# Stable Diffusion XL ( API )
Reverse engineered API of Stable Diffusion XL 1.0 ( Midjourney Alternative ) via https://replicate.com/ , A text-to-image generative AI model that creates beautiful 1024x1024 images.
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/d1022d40-05f0-4d2d-a37e-8cab7d444bec" width="900" >
# Table of Contents
- [Stable Diffusion XL ( API )](#stable-diffusion-xl---api--)
* [Prerequisites](#prerequisites)
* [Installation](#installation)
* [Usage](#usage)
* [Send Prompt to generate image](#send-prompt-to-generate-image)
+ [Output](#output)
* [Example Images Generated](#example-images-generated)
* [Advanced Generation using parameters](#advanced-generation-using-parameters)
+ [List of parameters](#list-of-parameters)
* [CLI Version](#cli-version)
* [Disclaimer](#disclaimer)
* [License](#license)
## Prerequisites
To use this API, you need to have the following:
Python installed on your system
requests library installed
```bash
pip install requests
```
## Installation
To use the Claude AI Unofficial API, you can either clone the GitHub repository or directly download the Python file.
Terminal :
pip install sdxl
or
Clone the repository:
git clone https://github.com/KoushikNavuluri/stable-diffusion-xl-api.git
## Usage
Import the claude_api module in your Python script:
from sdxl import ImageGenerator
* Next, you need to create an instance of the ImageGenerator class:
```bash
client = ImageGenerator()
```
## Send Prompt to generate image
```bash
images = sdxl.gen_image(
"Vibrant, Headshot of a serene, meditating individual surrounded by soft, ambient lighting.")
print(images)
```
### Output
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/5f362c03-d8f1-462c-873a-40e47bdaea63" width="600" >
## Example Images Generated
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/eb1976ac-0cf7-4817-9116-bd7384282380" width="200" >
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/9bcfa7de-338e-48ca-a008-a068236d052c" width="200">
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/a7ad3bc8-431a-40d3-a43f-aec9426b8f18" width="200" >
<img src="https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/1fd90d12-aaba-4fce-bf94-2077355a5d41" width="200">
## Advanced Generation using parameters
```bash
#Parameters set to their default values
images = sdxl.gen_image(prompt=
"Vibrant, Headshot of a serene, meditating individual surrounded by soft, ambient lighting.",count=1, width=1024, height=1024, refine="expert_ensemble_refiner", scheduler="DDIM", guidance_scale=7.5, high_noise_frac=0.8, prompt_strength=0.8, num_inference_steps=50)
print(images)
```
### List of parameters
* prompt = Input text prompt
* width = Width of output image(max:1024)
* height = height of output image(max:1024)
* count = Number of images to output. (minimum: 1; maximum: 4)
* refine = Which refine style to use ( no_refiner or expert_ensemble_refiner or base_image_refiner )
* scheduler = scheduler (valid_schedulers = ["DDIM" or "DPMSolverMultistep" or "HeunDiscrete" or "KarrasDPM" or "K_EULER_ANCESTRAL" or "K_EULER" or "PNDM"])
* guidance_scale = Scale for classifier-free guidance (minimum: 1; maximum: 50)
* prompt_strength = Prompt strength in image (maximum: 1)
* num_inference_steps = Number of denoising steps (minimum: 1; maximum: 500)
* high_noise_frac = for expert_ensemble_refiner, the fraction of noise to use (maximum: 1)
## CLI Version
For cli version you can check example folder in this repository (filename:cli.py)
> How to:
```bash
python main.py "beautiful landscape with two kittens,realistic,4k" --count 1 --width 1024 --height 1024 --refine expert_ensemble_refiner --scheduler DDIM --guidance_scale 7.5 --high_noise_frac 0.6 --prompt_strength 0.9 --num_inference_steps 40
```
## Disclaimer
This project provides an unofficial API for Replicate's Stable Diffusion XL and is not affiliated with or endorsed by Replicate or Stable Diffusion. Use it at your own risk.
## License
This project is licensed under the [MIT](https://choosealicense.com/licenses/mit/) License - see the LICENSE file for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/KoushikNavuluri/stable-diffusion-xl-api/",
"name": "sdxl",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "stable diffusion,ai,midjourney,API,requests,images,llm,sdxl,replicate",
"author": "Koushik",
"author_email": "koushikk@outlook.com",
"download_url": "https://files.pythonhosted.org/packages/a0/72/e8e46f1c2de0df7958f5ab37c519e7370b30b5751cc8b70a942bed0653b7/sdxl-1.0.0.tar.gz",
"platform": null,
"description": "# Stable Diffusion XL ( API )\r\n\r\n Reverse engineered API of Stable Diffusion XL 1.0 ( Midjourney Alternative ) via https://replicate.com/ , A text-to-image generative AI model that creates beautiful 1024x1024 images.\r\n\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/d1022d40-05f0-4d2d-a37e-8cab7d444bec\" width=\"900\" > \r\n\r\n# Table of Contents\r\n\r\n- [Stable Diffusion XL ( API )](#stable-diffusion-xl---api--)\r\n * [Prerequisites](#prerequisites)\r\n * [Installation](#installation)\r\n * [Usage](#usage)\r\n * [Send Prompt to generate image](#send-prompt-to-generate-image)\r\n + [Output](#output)\r\n * [Example Images Generated](#example-images-generated)\r\n * [Advanced Generation using parameters](#advanced-generation-using-parameters)\r\n + [List of parameters](#list-of-parameters)\r\n * [CLI Version](#cli-version)\r\n * [Disclaimer](#disclaimer)\r\n * [License](#license)\r\n\r\n## Prerequisites\r\n\r\nTo use this API, you need to have the following:\r\n\r\nPython installed on your system\r\nrequests library installed \r\n```bash\r\n pip install requests\r\n\r\n```\r\n\r\n## Installation\r\n\r\nTo use the Claude AI Unofficial API, you can either clone the GitHub repository or directly download the Python file.\r\n\r\nTerminal :\r\n\r\n pip install sdxl\r\n \r\nor\r\n\r\nClone the repository:\r\n\r\n git clone https://github.com/KoushikNavuluri/stable-diffusion-xl-api.git\r\n\r\n## Usage\r\nImport the claude_api module in your Python script:\r\n\r\n from sdxl import ImageGenerator\r\n\r\n* Next, you need to create an instance of the ImageGenerator class:\r\n \r\n```bash\r\nclient = ImageGenerator()\r\n```\r\n## Send Prompt to generate image\r\n```bash\r\nimages = sdxl.gen_image(\r\n \"Vibrant, Headshot of a serene, meditating individual surrounded by soft, ambient lighting.\")\r\nprint(images)\r\n```\r\n\r\n### Output\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/5f362c03-d8f1-462c-873a-40e47bdaea63\" width=\"600\" >\r\n\r\n## Example Images Generated\r\n\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/eb1976ac-0cf7-4817-9116-bd7384282380\" width=\"200\" >\r\n\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/9bcfa7de-338e-48ca-a008-a068236d052c\" width=\"200\">\r\n\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/a7ad3bc8-431a-40d3-a43f-aec9426b8f18\" width=\"200\" >\r\n\r\n<img src=\"https://github.com/KoushikNavuluri/stable-diffusion-xl-api/assets/103725723/1fd90d12-aaba-4fce-bf94-2077355a5d41\" width=\"200\">\r\n\r\n\r\n\r\n## Advanced Generation using parameters\r\n\r\n```bash\r\n#Parameters set to their default values\r\nimages = sdxl.gen_image(prompt=\r\n \"Vibrant, Headshot of a serene, meditating individual surrounded by soft, ambient lighting.\",count=1, width=1024, height=1024, refine=\"expert_ensemble_refiner\", scheduler=\"DDIM\", guidance_scale=7.5, high_noise_frac=0.8, prompt_strength=0.8, num_inference_steps=50)\r\nprint(images)\r\n```\r\n### List of parameters\r\n\r\n * prompt = Input text prompt\r\n * width = Width of output image(max:1024)\r\n * height = height of output image(max:1024)\r\n * count = Number of images to output. (minimum: 1; maximum: 4) \r\n * refine = Which refine style to use ( no_refiner or expert_ensemble_refiner or base_image_refiner )\r\n * scheduler = scheduler (valid_schedulers = [\"DDIM\" or \"DPMSolverMultistep\" or \"HeunDiscrete\" or \"KarrasDPM\" or \"K_EULER_ANCESTRAL\" or \"K_EULER\" or \"PNDM\"])\r\n * guidance_scale = Scale for classifier-free guidance (minimum: 1; maximum: 50) \r\n * prompt_strength = Prompt strength in image (maximum: 1) \r\n * num_inference_steps = Number of denoising steps (minimum: 1; maximum: 500) \r\n * high_noise_frac = for expert_ensemble_refiner, the fraction of noise to use (maximum: 1)\r\n \r\n## CLI Version\r\n\r\nFor cli version you can check example folder in this repository (filename:cli.py)\r\n\r\n> How to:\r\n\r\n```bash\r\npython main.py \"beautiful landscape with two kittens,realistic,4k\" --count 1 --width 1024 --height 1024 --refine expert_ensemble_refiner --scheduler DDIM --guidance_scale 7.5 --high_noise_frac 0.6 --prompt_strength 0.9 --num_inference_steps 40\r\n\r\n```\r\n\r\n## Disclaimer\r\n\r\nThis project provides an unofficial API for Replicate's Stable Diffusion XL and is not affiliated with or endorsed by Replicate or Stable Diffusion. Use it at your own risk.\r\n\r\n## License\r\nThis project is licensed under the [MIT](https://choosealicense.com/licenses/mit/) License - see the LICENSE file for details.\r\n\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Reverse engineered API of Stable Diffusion XL 1.0 ( Midjourney Alternative ), A text-to-image generative AI model that creates beautiful 1024x1024 images.",
"version": "1.0.0",
"project_urls": {
"Homepage": "https://github.com/KoushikNavuluri/stable-diffusion-xl-api/"
},
"split_keywords": [
"stable diffusion",
"ai",
"midjourney",
"api",
"requests",
"images",
"llm",
"sdxl",
"replicate"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "809750be0d2ea23991dea595f4c33031a1f14fe94975a434b1b69177ac3e2654",
"md5": "905009bb72a7b44aa4b6ecd769e29eb6",
"sha256": "0e6086719567126c1ac3bba6e3f07d7bedfc1d602c758b0b5960c6a786d53e4b"
},
"downloads": -1,
"filename": "sdxl-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "905009bb72a7b44aa4b6ecd769e29eb6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 5282,
"upload_time": "2023-08-04T05:45:22",
"upload_time_iso_8601": "2023-08-04T05:45:22.757867Z",
"url": "https://files.pythonhosted.org/packages/80/97/50be0d2ea23991dea595f4c33031a1f14fe94975a434b1b69177ac3e2654/sdxl-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a072e8e46f1c2de0df7958f5ab37c519e7370b30b5751cc8b70a942bed0653b7",
"md5": "650e466cd9de04dcfcdf151904951f5d",
"sha256": "389be1a73ce368f8e3c402900b543223130cf485338e8e1977ab99d760cd5e79"
},
"downloads": -1,
"filename": "sdxl-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "650e466cd9de04dcfcdf151904951f5d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 5137,
"upload_time": "2023-08-04T05:45:24",
"upload_time_iso_8601": "2023-08-04T05:45:24.587136Z",
"url": "https://files.pythonhosted.org/packages/a0/72/e8e46f1c2de0df7958f5ab37c519e7370b30b5751cc8b70a942bed0653b7/sdxl-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-04 05:45:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "KoushikNavuluri",
"github_project": "stable-diffusion-xl-api",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "sdxl"
}
JSON
