chenxwh/hunyuandit:0cc2a985 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

chenxwh /hunyuandit:0cc2a985

Input

prompt

string

Shift + Return to add a new line

一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影

Input prompt

Default: "一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影"

negative_prompt

string

Shift + Return to add a new line

错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺

Specify things to not see in the output

Default: "错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺"

size

string

Choose the output size. square: (1024, 1024), landscape: (768, 1280), portrait: (1280, 768).

Default: "square"

infer_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 40

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 6

enhance_prompt

boolean

Choose if enhance the prompt.

Default: false

sampler

string

Choose a sampler.

Default: "ddpm"

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=chenxwh/hunyuandit

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

const output = await replicate.run(
  "chenxwh/hunyuandit:0cc2a985f119c84a952b916e52a68e32f9ff7da5e05b271b081c3838a7de93b2",
  {
    input: {
      size: "square",
      prompt: "一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影",
      sampler: "ddpm",
      infer_steps: 20,
      enhance_prompt: false,
      guidance_scale: 6,
      negative_prompt: "错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

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

output = replicate.run(
    "chenxwh/hunyuandit:0cc2a985f119c84a952b916e52a68e32f9ff7da5e05b271b081c3838a7de93b2",
    input={
        "size": "square",
        "prompt": "一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影",
        "sampler": "ddpm",
        "infer_steps": 20,
        "enhance_prompt": False,
        "guidance_scale": 6,
        "negative_prompt": "错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺"
    }
)
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 chenxwh/hunyuandit 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": "chenxwh/hunyuandit:0cc2a985f119c84a952b916e52a68e32f9ff7da5e05b271b081c3838a7de93b2",
    "input": {
      "size": "square",
      "prompt": "一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影",
      "sampler": "ddpm",
      "infer_steps": 20,
      "enhance_prompt": false,
      "guidance_scale": 6,
      "negative_prompt": "错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-05-23T23:28:04.867807Z",
  "created_at": "2024-05-23T23:27:45.001000Z",
  "data_removed": false,
  "error": null,
  "id": "bthdy11dd5rgg0cfmz4axrdt6c",
  "input": {
    "size": "square",
    "prompt": "一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影",
    "sampler": "ddpm",
    "infer_steps": 20,
    "enhance_prompt": false,
    "guidance_scale": 6,
    "negative_prompt": "错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺"
  },
  "logs": "Using seed: 17152\n2024-05-23 23:27:45.010 | INFO     | hydit.inference:predict:312 - Input (height, width) = (1024, 1024)\n2024-05-23 23:27:45.011 | INFO     | hydit.inference:predict:317 - Align to 16: (height, width) = (1024, 1024)\n2024-05-23 23:27:45.011 | DEBUG    | hydit.inference:predict:363 -\nprompt: 一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影\nenhanced prompt: None\nseed: 17152\n(height, width): (1024, 1024)\nnegative_prompt: 错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺\nbatch_size: 1\nguidance_scale: 6.0\ninfer_steps: 20\nimage_meta_size: [1024, 1024, 1024, 1024, 0, 0]\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:17,  1.09it/s]\n 10%|█         | 2/20 [00:01<00:16,  1.09it/s]\n 15%|█▌        | 3/20 [00:02<00:15,  1.09it/s]\n 20%|██        | 4/20 [00:03<00:14,  1.09it/s]\n 25%|██▌       | 5/20 [00:04<00:13,  1.08it/s]\n 30%|███       | 6/20 [00:05<00:12,  1.08it/s]\n 35%|███▌      | 7/20 [00:06<00:11,  1.08it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.08it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.08it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.08it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.08it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.08it/s]\n 65%|██████▌   | 13/20 [00:11<00:06,  1.08it/s]\n 70%|███████   | 14/20 [00:12<00:05,  1.08it/s]\n 75%|███████▌  | 15/20 [00:13<00:04,  1.08it/s]\n 80%|████████  | 16/20 [00:14<00:03,  1.08it/s]\n 85%|████████▌ | 17/20 [00:15<00:02,  1.08it/s]\n 90%|█████████ | 18/20 [00:16<00:01,  1.08it/s]\n 95%|█████████▌| 19/20 [00:17<00:00,  1.08it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.08it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.08it/s]\n2024-05-23 23:28:03.974 | DEBUG    | hydit.inference:predict:400 - Success, time: 18.96296739578247",
  "metrics": {
    "predict_time": 19.857278,
    "total_time": 19.866807
  },
  "output": "https://replicate.delivery/pbxt/WE6QOERp6ObcIluFRWkUc5Pf1KfClmLH0h2GjM02aKvEMY3SA/out.png",
  "started_at": "2024-05-23T23:27:45.010529Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bthdy11dd5rgg0cfmz4axrdt6c",
    "cancel": "https://api.replicate.com/v1/predictions/bthdy11dd5rgg0cfmz4axrdt6c/cancel"
  },
  "version": "0cc2a985f119c84a952b916e52a68e32f9ff7da5e05b271b081c3838a7de93b2"
}

Generated in

19.9 seconds

Tweak it Share Report

Using seed: 17152
2024-05-23 23:27:45.010 | INFO     | hydit.inference:predict:312 - Input (height, width) = (1024, 1024)
2024-05-23 23:27:45.011 | INFO     | hydit.inference:predict:317 - Align to 16: (height, width) = (1024, 1024)
2024-05-23 23:27:45.011 | DEBUG    | hydit.inference:predict:363 -
prompt: 一只聪明的狐狸走在阔叶树林里, 旁边是一条小溪, 细节真实, 摄影
enhanced prompt: None
seed: 17152
(height, width): (1024, 1024)
negative_prompt: 错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺
batch_size: 1
guidance_scale: 6.0
infer_steps: 20
image_meta_size: [1024, 1024, 1024, 1024, 0, 0]
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:17,  1.09it/s]
 10%|█         | 2/20 [00:01<00:16,  1.09it/s]
 15%|█▌        | 3/20 [00:02<00:15,  1.09it/s]
 20%|██        | 4/20 [00:03<00:14,  1.09it/s]
 25%|██▌       | 5/20 [00:04<00:13,  1.08it/s]
 30%|███       | 6/20 [00:05<00:12,  1.08it/s]
 35%|███▌      | 7/20 [00:06<00:11,  1.08it/s]
 40%|████      | 8/20 [00:07<00:11,  1.08it/s]
 45%|████▌     | 9/20 [00:08<00:10,  1.08it/s]
 50%|█████     | 10/20 [00:09<00:09,  1.08it/s]
 55%|█████▌    | 11/20 [00:10<00:08,  1.08it/s]
 60%|██████    | 12/20 [00:11<00:07,  1.08it/s]
 65%|██████▌   | 13/20 [00:11<00:06,  1.08it/s]
 70%|███████   | 14/20 [00:12<00:05,  1.08it/s]
 75%|███████▌  | 15/20 [00:13<00:04,  1.08it/s]
 80%|████████  | 16/20 [00:14<00:03,  1.08it/s]
 85%|████████▌ | 17/20 [00:15<00:02,  1.08it/s]
 90%|█████████ | 18/20 [00:16<00:01,  1.08it/s]
 95%|█████████▌| 19/20 [00:17<00:00,  1.08it/s]
100%|██████████| 20/20 [00:18<00:00,  1.08it/s]
100%|██████████| 20/20 [00:18<00:00,  1.08it/s]
2024-05-23 23:28:03.974 | DEBUG    | hydit.inference:predict:400 - Success, time: 18.96296739578247