Versions
988b3a09
Latest
You're looking at a specific version of this model. Jump to the model overview.
justmalhar /sxdl-sketchnotes:988b3a09
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=justmalhar/sxdl-sketchnotes
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 justmalhar/sxdl-sketchnotes using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"justmalhar/sxdl-sketchnotes:988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7c",
{
input: {
width: 1024,
height: 1024,
prompt: "a sketchnote photo of TOK explaining what is Sketchnotes ",
refine: "expert_ensemble_refiner",
scheduler: "K_EULER",
lora_scale: 0.6,
num_outputs: 4,
guidance_scale: 7.5,
apply_watermark: false,
high_noise_frac: 0.8,
negative_prompt: "",
prompt_strength: 0.8,
num_inference_steps: 50
}
}
);
console.log(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 justmalhar/sxdl-sketchnotes using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"justmalhar/sxdl-sketchnotes:988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7c",
input={
"width": 1024,
"height": 1024,
"prompt": "a sketchnote photo of TOK explaining what is Sketchnotes ",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 4,
"guidance_scale": 7.5,
"apply_watermark": False,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"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 justmalhar/sxdl-sketchnotes 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": "988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7c",
"input": {
"width": 1024,
"height": 1024,
"prompt": "a sketchnote photo of TOK explaining what is Sketchnotes ",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 4,
"guidance_scale": 7.5,
"apply_watermark": false,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"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/justmalhar/sxdl-sketchnotes@sha256:988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7c \
-i 'width=1024' \
-i 'height=1024' \
-i 'prompt="a sketchnote photo of TOK explaining what is Sketchnotes "' \
-i 'refine="expert_ensemble_refiner"' \
-i 'scheduler="K_EULER"' \
-i 'lora_scale=0.6' \
-i 'num_outputs=4' \
-i 'guidance_scale=7.5' \
-i 'apply_watermark=false' \
-i 'high_noise_frac=0.8' \
-i 'negative_prompt=""' \
-i 'prompt_strength=0.8' \
-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/justmalhar/sxdl-sketchnotes@sha256:988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7ccurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a sketchnote photo of TOK explaining what is Sketchnotes ", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "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 $0.060. 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": "2024-05-22T18:30:25.496195Z",
"created_at": "2024-05-22T18:28:34.201000Z",
"data_removed": false,
"error": null,
"id": "5wva6kf935rgj0cfm67tscg92m",
"input": {
"width": 1024,
"height": 1024,
"prompt": "a sketchnote photo of TOK explaining what is Sketchnotes ",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 4,
"guidance_scale": 7.5,
"apply_watermark": false,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 20959\nEnsuring enough disk space...\nFree disk space: 1886305222656\nDownloading weights: https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar\n2024-05-22T18:29:31Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/864fe49e400e52a3 url=https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar\n2024-05-22T18:29:32Z | INFO | [ Complete ] dest=/src/weights-cache/864fe49e400e52a3 size=\"186 MB\" total_elapsed=0.671s url=https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar\nb''\nDownloaded weights in 0.7931919097900391 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a sketchnote photo of <s0><s1> explaining what is Sketchnotes\ntxt2img mode\n 0%| | 0/40 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▎ | 1/40 [00:01<00:41, 1.05s/it]\n 5%|▌ | 2/40 [00:01<00:36, 1.03it/s]\n 8%|▊ | 3/40 [00:02<00:34, 1.06it/s]\n 10%|█ | 4/40 [00:03<00:33, 1.07it/s]\n 12%|█▎ | 5/40 [00:04<00:32, 1.08it/s]\n 15%|█▌ | 6/40 [00:05<00:31, 1.08it/s]\n 18%|█▊ | 7/40 [00:06<00:30, 1.08it/s]\n 20%|██ | 8/40 [00:07<00:29, 1.09it/s]\n 22%|██▎ | 9/40 [00:08<00:28, 1.09it/s]\n 25%|██▌ | 10/40 [00:09<00:27, 1.09it/s]\n 28%|██▊ | 11/40 [00:10<00:26, 1.09it/s]\n 30%|███ | 12/40 [00:11<00:25, 1.09it/s]\n 32%|███▎ | 13/40 [00:12<00:24, 1.09it/s]\n 35%|███▌ | 14/40 [00:12<00:23, 1.09it/s]\n 38%|███▊ | 15/40 [00:13<00:22, 1.09it/s]\n 40%|████ | 16/40 [00:14<00:21, 1.09it/s]\n 42%|████▎ | 17/40 [00:15<00:21, 1.09it/s]\n 45%|████▌ | 18/40 [00:16<00:20, 1.09it/s]\n 48%|████▊ | 19/40 [00:17<00:19, 1.09it/s]\n 50%|█████ | 20/40 [00:18<00:18, 1.09it/s]\n 52%|█████▎ | 21/40 [00:19<00:17, 1.09it/s]\n 55%|█████▌ | 22/40 [00:20<00:16, 1.09it/s]\n 57%|█████▊ | 23/40 [00:21<00:15, 1.09it/s]\n 60%|██████ | 24/40 [00:22<00:14, 1.09it/s]\n 62%|██████▎ | 25/40 [00:23<00:13, 1.09it/s]\n 65%|██████▌ | 26/40 [00:23<00:12, 1.09it/s]\n 68%|██████▊ | 27/40 [00:24<00:11, 1.09it/s]\n 70%|███████ | 28/40 [00:25<00:11, 1.09it/s]\n 72%|███████▎ | 29/40 [00:26<00:10, 1.09it/s]\n 75%|███████▌ | 30/40 [00:27<00:09, 1.09it/s]\n 78%|███████▊ | 31/40 [00:28<00:08, 1.09it/s]\n 80%|████████ | 32/40 [00:29<00:07, 1.08it/s]\n 82%|████████▎ | 33/40 [00:30<00:06, 1.08it/s]\n 85%|████████▌ | 34/40 [00:31<00:05, 1.08it/s]\n 88%|████████▊ | 35/40 [00:32<00:04, 1.08it/s]\n 90%|█████████ | 36/40 [00:33<00:03, 1.08it/s]\n 92%|█████████▎| 37/40 [00:34<00:02, 1.08it/s]\n 95%|█████████▌| 38/40 [00:35<00:01, 1.08it/s]\n 98%|█████████▊| 39/40 [00:35<00:00, 1.08it/s]\n100%|██████████| 40/40 [00:36<00:00, 1.08it/s]\n100%|██████████| 40/40 [00:36<00:00, 1.08it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:08, 1.08it/s]\n 20%|██ | 2/10 [00:01<00:07, 1.09it/s]\n 30%|███ | 3/10 [00:02<00:06, 1.09it/s]\n 40%|████ | 4/10 [00:03<00:05, 1.09it/s]\n 50%|█████ | 5/10 [00:04<00:04, 1.08it/s]\n 60%|██████ | 6/10 [00:05<00:03, 1.09it/s]\n 70%|███████ | 7/10 [00:06<00:02, 1.09it/s]\n 80%|████████ | 8/10 [00:07<00:01, 1.09it/s]\n 90%|█████████ | 9/10 [00:08<00:00, 1.09it/s]\n100%|██████████| 10/10 [00:09<00:00, 1.09it/s]\n100%|██████████| 10/10 [00:09<00:00, 1.09it/s]",
"metrics": {
"predict_time": 53.751031,
"total_time": 111.295195
},
"output": [
"https://replicate.delivery/pbxt/POdn5Yai9npsPZl4xuWXexOYJwpTDYuXyd7ebA1xq3wfd9tlA/out-0.png",
"https://replicate.delivery/pbxt/5DY8wNw4dX42H5gMfmzQvlnrHwtJogaSf5WzCuMlYaqAvetlA/out-1.png",
"https://replicate.delivery/pbxt/E0scZMp9Qk6zPZJrfmmnUpQcJrTnCOe9NNp1IK2ZubBAvetlA/out-2.png",
"https://replicate.delivery/pbxt/nqU1dur06I5cMR5BIdsdiFzjSem0M685OfotOku9xIMBvetlA/out-3.png"
],
"started_at": "2024-05-22T18:29:31.745164Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/5wva6kf935rgj0cfm67tscg92m",
"cancel": "https://api.replicate.com/v1/predictions/5wva6kf935rgj0cfm67tscg92m/cancel"
},
"version": "988b3a09e1c2441fb4f22a04aeae435ddb0467357b7dec3337fef7ccc6f7df7c"
}Generated in
Using seed: 20959
Ensuring enough disk space...
Free disk space: 1886305222656
Downloading weights: https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar
2024-05-22T18:29:31Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/864fe49e400e52a3 url=https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar
2024-05-22T18:29:32Z | INFO | [ Complete ] dest=/src/weights-cache/864fe49e400e52a3 size="186 MB" total_elapsed=0.671s url=https://replicate.delivery/pbxt/SemDU9mXjlQsa6nDjLaQLdgfQNI4Loqw3xHB6lQAzeJfi5bLB/trained_model.tar
b''
Downloaded weights in 0.7931919097900391 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a sketchnote photo of <s0><s1> explaining what is Sketchnotes
txt2img mode
0%| | 0/40 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)
return F.conv2d(input, weight, bias, self.stride,
/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`
deprecate(
2%|▎ | 1/40 [00:01<00:41, 1.05s/it]
5%|▌ | 2/40 [00:01<00:36, 1.03it/s]
8%|▊ | 3/40 [00:02<00:34, 1.06it/s]
10%|█ | 4/40 [00:03<00:33, 1.07it/s]
12%|█▎ | 5/40 [00:04<00:32, 1.08it/s]
15%|█▌ | 6/40 [00:05<00:31, 1.08it/s]
18%|█▊ | 7/40 [00:06<00:30, 1.08it/s]
20%|██ | 8/40 [00:07<00:29, 1.09it/s]
22%|██▎ | 9/40 [00:08<00:28, 1.09it/s]
25%|██▌ | 10/40 [00:09<00:27, 1.09it/s]
28%|██▊ | 11/40 [00:10<00:26, 1.09it/s]
30%|███ | 12/40 [00:11<00:25, 1.09it/s]
32%|███▎ | 13/40 [00:12<00:24, 1.09it/s]
35%|███▌ | 14/40 [00:12<00:23, 1.09it/s]
38%|███▊ | 15/40 [00:13<00:22, 1.09it/s]
40%|████ | 16/40 [00:14<00:21, 1.09it/s]
42%|████▎ | 17/40 [00:15<00:21, 1.09it/s]
45%|████▌ | 18/40 [00:16<00:20, 1.09it/s]
48%|████▊ | 19/40 [00:17<00:19, 1.09it/s]
50%|█████ | 20/40 [00:18<00:18, 1.09it/s]
52%|█████▎ | 21/40 [00:19<00:17, 1.09it/s]
55%|█████▌ | 22/40 [00:20<00:16, 1.09it/s]
57%|█████▊ | 23/40 [00:21<00:15, 1.09it/s]
60%|██████ | 24/40 [00:22<00:14, 1.09it/s]
62%|██████▎ | 25/40 [00:23<00:13, 1.09it/s]
65%|██████▌ | 26/40 [00:23<00:12, 1.09it/s]
68%|██████▊ | 27/40 [00:24<00:11, 1.09it/s]
70%|███████ | 28/40 [00:25<00:11, 1.09it/s]
72%|███████▎ | 29/40 [00:26<00:10, 1.09it/s]
75%|███████▌ | 30/40 [00:27<00:09, 1.09it/s]
78%|███████▊ | 31/40 [00:28<00:08, 1.09it/s]
80%|████████ | 32/40 [00:29<00:07, 1.08it/s]
82%|████████▎ | 33/40 [00:30<00:06, 1.08it/s]
85%|████████▌ | 34/40 [00:31<00:05, 1.08it/s]
88%|████████▊ | 35/40 [00:32<00:04, 1.08it/s]
90%|█████████ | 36/40 [00:33<00:03, 1.08it/s]
92%|█████████▎| 37/40 [00:34<00:02, 1.08it/s]
95%|█████████▌| 38/40 [00:35<00:01, 1.08it/s]
98%|█████████▊| 39/40 [00:35<00:00, 1.08it/s]
100%|██████████| 40/40 [00:36<00:00, 1.08it/s]
100%|██████████| 40/40 [00:36<00:00, 1.08it/s]
0%| | 0/10 [00:00<?, ?it/s]
10%|█ | 1/10 [00:00<00:08, 1.08it/s]
20%|██ | 2/10 [00:01<00:07, 1.09it/s]
30%|███ | 3/10 [00:02<00:06, 1.09it/s]
40%|████ | 4/10 [00:03<00:05, 1.09it/s]
50%|█████ | 5/10 [00:04<00:04, 1.08it/s]
60%|██████ | 6/10 [00:05<00:03, 1.09it/s]
70%|███████ | 7/10 [00:06<00:02, 1.09it/s]
80%|████████ | 8/10 [00:07<00:01, 1.09it/s]
90%|█████████ | 9/10 [00:08<00:00, 1.09it/s]
100%|██████████| 10/10 [00:09<00:00, 1.09it/s]
100%|██████████| 10/10 [00:09<00:00, 1.09it/s]