14<01:59, 6.28s/it]
64%|██████▍ | 32/50 [03:21<01:52, 6.28s/it]
66%|██████▌ | 33/50 [03:27<01:46, 6.27s/it]
68%|██████▊ | 34/50 [03:33<01:40, 6.27s/it]
70%|███████ | 35/50 [03:39<01:34, 6.27s/it]
72%|███████▏ | 36/50 [03:46<01:27, 6.27s/it]
74%|███████▍ | 37/50 [03:52<01:21, 6.26s/it]
76%|███████▌ | 38/50 [03:58<01:15, 6.26s/it]
78%|███████▊ | 39/50 [04:04<01:08, 6.26s/it]
80%|████████ | 40/50 [04:11<01:02, 6.26s/it]
82%|████████▏ | 41/50 [04:17<00:56, 6.26s/it]
84%|████████▍ | 42/50 [04:23<00:50, 6.27s/it]
86%|████████▌ | 43/50 [04:29<00:43, 6.28s/it]
88%|████████▊ | 44/50 [04:36<00:37, 6.27s/it]
90%|█████████ | 45/50 [04:42<00:31, 6.27s/it]
92%|█████████▏| 46/50 [04:48<00:25, 6.27s/it]
94%|█████████▍| 47/50 [04:55<00:18, 6.27s/it]
96%|█████████▌| 48/50 [05:01<00:12, 6.27s/it]
98%|█████████▊| 49/50 [05:07<00:06, 6.27s/it]
100%|██████████| 50/50 [05:12<00:00, 5.87s/it]
100%|██████████| 50/50 [05:12<00:00, 6.25s/it]
[INFO] Time taken: 313.1778419017792 seconds.