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.
stability-ai /sdxl:7762fd07
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=stability-ai/sdxl
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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
{
input: {
width: 2048,
height: 2048,
prompt: "a stunning watercolor painting on canvas of california poppy flowers, in the style of Claude Monet, Giverny, impressionism, impressionistic landscapes, pastel colors, impressionistic portraits, exaggerated blurry brushstrokes, dramatic lighting",
refine: "expert_ensemble_refiner",
scheduler: "K_EULER",
lora_scale: 0.6,
num_outputs: 1,
guidance_scale: 7.5,
apply_watermark: true,
high_noise_frac: 0.8,
negative_prompt: "ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face",
prompt_strength: 0.8,
num_inference_steps: 100
}
}
);
// 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 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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
input={
"width": 2048,
"height": 2048,
"prompt": "a stunning watercolor painting on canvas of california poppy flowers, in the style of Claude Monet, Giverny, impressionism, impressionistic landscapes, pastel colors, impressionistic portraits, exaggerated blurry brushstrokes, dramatic lighting",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": True,
"high_noise_frac": 0.8,
"negative_prompt": "ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face",
"prompt_strength": 0.8,
"num_inference_steps": 100
}
)
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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
"input": {
"width": 2048,
"height": 2048,
"prompt": "a stunning watercolor painting on canvas of california poppy flowers, in the style of Claude Monet, Giverny, impressionism, impressionistic landscapes, pastel colors, impressionistic portraits, exaggerated blurry brushstrokes, dramatic lighting",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.8,
"negative_prompt": "ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face",
"prompt_strength": 0.8,
"num_inference_steps": 100
}
}' \
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": "2023-07-27T03:51:00.135005Z",
"created_at": "2023-07-27T03:49:16.327850Z",
"data_removed": false,
"error": null,
"id": "ckscvclbivgjl5cprho7lbgwhm",
"input": {
"width": 2048,
"height": 2048,
"prompt": "a stunning watercolor painting on canvas of california poppy flowers, in the style of Claude Monet, Giverny, impressionism, impressionistic landscapes, pastel colors, impressionistic portraits, exaggerated blurry brushstrokes, dramatic lighting",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"num_outputs": 1,
"guidance_scale": 7.5,
"high_noise_frac": 0.8,
"negative_prompt": "ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face",
"prompt_strength": 0.8,
"num_inference_steps": 100
},
"logs": "Using seed: 47424\ntxt2img mode\n 0%| | 0/65 [00:00<?, ?it/s]\n 2%|▏ | 1/65 [00:01<01:10, 1.09s/it]\n 3%|▎ | 2/65 [00:02<01:09, 1.10s/it]\n 5%|▍ | 3/65 [00:03<01:08, 1.10s/it]\n 6%|▌ | 4/65 [00:04<01:07, 1.10s/it]\n 8%|▊ | 5/65 [00:05<01:05, 1.10s/it]\n 9%|▉ | 6/65 [00:06<01:04, 1.10s/it]\n 11%|█ | 7/65 [00:07<01:03, 1.10s/it]\n 12%|█▏ | 8/65 [00:08<01:02, 1.10s/it]\n 14%|█▍ | 9/65 [00:09<01:01, 1.10s/it]\n 15%|█▌ | 10/65 [00:11<01:00, 1.10s/it]\n 17%|█▋ | 11/65 [00:12<00:59, 1.10s/it]\n 18%|█▊ | 12/65 [00:13<00:58, 1.10s/it]\n 20%|██ | 13/65 [00:14<00:57, 1.10s/it]\n 22%|██▏ | 14/65 [00:15<00:56, 1.10s/it]\n 23%|██▎ | 15/65 [00:16<00:55, 1.11s/it]\n 25%|██▍ | 16/65 [00:17<00:54, 1.11s/it]\n 26%|██▌ | 17/65 [00:18<00:53, 1.11s/it]\n 28%|██▊ | 18/65 [00:19<00:51, 1.11s/it]\n 29%|██▉ | 19/65 [00:20<00:50, 1.11s/it]\n 31%|███ | 20/65 [00:22<00:49, 1.11s/it]\n 32%|███▏ | 21/65 [00:23<00:48, 1.11s/it]\n 34%|███▍ | 22/65 [00:24<00:47, 1.11s/it]\n 35%|███▌ | 23/65 [00:25<00:46, 1.11s/it]\n 37%|███▋ | 24/65 [00:26<00:45, 1.11s/it]\n 38%|███▊ | 25/65 [00:27<00:44, 1.10s/it]\n 40%|████ | 26/65 [00:28<00:43, 1.10s/it]\n 42%|████▏ | 27/65 [00:29<00:42, 1.11s/it]\n 43%|████▎ | 28/65 [00:30<00:40, 1.11s/it]\n 45%|████▍ | 29/65 [00:32<00:39, 1.10s/it]\n 46%|████▌ | 30/65 [00:33<00:38, 1.10s/it]\n 48%|████▊ | 31/65 [00:34<00:37, 1.11s/it]\n 49%|████▉ | 32/65 [00:35<00:36, 1.11s/it]\n 51%|█████ | 33/65 [00:36<00:35, 1.11s/it]\n 52%|█████▏ | 34/65 [00:37<00:34, 1.11s/it]\n 54%|█████▍ | 35/65 [00:38<00:33, 1.11s/it]\n 55%|█████▌ | 36/65 [00:39<00:32, 1.11s/it]\n 57%|█████▋ | 37/65 [00:40<00:30, 1.11s/it]\n 58%|█████▊ | 38/65 [00:41<00:29, 1.11s/it]\n 60%|██████ | 39/65 [00:43<00:28, 1.11s/it]\n 62%|██████▏ | 40/65 [00:44<00:27, 1.11s/it]\n 63%|██████▎ | 41/65 [00:45<00:26, 1.11s/it]\n 65%|██████▍ | 42/65 [00:46<00:25, 1.11s/it]\n 66%|██████▌ | 43/65 [00:47<00:24, 1.11s/it]\n 68%|██████▊ | 44/65 [00:48<00:23, 1.11s/it]\n 69%|██████▉ | 45/65 [00:49<00:22, 1.11s/it]\n 71%|███████ | 46/65 [00:50<00:21, 1.11s/it]\n 72%|███████▏ | 47/65 [00:51<00:19, 1.11s/it]\n 74%|███████▍ | 48/65 [00:53<00:18, 1.11s/it]\n 75%|███████▌ | 49/65 [00:54<00:17, 1.11s/it]\n 77%|███████▋ | 50/65 [00:55<00:16, 1.11s/it]\n 78%|███████▊ | 51/65 [00:56<00:15, 1.11s/it]\n 80%|████████ | 52/65 [00:57<00:14, 1.11s/it]\n 82%|████████▏ | 53/65 [00:58<00:13, 1.11s/it]\n 83%|████████▎ | 54/65 [00:59<00:12, 1.11s/it]\n 85%|████████▍ | 55/65 [01:00<00:11, 1.11s/it]\n 86%|████████▌ | 56/65 [01:01<00:09, 1.11s/it]\n 88%|████████▊ | 57/65 [01:03<00:08, 1.11s/it]\n 89%|████████▉ | 58/65 [01:04<00:07, 1.11s/it]\n 91%|█████████ | 59/65 [01:05<00:06, 1.11s/it]\n 92%|█████████▏| 60/65 [01:06<00:05, 1.11s/it]\n 94%|█████████▍| 61/65 [01:07<00:04, 1.11s/it]\n 95%|█████████▌| 62/65 [01:08<00:03, 1.11s/it]\n 97%|█████████▋| 63/65 [01:09<00:02, 1.11s/it]\n 98%|█████████▊| 64/65 [01:10<00:01, 1.11s/it]\n100%|██████████| 65/65 [01:11<00:00, 1.11s/it]\n100%|██████████| 65/65 [01:11<00:00, 1.11s/it]\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:01<00:25, 1.34s/it]\n 10%|█ | 2/20 [00:02<00:24, 1.34s/it]\n 15%|█▌ | 3/20 [00:04<00:22, 1.34s/it]\n 20%|██ | 4/20 [00:05<00:21, 1.34s/it]\n 25%|██▌ | 5/20 [00:06<00:20, 1.34s/it]\n 30%|███ | 6/20 [00:08<00:18, 1.34s/it]\n 35%|███▌ | 7/20 [00:09<00:17, 1.34s/it]\n 40%|████ | 8/20 [00:10<00:16, 1.34s/it]\n 45%|████▌ | 9/20 [00:12<00:14, 1.34s/it]\n 50%|█████ | 10/20 [00:13<00:13, 1.34s/it]\n 55%|█████▌ | 11/20 [00:14<00:12, 1.34s/it]\n 60%|██████ | 12/20 [00:16<00:10, 1.34s/it]\n 65%|██████▌ | 13/20 [00:17<00:09, 1.34s/it]\n 70%|███████ | 14/20 [00:18<00:08, 1.34s/it]\n 75%|███████▌ | 15/20 [00:20<00:06, 1.34s/it]\n 80%|████████ | 16/20 [00:21<00:05, 1.34s/it]\n 85%|████████▌ | 17/20 [00:22<00:04, 1.34s/it]\n 90%|█████████ | 18/20 [00:24<00:02, 1.34s/it]\n 95%|█████████▌| 19/20 [00:25<00:01, 1.34s/it]\n100%|██████████| 20/20 [00:26<00:00, 1.34s/it]\n100%|██████████| 20/20 [00:26<00:00, 1.34s/it]",
"metrics": {
"predict_time": 103.846238,
"total_time": 103.807155
},
"output": [
"https://replicate.delivery/pbxt/N2fpLQB1e0nFgk018oQfKCzP6lDtQrF3hRK1pqAZedqP6mPFB/out-0.png"
],
"started_at": "2023-07-27T03:49:16.288767Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/ckscvclbivgjl5cprho7lbgwhm",
"cancel": "https://api.replicate.com/v1/predictions/ckscvclbivgjl5cprho7lbgwhm/cancel"
},
"version": "2f779eb9b23b34fe171f8eaa021b8261566f0d2c10cd2674063e7dbcd351509e"
}Generated in
Using seed: 47424
txt2img mode
0%| | 0/65 [00:00<?, ?it/s]
2%|▏ | 1/65 [00:01<01:10, 1.09s/it]
3%|▎ | 2/65 [00:02<01:09, 1.10s/it]
5%|▍ | 3/65 [00:03<01:08, 1.10s/it]
6%|▌ | 4/65 [00:04<01:07, 1.10s/it]
8%|▊ | 5/65 [00:05<01:05, 1.10s/it]
9%|▉ | 6/65 [00:06<01:04, 1.10s/it]
11%|█ | 7/65 [00:07<01:03, 1.10s/it]
12%|█▏ | 8/65 [00:08<01:02, 1.10s/it]
14%|█▍ | 9/65 [00:09<01:01, 1.10s/it]
15%|█▌ | 10/65 [00:11<01:00, 1.10s/it]
17%|█▋ | 11/65 [00:12<00:59, 1.10s/it]
18%|█▊ | 12/65 [00:13<00:58, 1.10s/it]
20%|██ | 13/65 [00:14<00:57, 1.10s/it]
22%|██▏ | 14/65 [00:15<00:56, 1.10s/it]
23%|██▎ | 15/65 [00:16<00:55, 1.11s/it]
25%|██▍ | 16/65 [00:17<00:54, 1.11s/it]
26%|██▌ | 17/65 [00:18<00:53, 1.11s/it]
28%|██▊ | 18/65 [00:19<00:51, 1.11s/it]
29%|██▉ | 19/65 [00:20<00:50, 1.11s/it]
31%|███ | 20/65 [00:22<00:49, 1.11s/it]
32%|███▏ | 21/65 [00:23<00:48, 1.11s/it]
34%|███▍ | 22/65 [00:24<00:47, 1.11s/it]
35%|███▌ | 23/65 [00:25<00:46, 1.11s/it]
37%|███▋ | 24/65 [00:26<00:45, 1.11s/it]
38%|███▊ | 25/65 [00:27<00:44, 1.10s/it]
40%|████ | 26/65 [00:28<00:43, 1.10s/it]
42%|████▏ | 27/65 [00:29<00:42, 1.11s/it]
43%|████▎ | 28/65 [00:30<00:40, 1.11s/it]
45%|████▍ | 29/65 [00:32<00:39, 1.10s/it]
46%|████▌ | 30/65 [00:33<00:38, 1.10s/it]
48%|████▊ | 31/65 [00:34<00:37, 1.11s/it]
49%|████▉ | 32/65 [00:35<00:36, 1.11s/it]
51%|█████ | 33/65 [00:36<00:35, 1.11s/it]
52%|█████▏ | 34/65 [00:37<00:34, 1.11s/it]
54%|█████▍ | 35/65 [00:38<00:33, 1.11s/it]
55%|█████▌ | 36/65 [00:39<00:32, 1.11s/it]
57%|█████▋ | 37/65 [00:40<00:30, 1.11s/it]
58%|█████▊ | 38/65 [00:41<00:29, 1.11s/it]
60%|██████ | 39/65 [00:43<00:28, 1.11s/it]
62%|██████▏ | 40/65 [00:44<00:27, 1.11s/it]
63%|██████▎ | 41/65 [00:45<00:26, 1.11s/it]
65%|██████▍ | 42/65 [00:46<00:25, 1.11s/it]
66%|██████▌ | 43/65 [00:47<00:24, 1.11s/it]
68%|██████▊ | 44/65 [00:48<00:23, 1.11s/it]
69%|██████▉ | 45/65 [00:49<00:22, 1.11s/it]
71%|███████ | 46/65 [00:50<00:21, 1.11s/it]
72%|███████▏ | 47/65 [00:51<00:19, 1.11s/it]
74%|███████▍ | 48/65 [00:53<00:18, 1.11s/it]
75%|███████▌ | 49/65 [00:54<00:17, 1.11s/it]
77%|███████▋ | 50/65 [00:55<00:16, 1.11s/it]
78%|███████▊ | 51/65 [00:56<00:15, 1.11s/it]
80%|████████ | 52/65 [00:57<00:14, 1.11s/it]
82%|████████▏ | 53/65 [00:58<00:13, 1.11s/it]
83%|████████▎ | 54/65 [00:59<00:12, 1.11s/it]
85%|████████▍ | 55/65 [01:00<00:11, 1.11s/it]
86%|████████▌ | 56/65 [01:01<00:09, 1.11s/it]
88%|████████▊ | 57/65 [01:03<00:08, 1.11s/it]
89%|████████▉ | 58/65 [01:04<00:07, 1.11s/it]
91%|█████████ | 59/65 [01:05<00:06, 1.11s/it]
92%|█████████▏| 60/65 [01:06<00:05, 1.11s/it]
94%|█████████▍| 61/65 [01:07<00:04, 1.11s/it]
95%|█████████▌| 62/65 [01:08<00:03, 1.11s/it]
97%|█████████▋| 63/65 [01:09<00:02, 1.11s/it]
98%|█████████▊| 64/65 [01:10<00:01, 1.11s/it]
100%|██████████| 65/65 [01:11<00:00, 1.11s/it]
100%|██████████| 65/65 [01:11<00:00, 1.11s/it]
0%| | 0/20 [00:00<?, ?it/s]
5%|▌ | 1/20 [00:01<00:25, 1.34s/it]
10%|█ | 2/20 [00:02<00:24, 1.34s/it]
15%|█▌ | 3/20 [00:04<00:22, 1.34s/it]
20%|██ | 4/20 [00:05<00:21, 1.34s/it]
25%|██▌ | 5/20 [00:06<00:20, 1.34s/it]
30%|███ | 6/20 [00:08<00:18, 1.34s/it]
35%|███▌ | 7/20 [00:09<00:17, 1.34s/it]
40%|████ | 8/20 [00:10<00:16, 1.34s/it]
45%|████▌ | 9/20 [00:12<00:14, 1.34s/it]
50%|█████ | 10/20 [00:13<00:13, 1.34s/it]
55%|█████▌ | 11/20 [00:14<00:12, 1.34s/it]
60%|██████ | 12/20 [00:16<00:10, 1.34s/it]
65%|██████▌ | 13/20 [00:17<00:09, 1.34s/it]
70%|███████ | 14/20 [00:18<00:08, 1.34s/it]
75%|███████▌ | 15/20 [00:20<00:06, 1.34s/it]
80%|████████ | 16/20 [00:21<00:05, 1.34s/it]
85%|████████▌ | 17/20 [00:22<00:04, 1.34s/it]
90%|█████████ | 18/20 [00:24<00:02, 1.34s/it]
95%|█████████▌| 19/20 [00:25<00:01, 1.34s/it]
100%|██████████| 20/20 [00:26<00:00, 1.34s/it]
100%|██████████| 20/20 [00:26<00:00, 1.34s/it]This output was created using a different version of the model, stability-ai/sdxl:2f779eb9.