cloneofsimo/avatar – Run with an API on Replicate

cloneofsimo / avatar

Generate characters from Avatar

Cold

Public
175 runs
T4

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a photo of <1> riding a horse on mars, avatarart stylea photo of <1> riding a horse on mars, avatarart style

Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts

Default: "a photo of <1> riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

Default: ""

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

lora_urls

string

Shift + Return to add a new line

List of urls for safetensors of lora models, seperated with | . If provided, it will override all above options.

Default: ""

lora_scales

string

Shift + Return to add a new line

List of scales for safetensors of lora models, seperated with |

Default: "0.3"

seed

integer

Random seed. Leave blank to randomize the seed

Run this model in Node.js with one line of code:

npx create-replicate --model=cloneofsimo/avatar

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set 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 cloneofsimo/avatar using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cloneofsimo/avatar:f72c64e7bdc9dfa0204a9700aca5c038d2f43c032ee97292b15ee7365651fe78",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "a photo of <1> riding a horse on mars, avatarart style",
      lora_urls: "",
      scheduler: "DPMSolverMultistep",
      lora_scales: "0.3",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "",
      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 replicate

Set 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 replicate

Run cloneofsimo/avatar using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cloneofsimo/avatar:f72c64e7bdc9dfa0204a9700aca5c038d2f43c032ee97292b15ee7365651fe78",
    input={
        "width": 512,
        "height": 512,
        "prompt": "a photo of <1> riding a horse on mars, avatarart style",
        "lora_urls": "",
        "scheduler": "DPMSolverMultistep",
        "lora_scales": "0.3",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "",
        "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 cloneofsimo/avatar 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": "f72c64e7bdc9dfa0204a9700aca5c038d2f43c032ee97292b15ee7365651fe78",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "a photo of <1> riding a horse on mars, avatarart style",
      "lora_urls": "",
      "scheduler": "DPMSolverMultistep",
      "lora_scales": "0.3",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "",
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2023-02-07T09:12:48.567509Z",
  "created_at": "2023-02-07T09:12:24.348184Z",
  "data_removed": false,
  "error": null,
  "id": "6py6tchzlbb5bco6vundazwmde",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "a photo of <1> riding a horse on mars, avatarart style",
    "scheduler": "DPMSolverMultistep",
    "lora_scales": "0.3",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 41696\nNo LoRA models provided, using default model...\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:24,  1.97it/s]\n  4%|▍         | 2/50 [00:00<00:22,  2.15it/s]\n  6%|▌         | 3/50 [00:01<00:21,  2.20it/s]\n  8%|▊         | 4/50 [00:01<00:20,  2.23it/s]\n 10%|█         | 5/50 [00:02<00:20,  2.24it/s]\n 12%|█▏        | 6/50 [00:02<00:19,  2.25it/s]\n 14%|█▍        | 7/50 [00:03<00:19,  2.25it/s]\n 16%|█▌        | 8/50 [00:03<00:18,  2.25it/s]\n 18%|█▊        | 9/50 [00:04<00:18,  2.26it/s]\n 20%|██        | 10/50 [00:04<00:17,  2.26it/s]\n 22%|██▏       | 11/50 [00:04<00:17,  2.26it/s]\n 24%|██▍       | 12/50 [00:05<00:16,  2.26it/s]\n 26%|██▌       | 13/50 [00:05<00:16,  2.26it/s]\n 28%|██▊       | 14/50 [00:06<00:15,  2.26it/s]\n 30%|███       | 15/50 [00:06<00:15,  2.26it/s]\n 32%|███▏      | 16/50 [00:07<00:15,  2.26it/s]\n 34%|███▍      | 17/50 [00:07<00:14,  2.26it/s]\n 36%|███▌      | 18/50 [00:08<00:14,  2.26it/s]\n 38%|███▊      | 19/50 [00:08<00:13,  2.25it/s]\n 40%|████      | 20/50 [00:08<00:13,  2.26it/s]\n 42%|████▏     | 21/50 [00:09<00:12,  2.25it/s]\n 44%|████▍     | 22/50 [00:09<00:12,  2.25it/s]\n 46%|████▌     | 23/50 [00:10<00:12,  2.25it/s]\n 48%|████▊     | 24/50 [00:10<00:11,  2.24it/s]\n 50%|█████     | 25/50 [00:11<00:11,  2.24it/s]\n 52%|█████▏    | 26/50 [00:11<00:10,  2.23it/s]\n 54%|█████▍    | 27/50 [00:12<00:10,  2.24it/s]\n 56%|█████▌    | 28/50 [00:12<00:09,  2.24it/s]\n 58%|█████▊    | 29/50 [00:12<00:09,  2.24it/s]\n 60%|██████    | 30/50 [00:13<00:08,  2.24it/s]\n 62%|██████▏   | 31/50 [00:13<00:08,  2.24it/s]\n 64%|██████▍   | 32/50 [00:14<00:08,  2.24it/s]\n 66%|██████▌   | 33/50 [00:14<00:07,  2.24it/s]\n 68%|██████▊   | 34/50 [00:15<00:07,  2.24it/s]\n 70%|███████   | 35/50 [00:15<00:06,  2.25it/s]\n 72%|███████▏  | 36/50 [00:16<00:06,  2.24it/s]\n 74%|███████▍  | 37/50 [00:16<00:05,  2.24it/s]\n 76%|███████▌  | 38/50 [00:16<00:05,  2.24it/s]\n 78%|███████▊  | 39/50 [00:17<00:04,  2.24it/s]\n 80%|████████  | 40/50 [00:17<00:04,  2.24it/s]\n 82%|████████▏ | 41/50 [00:18<00:04,  2.24it/s]\n 84%|████████▍ | 42/50 [00:18<00:03,  2.23it/s]\n 86%|████████▌ | 43/50 [00:19<00:03,  2.23it/s]\n 88%|████████▊ | 44/50 [00:19<00:02,  2.22it/s]\n 90%|█████████ | 45/50 [00:20<00:02,  2.22it/s]\n 92%|█████████▏| 46/50 [00:20<00:01,  2.23it/s]\n 94%|█████████▍| 47/50 [00:20<00:01,  2.23it/s]\n 96%|█████████▌| 48/50 [00:21<00:00,  2.23it/s]\n 98%|█████████▊| 49/50 [00:21<00:00,  2.23it/s]\n100%|██████████| 50/50 [00:22<00:00,  2.23it/s]\n100%|██████████| 50/50 [00:22<00:00,  2.24it/s]",
  "metrics": {
    "predict_time": 23.280949,
    "total_time": 24.219325
  },
  "output": [
    "https://replicate.delivery/pbxt/lLGfls5zK0Te5ELLvMb2yqRmTe2b2gvVAkFjpy2S6RBhA53gA/out-0.png"
  ],
  "started_at": "2023-02-07T09:12:25.286560Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6py6tchzlbb5bco6vundazwmde",
    "cancel": "https://api.replicate.com/v1/predictions/6py6tchzlbb5bco6vundazwmde/cancel"
  },
  "version": "f72c64e7bdc9dfa0204a9700aca5c038d2f43c032ee97292b15ee7365651fe78"
}

Generated in

23.3 seconds

Tweak itReport

Using seed: 41696
No LoRA models provided, using default model...
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:24,  1.97it/s]
  4%|▍         | 2/50 [00:00<00:22,  2.15it/s]
  6%|▌         | 3/50 [00:01<00:21,  2.20it/s]
  8%|▊         | 4/50 [00:01<00:20,  2.23it/s]
 10%|█         | 5/50 [00:02<00:20,  2.24it/s]
 12%|█▏        | 6/50 [00:02<00:19,  2.25it/s]
 14%|█▍        | 7/50 [00:03<00:19,  2.25it/s]
 16%|█▌        | 8/50 [00:03<00:18,  2.25it/s]
 18%|█▊        | 9/50 [00:04<00:18,  2.26it/s]
 20%|██        | 10/50 [00:04<00:17,  2.26it/s]
 22%|██▏       | 11/50 [00:04<00:17,  2.26it/s]
 24%|██▍       | 12/50 [00:05<00:16,  2.26it/s]
 26%|██▌       | 13/50 [00:05<00:16,  2.26it/s]
 28%|██▊       | 14/50 [00:06<00:15,  2.26it/s]
 30%|███       | 15/50 [00:06<00:15,  2.26it/s]
 32%|███▏      | 16/50 [00:07<00:15,  2.26it/s]
 34%|███▍      | 17/50 [00:07<00:14,  2.26it/s]
 36%|███▌      | 18/50 [00:08<00:14,  2.26it/s]
 38%|███▊      | 19/50 [00:08<00:13,  2.25it/s]
 40%|████      | 20/50 [00:08<00:13,  2.26it/s]
 42%|████▏     | 21/50 [00:09<00:12,  2.25it/s]
 44%|████▍     | 22/50 [00:09<00:12,  2.25it/s]
 46%|████▌     | 23/50 [00:10<00:12,  2.25it/s]
 48%|████▊     | 24/50 [00:10<00:11,  2.24it/s]
 50%|█████     | 25/50 [00:11<00:11,  2.24it/s]
 52%|█████▏    | 26/50 [00:11<00:10,  2.23it/s]
 54%|█████▍    | 27/50 [00:12<00:10,  2.24it/s]
 56%|█████▌    | 28/50 [00:12<00:09,  2.24it/s]
 58%|█████▊    | 29/50 [00:12<00:09,  2.24it/s]
 60%|██████    | 30/50 [00:13<00:08,  2.24it/s]
 62%|██████▏   | 31/50 [00:13<00:08,  2.24it/s]
 64%|██████▍   | 32/50 [00:14<00:08,  2.24it/s]
 66%|██████▌   | 33/50 [00:14<00:07,  2.24it/s]
 68%|██████▊   | 34/50 [00:15<00:07,  2.24it/s]
 70%|███████   | 35/50 [00:15<00:06,  2.25it/s]
 72%|███████▏  | 36/50 [00:16<00:06,  2.24it/s]
 74%|███████▍  | 37/50 [00:16<00:05,  2.24it/s]
 76%|███████▌  | 38/50 [00:16<00:05,  2.24it/s]
 78%|███████▊  | 39/50 [00:17<00:04,  2.24it/s]
 80%|████████  | 40/50 [00:17<00:04,  2.24it/s]
 82%|████████▏ | 41/50 [00:18<00:04,  2.24it/s]
 84%|████████▍ | 42/50 [00:18<00:03,  2.23it/s]
 86%|████████▌ | 43/50 [00:19<00:03,  2.23it/s]
 88%|████████▊ | 44/50 [00:19<00:02,  2.22it/s]
 90%|█████████ | 45/50 [00:20<00:02,  2.22it/s]
 92%|█████████▏| 46/50 [00:20<00:01,  2.23it/s]
 94%|█████████▍| 47/50 [00:20<00:01,  2.23it/s]
 96%|█████████▌| 48/50 [00:21<00:00,  2.23it/s]
 98%|█████████▊| 49/50 [00:21<00:00,  2.23it/s]
100%|██████████| 50/50 [00:22<00:00,  2.23it/s]
100%|██████████| 50/50 [00:22<00:00,  2.24it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.066 to run on Replicate, or 15 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 T4 GPU hardware. Predictions typically complete within 5 minutes. The predict time for this model varies significantly based on the inputs.

Readme

LoRA-capable, fp16 model of Avatar characters