https://github.com/cloud-py-api/ai_image_generator_bot

Nextcloud AI image generator Talk bot
https://github.com/cloud-py-api/ai_image_generator_bot

nextcloud stable-diffusion talk

Last synced: 3 months ago
JSON representation

Nextcloud AI image generator Talk bot

• Host: GitHub
• URL: https://github.com/cloud-py-api/ai_image_generator_bot
• Owner: cloud-py-api
• License: mit
• Created: 2023-12-17T12:29:32.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-25T09:21:05.000Z (9 months ago)
• Last Synced: 2024-09-27T06:20:11.954Z (4 months ago)
• Topics: nextcloud, stable-diffusion, talk
• Language: Python
• Homepage: https://apps.nextcloud.com/apps/ai_image_generator_bot
• Size: 13.3 MB
• Stars: 5
• Watchers: 2
• Forks: 0
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Nextcloud AI Image generator bot

Uses [SDXL-Turbo](https://huggingface.co/stabilityai/sdxl-turbo) for fast image generation.

*Using the RTX 3060 12GB, bot is capable of processing 2 requests per second.*

> [!WARNING]

> Note: Model loaded in GPU memory uses ~9.4GB.

> Can be run on CPU but will require ~2x of memory.

>

> Models remain in memory after a request, for faster processing of subsequent requests.

>

> Memory is freed after an hour of inactivity.

![Enable talk bot](/screenshots/ai_image_generator_bot_1.png)

![Send prompts](/screenshots/ai_image_generator_bot_2.png)

## How to use

1. Install ExApp from AppStore

2. Wait for models download and initialization(`6.5` Gb for GPU, `13` Gb for CPU)

3. Enable talk bot in your room

4. Use @image mention to send prompts: `@image cinematic portrait of fluffy cat with black eyes`

5. Image will be posted to room and stored into `image_generator_bot` folder at the user's root.

> [!IMPORTANT]

> Only English language is supported

## State of support

The project is being developed in personal and free time, any ideas or pull requests are welcome.

*Note: We understand that the model used here is quite old and cannot compare with the new SDXL-Lightning*

*We are currently working on a new much more advanced image generation project which you can find here: [Visionatrix](https://github.com/Visionatrix/Visionatrix)*

*If this is of interest to the Nextcloud community, we can try to adapt Visionatrix either as an Image Provider for Nextcloud 30 or simply as an AppAPI Nextcloud application.*