Versions
bddc0936
Latest
cb1517af
312f550e
fee3e72c
e9add139
4d86931d
45fc1b70
af2f1130
a1e9168d
add038e7
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 front view of a beautiful waterfall",
img_width: 2048,
rrg_scale: 1000,
img_height: 512,
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 front view of a beautiful waterfall",
"img_width": 2048,
"rrg_scale": 1000,
"img_height": 512,
"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 front view of a beautiful waterfall",
"img_width": 2048,
"rrg_scale": 1000,
"img_height": 512,
"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.
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/moayedhajiali/elasticdiffusion@sha256:bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88 \
-i 'seed=0' \
-i 'prompt="A front view of a beautiful waterfall"' \
-i 'img_width=2048' \
-i 'rrg_scale=1000' \
-i 'img_height=512' \
-i 'cosine_scale=10' \
-i 'guidance_scale=10' \
-i 'view_batch_size=16' \
-i 'negative_prompts="blurry, ugly, poorly drawn, deformed"' \
-i 'resampling_new_p=0.3' \
-i 'resampling_steps=7' \
-i 'num_inference_steps=50'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/moayedhajiali/elasticdiffusion@sha256:bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 0, "prompt": "A front view of a beautiful waterfall", "img_width": 2048, "rrg_scale": 1000, "img_height": 512, "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 } }' \ 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 $0.50. 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": "2023-12-28T04:14:40.379623Z",
"created_at": "2023-12-28T04:09:12.956407Z",
"data_removed": false,
"error": null,
"id": "arekedtbs2ou7zjfjvbokqkssm",
"input": {
"seed": 0,
"prompt": "A front view of a beautiful waterfall",
"img_width": 2048,
"rrg_scale": 1000,
"img_height": 512,
"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]\n 2%|▏ | 1/50 [00:06<05:20, 6.54s/it]\n 4%|▍ | 2/50 [00:13<05:13, 6.53s/it]\n 6%|▌ | 3/50 [00:19<05:06, 6.53s/it]\n 8%|▊ | 4/50 [00:26<05:00, 6.53s/it]\n 10%|█ | 5/50 [00:32<04:53, 6.53s/it]\n 12%|█▏ | 6/50 [00:39<04:47, 6.53s/it]\n 14%|█▍ | 7/50 [00:45<04:40, 6.53s/it]\n 16%|█▌ | 8/50 [00:52<04:34, 6.54s/it]\n 18%|█▊ | 9/50 [00:58<04:28, 6.54s/it]\n 20%|██ | 10/50 [01:05<04:21, 6.54s/it]\n 22%|██▏ | 11/50 [01:11<04:14, 6.54s/it]\n 24%|██▍ | 12/50 [01:18<04:08, 6.54s/it]\n 26%|██▌ | 13/50 [01:24<04:01, 6.54s/it]\n 28%|██▊ | 14/50 [01:31<03:55, 6.54s/it]\n 30%|███ | 15/50 [01:38<03:48, 6.54s/it]\n 32%|███▏ | 16/50 [01:44<03:42, 6.54s/it]\n 34%|███▍ | 17/50 [01:51<03:35, 6.54s/it]\n 36%|███▌ | 18/50 [01:57<03:29, 6.54s/it]\n 38%|███▊ | 19/50 [02:04<03:22, 6.54s/it]\n 40%|████ | 20/50 [02:10<03:16, 6.54s/it]\n 42%|████▏ | 21/50 [02:17<03:09, 6.54s/it]\n 44%|████▍ | 22/50 [02:23<03:03, 6.54s/it]\n 46%|████▌ | 23/50 [02:30<02:56, 6.54s/it]\n 48%|████▊ | 24/50 [02:36<02:50, 6.54s/it]\n 50%|█████ | 25/50 [02:43<02:43, 6.54s/it]\n 52%|█████▏ | 26/50 [02:49<02:36, 6.54s/it]\n 54%|█████▍ | 27/50 [02:56<02:30, 6.54s/it]\n 56%|█████▌ | 28/50 [03:03<02:23, 6.54s/it]\n 58%|█████▊ | 29/50 [03:09<02:17, 6.54s/it]\n 60%|██████ | 30/50 [03:16<02:10, 6.54s/it]\n 62%|██████▏ | 31/50 [03:22<02:04, 6.54s/it]\n 64%|██████▍ | 32/50 [03:29<01:57, 6.54s/it]\n 66%|██████▌ | 33/50 [03:35<01:51, 6.54s/it]\n 68%|██████▊ | 34/50 [03:42<01:44, 6.54s/it]\n 70%|███████ | 35/50 [03:48<01:38, 6.54s/it]\n 72%|███████▏ | 36/50 [03:55<01:31, 6.54s/it]\n 74%|███████▍ | 37/50 [04:01<01:25, 6.54s/it]\n 76%|███████▌ | 38/50 [04:08<01:18, 6.54s/it]\n 78%|███████▊ | 39/50 [04:14<01:11, 6.54s/it]\n 80%|████████ | 40/50 [04:21<01:05, 6.54s/it]\n 82%|████████▏ | 41/50 [04:28<00:58, 6.54s/it]\n 84%|████████▍ | 42/50 [04:34<00:52, 6.54s/it]\n 86%|████████▌ | 43/50 [04:41<00:45, 6.54s/it]\n 88%|████████▊ | 44/50 [04:47<00:39, 6.54s/it]\n 90%|█████████ | 45/50 [04:54<00:32, 6.54s/it]\n 92%|█████████▏| 46/50 [05:00<00:26, 6.54s/it]\n 94%|█████████▍| 47/50 [05:07<00:19, 6.54s/it]\n 96%|█████████▌| 48/50 [05:13<00:13, 6.54s/it]\n 98%|█████████▊| 49/50 [05:20<00:06, 6.54s/it]\n100%|██████████| 50/50 [05:25<00:00, 6.12s/it]\n100%|██████████| 50/50 [05:25<00:00, 6.51s/it]\n[INFO] Time taken: 326.00207567214966 seconds.",
"metrics": {
"predict_time": 327.390563,
"total_time": 327.423216
},
"output": "https://replicate.delivery/pbxt/f2Jieqy7FPjbW0MM7xjU1SKZ8DUvlve594cxx29ySoe8CqaIB/result.png",
"started_at": "2023-12-28T04:09:12.989060Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/arekedtbs2ou7zjfjvbokqkssm",
"cancel": "https://api.replicate.com/v1/predictions/arekedtbs2ou7zjfjvbokqkssm/cancel"
},
"version": "bddc09369f9e622518f6d11daff26723a513714e08830ed053660d8ac44ffe88"
}Generated in
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:06<05:20, 6.54s/it]
4%|▍ | 2/50 [00:13<05:13, 6.53s/it]
6%|▌ | 3/50 [00:19<05:06, 6.53s/it]
8%|▊ | 4/50 [00:26<05:00, 6.53s/it]
10%|█ | 5/50 [00:32<04:53, 6.53s/it]
12%|█▏ | 6/50 [00:39<04:47, 6.53s/it]
14%|█▍ | 7/50 [00:45<04:40, 6.53s/it]
16%|█▌ | 8/50 [00:52<04:34, 6.54s/it]
18%|█▊ | 9/50 [00:58<04:28, 6.54s/it]
20%|██ | 10/50 [01:05<04:21, 6.54s/it]
22%|██▏ | 11/50 [01:11<04:14, 6.54s/it]
24%|██▍ | 12/50 [01:18<04:08, 6.54s/it]
26%|██▌ | 13/50 [01:24<04:01, 6.54s/it]
28%|██▊ | 14/50 [01:31<03:55, 6.54s/it]
30%|███ | 15/50 [01:38<03:48, 6.54s/it]
32%|███▏ | 16/50 [01:44<03:42, 6.54s/it]
34%|███▍ | 17/50 [01:51<03:35, 6.54s/it]
36%|███▌ | 18/50 [01:57<03:29, 6.54s/it]
38%|███▊ | 19/50 [02:04<03:22, 6.54s/it]
40%|████ | 20/50 [02:10<03:16, 6.54s/it]
42%|████▏ | 21/50 [02:17<03:09, 6.54s/it]
44%|████▍ | 22/50 [02:23<03:03, 6.54s/it]
46%|████▌ | 23/50 [02:30<02:56, 6.54s/it]
48%|████▊ | 24/50 [02:36<02:50, 6.54s/it]
50%|█████ | 25/50 [02:43<02:43, 6.54s/it]
52%|█████▏ | 26/50 [02:49<02:36, 6.54s/it]
54%|█████▍ | 27/50 [02:56<02:30, 6.54s/it]
56%|█████▌ | 28/50 [03:03<02:23, 6.54s/it]
58%|█████▊ | 29/50 [03:09<02:17, 6.54s/it]
60%|██████ | 30/50 [03:16<02:10, 6.54s/it]
62%|██████▏ | 31/50 [03:22<02:04, 6.54s/it]
64%|██████▍ | 32/50 [03:29<01:57, 6.54s/it]
66%|██████▌ | 33/50 [03:35<01:51, 6.54s/it]
68%|██████▊ | 34/50 [03:42<01:44, 6.54s/it]
70%|███████ | 35/50 [03:48<01:38, 6.54s/it]
72%|███████▏ | 36/50 [03:55<01:31, 6.54s/it]
74%|███████▍ | 37/50 [04:01<01:25, 6.54s/it]
76%|███████▌ | 38/50 [04:08<01:18, 6.54s/it]
78%|███████▊ | 39/50 [04:14<01:11, 6.54s/it]
80%|████████ | 40/50 [04:21<01:05, 6.54s/it]
82%|████████▏ | 41/50 [04:28<00:58, 6.54s/it]
84%|████████▍ | 42/50 [04:34<00:52, 6.54s/it]
86%|████████▌ | 43/50 [04:41<00:45, 6.54s/it]
88%|████████▊ | 44/50 [04:47<00:39, 6.54s/it]
90%|█████████ | 45/50 [04:54<00:32, 6.54s/it]
92%|█████████▏| 46/50 [05:00<00:26, 6.54s/it]
94%|█████████▍| 47/50 [05:07<00:19, 6.54s/it]
96%|█████████▌| 48/50 [05:13<00:13, 6.54s/it]
98%|█████████▊| 49/50 [05:20<00:06, 6.54s/it]
100%|██████████| 50/50 [05:25<00:00, 6.12s/it]
100%|██████████| 50/50 [05:25<00:00, 6.51s/it]
[INFO] Time taken: 326.00207567214966 seconds.