Readme
This model doesn't have a readme.
callmejz-ai / doodle
Doodles trained on black line drawings, fashion illustrations, and wire sculptures. Simple images for complex intellectuals, luxury brands, b2b marketing, saas..
- Public
- 246 runs
-
L40S
- SDXL fine-tune
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=callmejz-ai/doodle
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";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run callmejz-ai/doodle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"callmejz-ai/doodle:b9e155a586824e58f5a5193d65b0992ae5b6e5ef7420c1a967638922c4e103a8",
{
input: {
width: 1024,
height: 1024,
prompt: "flower",
refine: "no_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: "",
prompt_strength: 0.8,
num_inference_steps: 50
}
}
);
// 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 callmejz-ai/doodle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"callmejz-ai/doodle:b9e155a586824e58f5a5193d65b0992ae5b6e5ef7420c1a967638922c4e103a8",
input={
"width": 1024,
"height": 1024,
"prompt": "flower",
"refine": "no_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": "",
"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 callmejz-ai/doodle 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": "callmejz-ai/doodle:b9e155a586824e58f5a5193d65b0992ae5b6e5ef7420c1a967638922c4e103a8",
"input": {
"width": 1024,
"height": 1024,
"prompt": "flower",
"refine": "no_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": "",
"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.
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": "2024-10-25T21:09:49.387587Z",
"created_at": "2024-10-25T21:09:20.611000Z",
"data_removed": false,
"error": null,
"id": "4dhywgsacdrgm0cjrp1s333qkc",
"input": {
"width": 1024,
"height": 1024,
"prompt": "flower",
"refine": "no_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": "",
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 7047\nEnsuring enough disk space...\nFree disk space: 1439622897664\nDownloading weights: https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar\n2024-10-25T21:09:27Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/b9e40f01def7cc54 url=https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar\n2024-10-25T21:09:32Z | INFO | [ Complete ] dest=/src/weights-cache/b9e40f01def7cc54 size=\"186 MB\" total_elapsed=4.907s url=https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar\nb''\nDownloaded weights in 5.0415003299713135 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: flower\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/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%|▏ | 1/50 [00:00<00:11, 4.20it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.19it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.17it/s]\n 8%|▊ | 4/50 [00:00<00:11, 4.16it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.16it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.16it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.16it/s]\n 16%|█▌ | 8/50 [00:01<00:10, 4.15it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.15it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.15it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.15it/s]\n 24%|██▍ | 12/50 [00:02<00:09, 4.16it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.16it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.15it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.15it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.16it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.15it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.15it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.15it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.15it/s]\n 42%|████▏ | 21/50 [00:05<00:06, 4.15it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.15it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.15it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.15it/s]\n 50%|█████ | 25/50 [00:06<00:06, 4.15it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.15it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.15it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.15it/s]\n 58%|█████▊ | 29/50 [00:06<00:05, 4.15it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.15it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.15it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.14it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.14it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.15it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.15it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.14it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.14it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.15it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.15it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.15it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.15it/s]\n 84%|████████▍ | 42/50 [00:10<00:01, 4.14it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.14it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.14it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.15it/s]\n 92%|█████████▏| 46/50 [00:11<00:00, 4.14it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.14it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.14it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.14it/s]\n100%|██████████| 50/50 [00:12<00:00, 4.14it/s]\n100%|██████████| 50/50 [00:12<00:00, 4.15it/s]",
"metrics": {
"predict_time": 21.646749119,
"total_time": 28.776587
},
"output": [
"https://replicate.delivery/pbxt/mwnCo7UxFypqBZTaNPfsfVbamEAzHvNGgsukppxa1ZycsbqTA/out-0.png"
],
"started_at": "2024-10-25T21:09:27.740838Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/4dhywgsacdrgm0cjrp1s333qkc",
"cancel": "https://api.replicate.com/v1/predictions/4dhywgsacdrgm0cjrp1s333qkc/cancel"
},
"version": "b9e155a586824e58f5a5193d65b0992ae5b6e5ef7420c1a967638922c4e103a8"
}Generated in
Using seed: 7047
Ensuring enough disk space...
Free disk space: 1439622897664
Downloading weights: https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar
2024-10-25T21:09:27Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/b9e40f01def7cc54 url=https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar
2024-10-25T21:09:32Z | INFO | [ Complete ] dest=/src/weights-cache/b9e40f01def7cc54 size="186 MB" total_elapsed=4.907s url=https://replicate.delivery/pbxt/WZoBJcam9jK2OtB0Loes20TaJNuR8C87mhikU4gLnbTU7M1JA/trained_model.tar
b''
Downloaded weights in 5.0415003299713135 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: flower
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]/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%|▏ | 1/50 [00:00<00:11, 4.20it/s]
4%|▍ | 2/50 [00:00<00:11, 4.19it/s]
6%|▌ | 3/50 [00:00<00:11, 4.17it/s]
8%|▊ | 4/50 [00:00<00:11, 4.16it/s]
10%|█ | 5/50 [00:01<00:10, 4.16it/s]
12%|█▏ | 6/50 [00:01<00:10, 4.16it/s]
14%|█▍ | 7/50 [00:01<00:10, 4.16it/s]
16%|█▌ | 8/50 [00:01<00:10, 4.15it/s]
18%|█▊ | 9/50 [00:02<00:09, 4.15it/s]
20%|██ | 10/50 [00:02<00:09, 4.15it/s]
22%|██▏ | 11/50 [00:02<00:09, 4.15it/s]
24%|██▍ | 12/50 [00:02<00:09, 4.16it/s]
26%|██▌ | 13/50 [00:03<00:08, 4.16it/s]
28%|██▊ | 14/50 [00:03<00:08, 4.15it/s]
30%|███ | 15/50 [00:03<00:08, 4.15it/s]
32%|███▏ | 16/50 [00:03<00:08, 4.16it/s]
34%|███▍ | 17/50 [00:04<00:07, 4.15it/s]
36%|███▌ | 18/50 [00:04<00:07, 4.15it/s]
38%|███▊ | 19/50 [00:04<00:07, 4.15it/s]
40%|████ | 20/50 [00:04<00:07, 4.15it/s]
42%|████▏ | 21/50 [00:05<00:06, 4.15it/s]
44%|████▍ | 22/50 [00:05<00:06, 4.15it/s]
46%|████▌ | 23/50 [00:05<00:06, 4.15it/s]
48%|████▊ | 24/50 [00:05<00:06, 4.15it/s]
50%|█████ | 25/50 [00:06<00:06, 4.15it/s]
52%|█████▏ | 26/50 [00:06<00:05, 4.15it/s]
54%|█████▍ | 27/50 [00:06<00:05, 4.15it/s]
56%|█████▌ | 28/50 [00:06<00:05, 4.15it/s]
58%|█████▊ | 29/50 [00:06<00:05, 4.15it/s]
60%|██████ | 30/50 [00:07<00:04, 4.15it/s]
62%|██████▏ | 31/50 [00:07<00:04, 4.15it/s]
64%|██████▍ | 32/50 [00:07<00:04, 4.14it/s]
66%|██████▌ | 33/50 [00:07<00:04, 4.14it/s]
68%|██████▊ | 34/50 [00:08<00:03, 4.15it/s]
70%|███████ | 35/50 [00:08<00:03, 4.15it/s]
72%|███████▏ | 36/50 [00:08<00:03, 4.14it/s]
74%|███████▍ | 37/50 [00:08<00:03, 4.14it/s]
76%|███████▌ | 38/50 [00:09<00:02, 4.15it/s]
78%|███████▊ | 39/50 [00:09<00:02, 4.15it/s]
80%|████████ | 40/50 [00:09<00:02, 4.15it/s]
82%|████████▏ | 41/50 [00:09<00:02, 4.15it/s]
84%|████████▍ | 42/50 [00:10<00:01, 4.14it/s]
86%|████████▌ | 43/50 [00:10<00:01, 4.14it/s]
88%|████████▊ | 44/50 [00:10<00:01, 4.14it/s]
90%|█████████ | 45/50 [00:10<00:01, 4.15it/s]
92%|█████████▏| 46/50 [00:11<00:00, 4.14it/s]
94%|█████████▍| 47/50 [00:11<00:00, 4.14it/s]
96%|█████████▌| 48/50 [00:11<00:00, 4.14it/s]
98%|█████████▊| 49/50 [00:11<00:00, 4.14it/s]
100%|██████████| 50/50 [00:12<00:00, 4.14it/s]
100%|██████████| 50/50 [00:12<00:00, 4.15it/s]Examples
Run time and cost
This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.