Readme
This is a fine-tuned version of SDXL trained on images of the βThis is Fineβ dog π₯
Create your own variants of "this is fine" π₯βοΈπ
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run zeke/this-is-fine using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"zeke/this-is-fine:11edb7172944ea9372d17aca78e8f016946bebab73d66765e20a9315609ff750",
{
input: {
width: 1024,
height: 1024,
prompt: "a llama sitting at a table in the style of THIS_IS_FINE with fire all around",
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
}
}
);
console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run zeke/this-is-fine using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"zeke/this-is-fine:11edb7172944ea9372d17aca78e8f016946bebab73d66765e20a9315609ff750",
input={
"width": 1024,
"height": 1024,
"prompt": "a llama sitting at a table in the style of THIS_IS_FINE with fire all around",
"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.
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run zeke/this-is-fine using Replicateβs 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": "11edb7172944ea9372d17aca78e8f016946bebab73d66765e20a9315609ff750",
"input": {
"width": 1024,
"height": 1024,
"prompt": "a llama sitting at a table in the style of THIS_IS_FINE with fire all around",
"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/predictions
To learn more, take a look at Replicateβs HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2023-08-17T18:50:23.377411Z",
"created_at": "2023-08-17T18:50:07.818823Z",
"data_removed": false,
"error": null,
"id": "6pr62udbpsmlo5p77hlasaeu6e",
"input": {
"width": 1024,
"height": 1024,
"prompt": "a llama sitting at a table in the style of THIS_IS_FINE with fire all around",
"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,
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 54488\nPrompt: a llama sitting at a table in the style of <s0><s1> with fire all around\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|β | 1/50 [00:00<00:13, 3.72it/s]\n 4%|β | 2/50 [00:00<00:12, 3.72it/s]\n 6%|β | 3/50 [00:00<00:12, 3.72it/s]\n 8%|β | 4/50 [00:01<00:12, 3.72it/s]\n 10%|β | 5/50 [00:01<00:12, 3.72it/s]\n 12%|ββ | 6/50 [00:01<00:11, 3.71it/s]\n 14%|ββ | 7/50 [00:01<00:11, 3.67it/s]\n 16%|ββ | 8/50 [00:02<00:11, 3.68it/s]\n 18%|ββ | 9/50 [00:02<00:11, 3.69it/s]\n 20%|ββ | 10/50 [00:02<00:10, 3.70it/s]\n 22%|βββ | 11/50 [00:02<00:10, 3.70it/s]\n 24%|βββ | 12/50 [00:03<00:10, 3.70it/s]\n 26%|βββ | 13/50 [00:03<00:10, 3.70it/s]\n 28%|βββ | 14/50 [00:03<00:09, 3.70it/s]\n 30%|βββ | 15/50 [00:04<00:09, 3.70it/s]\n 32%|ββββ | 16/50 [00:04<00:09, 3.70it/s]\n 34%|ββββ | 17/50 [00:04<00:08, 3.70it/s]\n 36%|ββββ | 18/50 [00:04<00:08, 3.70it/s]\n 38%|ββββ | 19/50 [00:05<00:08, 3.70it/s]\n 40%|ββββ | 20/50 [00:05<00:08, 3.70it/s]\n 42%|βββββ | 21/50 [00:05<00:07, 3.70it/s]\n 44%|βββββ | 22/50 [00:05<00:07, 3.70it/s]\n 46%|βββββ | 23/50 [00:06<00:07, 3.69it/s]\n 48%|βββββ | 24/50 [00:06<00:07, 3.70it/s]\n 50%|βββββ | 25/50 [00:06<00:06, 3.69it/s]\n 52%|ββββββ | 26/50 [00:07<00:06, 3.69it/s]\n 54%|ββββββ | 27/50 [00:07<00:06, 3.69it/s]\n 56%|ββββββ | 28/50 [00:07<00:05, 3.69it/s]\n 58%|ββββββ | 29/50 [00:07<00:05, 3.69it/s]\n 60%|ββββββ | 30/50 [00:08<00:05, 3.70it/s]\n 62%|βββββββ | 31/50 [00:08<00:05, 3.69it/s]\n 64%|βββββββ | 32/50 [00:08<00:04, 3.70it/s]\n 66%|βββββββ | 33/50 [00:08<00:04, 3.70it/s]\n 68%|βββββββ | 34/50 [00:09<00:04, 3.69it/s]\n 70%|βββββββ | 35/50 [00:09<00:04, 3.69it/s]\n 72%|ββββββββ | 36/50 [00:09<00:03, 3.69it/s]\n 74%|ββββββββ | 37/50 [00:10<00:03, 3.69it/s]\n 76%|ββββββββ | 38/50 [00:10<00:03, 3.69it/s]\n 78%|ββββββββ | 39/50 [00:10<00:02, 3.69it/s]\n 80%|ββββββββ | 40/50 [00:10<00:02, 3.69it/s]\n 82%|βββββββββ | 41/50 [00:11<00:02, 3.69it/s]\n 84%|βββββββββ | 42/50 [00:11<00:02, 3.69it/s]\n 86%|βββββββββ | 43/50 [00:11<00:01, 3.69it/s]\n 88%|βββββββββ | 44/50 [00:11<00:01, 3.69it/s]\n 90%|βββββββββ | 45/50 [00:12<00:01, 3.69it/s]\n 92%|ββββββββββ| 46/50 [00:12<00:01, 3.69it/s]\n 94%|ββββββββββ| 47/50 [00:12<00:00, 3.69it/s]\n 96%|ββββββββββ| 48/50 [00:12<00:00, 3.69it/s]\n 98%|ββββββββββ| 49/50 [00:13<00:00, 3.69it/s]\n100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]\n100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]",
"metrics": {
"predict_time": 15.573238,
"total_time": 15.558588
},
"output": [
"https://replicate.delivery/pbxt/jPVBJemj8O2VOKYv9qZeeJLN0JO4TyQFDEnWiT3cPpUdvD2iA/out-0.png"
],
"started_at": "2023-08-17T18:50:07.804173Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/6pr62udbpsmlo5p77hlasaeu6e",
"cancel": "https://api.replicate.com/v1/predictions/6pr62udbpsmlo5p77hlasaeu6e/cancel"
},
"version": "11edb7172944ea9372d17aca78e8f016946bebab73d66765e20a9315609ff750"
}
Using seed: 54488
Prompt: a llama sitting at a table in the style of <s0><s1> with fire all around
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|β | 1/50 [00:00<00:13, 3.72it/s]
4%|β | 2/50 [00:00<00:12, 3.72it/s]
6%|β | 3/50 [00:00<00:12, 3.72it/s]
8%|β | 4/50 [00:01<00:12, 3.72it/s]
10%|β | 5/50 [00:01<00:12, 3.72it/s]
12%|ββ | 6/50 [00:01<00:11, 3.71it/s]
14%|ββ | 7/50 [00:01<00:11, 3.67it/s]
16%|ββ | 8/50 [00:02<00:11, 3.68it/s]
18%|ββ | 9/50 [00:02<00:11, 3.69it/s]
20%|ββ | 10/50 [00:02<00:10, 3.70it/s]
22%|βββ | 11/50 [00:02<00:10, 3.70it/s]
24%|βββ | 12/50 [00:03<00:10, 3.70it/s]
26%|βββ | 13/50 [00:03<00:10, 3.70it/s]
28%|βββ | 14/50 [00:03<00:09, 3.70it/s]
30%|βββ | 15/50 [00:04<00:09, 3.70it/s]
32%|ββββ | 16/50 [00:04<00:09, 3.70it/s]
34%|ββββ | 17/50 [00:04<00:08, 3.70it/s]
36%|ββββ | 18/50 [00:04<00:08, 3.70it/s]
38%|ββββ | 19/50 [00:05<00:08, 3.70it/s]
40%|ββββ | 20/50 [00:05<00:08, 3.70it/s]
42%|βββββ | 21/50 [00:05<00:07, 3.70it/s]
44%|βββββ | 22/50 [00:05<00:07, 3.70it/s]
46%|βββββ | 23/50 [00:06<00:07, 3.69it/s]
48%|βββββ | 24/50 [00:06<00:07, 3.70it/s]
50%|βββββ | 25/50 [00:06<00:06, 3.69it/s]
52%|ββββββ | 26/50 [00:07<00:06, 3.69it/s]
54%|ββββββ | 27/50 [00:07<00:06, 3.69it/s]
56%|ββββββ | 28/50 [00:07<00:05, 3.69it/s]
58%|ββββββ | 29/50 [00:07<00:05, 3.69it/s]
60%|ββββββ | 30/50 [00:08<00:05, 3.70it/s]
62%|βββββββ | 31/50 [00:08<00:05, 3.69it/s]
64%|βββββββ | 32/50 [00:08<00:04, 3.70it/s]
66%|βββββββ | 33/50 [00:08<00:04, 3.70it/s]
68%|βββββββ | 34/50 [00:09<00:04, 3.69it/s]
70%|βββββββ | 35/50 [00:09<00:04, 3.69it/s]
72%|ββββββββ | 36/50 [00:09<00:03, 3.69it/s]
74%|ββββββββ | 37/50 [00:10<00:03, 3.69it/s]
76%|ββββββββ | 38/50 [00:10<00:03, 3.69it/s]
78%|ββββββββ | 39/50 [00:10<00:02, 3.69it/s]
80%|ββββββββ | 40/50 [00:10<00:02, 3.69it/s]
82%|βββββββββ | 41/50 [00:11<00:02, 3.69it/s]
84%|βββββββββ | 42/50 [00:11<00:02, 3.69it/s]
86%|βββββββββ | 43/50 [00:11<00:01, 3.69it/s]
88%|βββββββββ | 44/50 [00:11<00:01, 3.69it/s]
90%|βββββββββ | 45/50 [00:12<00:01, 3.69it/s]
92%|ββββββββββ| 46/50 [00:12<00:01, 3.69it/s]
94%|ββββββββββ| 47/50 [00:12<00:00, 3.69it/s]
96%|ββββββββββ| 48/50 [00:12<00:00, 3.69it/s]
98%|ββββββββββ| 49/50 [00:13<00:00, 3.69it/s]
100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]
100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]
This model costs approximately $0.015 to run on Replicate, or 66 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 16 seconds.
This is a fine-tuned version of SDXL trained on images of the βThis is Fineβ dog π₯
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Using seed: 54488
Prompt: a llama sitting at a table in the style of <s0><s1> with fire all around
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|β | 1/50 [00:00<00:13, 3.72it/s]
4%|β | 2/50 [00:00<00:12, 3.72it/s]
6%|β | 3/50 [00:00<00:12, 3.72it/s]
8%|β | 4/50 [00:01<00:12, 3.72it/s]
10%|β | 5/50 [00:01<00:12, 3.72it/s]
12%|ββ | 6/50 [00:01<00:11, 3.71it/s]
14%|ββ | 7/50 [00:01<00:11, 3.67it/s]
16%|ββ | 8/50 [00:02<00:11, 3.68it/s]
18%|ββ | 9/50 [00:02<00:11, 3.69it/s]
20%|ββ | 10/50 [00:02<00:10, 3.70it/s]
22%|βββ | 11/50 [00:02<00:10, 3.70it/s]
24%|βββ | 12/50 [00:03<00:10, 3.70it/s]
26%|βββ | 13/50 [00:03<00:10, 3.70it/s]
28%|βββ | 14/50 [00:03<00:09, 3.70it/s]
30%|βββ | 15/50 [00:04<00:09, 3.70it/s]
32%|ββββ | 16/50 [00:04<00:09, 3.70it/s]
34%|ββββ | 17/50 [00:04<00:08, 3.70it/s]
36%|ββββ | 18/50 [00:04<00:08, 3.70it/s]
38%|ββββ | 19/50 [00:05<00:08, 3.70it/s]
40%|ββββ | 20/50 [00:05<00:08, 3.70it/s]
42%|βββββ | 21/50 [00:05<00:07, 3.70it/s]
44%|βββββ | 22/50 [00:05<00:07, 3.70it/s]
46%|βββββ | 23/50 [00:06<00:07, 3.69it/s]
48%|βββββ | 24/50 [00:06<00:07, 3.70it/s]
50%|βββββ | 25/50 [00:06<00:06, 3.69it/s]
52%|ββββββ | 26/50 [00:07<00:06, 3.69it/s]
54%|ββββββ | 27/50 [00:07<00:06, 3.69it/s]
56%|ββββββ | 28/50 [00:07<00:05, 3.69it/s]
58%|ββββββ | 29/50 [00:07<00:05, 3.69it/s]
60%|ββββββ | 30/50 [00:08<00:05, 3.70it/s]
62%|βββββββ | 31/50 [00:08<00:05, 3.69it/s]
64%|βββββββ | 32/50 [00:08<00:04, 3.70it/s]
66%|βββββββ | 33/50 [00:08<00:04, 3.70it/s]
68%|βββββββ | 34/50 [00:09<00:04, 3.69it/s]
70%|βββββββ | 35/50 [00:09<00:04, 3.69it/s]
72%|ββββββββ | 36/50 [00:09<00:03, 3.69it/s]
74%|ββββββββ | 37/50 [00:10<00:03, 3.69it/s]
76%|ββββββββ | 38/50 [00:10<00:03, 3.69it/s]
78%|ββββββββ | 39/50 [00:10<00:02, 3.69it/s]
80%|ββββββββ | 40/50 [00:10<00:02, 3.69it/s]
82%|βββββββββ | 41/50 [00:11<00:02, 3.69it/s]
84%|βββββββββ | 42/50 [00:11<00:02, 3.69it/s]
86%|βββββββββ | 43/50 [00:11<00:01, 3.69it/s]
88%|βββββββββ | 44/50 [00:11<00:01, 3.69it/s]
90%|βββββββββ | 45/50 [00:12<00:01, 3.69it/s]
92%|ββββββββββ| 46/50 [00:12<00:01, 3.69it/s]
94%|ββββββββββ| 47/50 [00:12<00:00, 3.69it/s]
96%|ββββββββββ| 48/50 [00:12<00:00, 3.69it/s]
98%|ββββββββββ| 49/50 [00:13<00:00, 3.69it/s]
100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]
100%|ββββββββββ| 50/50 [00:13<00:00, 3.69it/s]