Skip to content
/ NeuroSandboxWebUI Public

(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 languages

dartvauder.github.io/neurosandboxwebui/

License

MIT license
73 stars 11 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

Dartvauder/NeuroSandboxWebUI

BranchesTags

Repository files navigation

Features | Dependencies | SystemRequirements | Install | Wiki | Acknowledgment | Licenses

main

Description:

A simple and convenient interface for using various neural network models. You can communicate with LLM using text, voice and image input; use StableDiffusion, Kandinsky, Flux, HunyuanDiT, Lumina-T2X, Kolors, AuraFlow, Würstchen, DeepFloydIF, PixArt, CogView3-Plus and PlaygroundV2.5, to generate images; ModelScope, ZeroScope 2, CogVideoX and Latte to generate videos; StableFast3D, Shap-E, and Zero123Plus to generate 3D objects; StableAudioOpen, AudioCraft and AudioLDM 2 to generate music and audio; CoquiTTS, MMS and SunoBark for text-to-speech; OpenAI-Whisper and MMS for speech-to-text; Wav2Lip for lip-sync; LivePortrait for animate an image; Roop to faceswap; Rembg to remove background; CodeFormer for face restore; PixelOE for image pixelization; DDColor for image colorization; LibreTranslate and SeamlessM4Tv2 for text translation; Demucs and UVR for audio file separation; RVC for voice conversion. You can also view files from the outputs directory in gallery, download the LLM and StableDiffusion models, change the application settings inside the interface and check system sensors

The goal of the project - to create the easiest possible application to use neural network models

Text: 1

Image: 2

Video: 3

3D: 4

Audio: 5

Extras: 6

Interface: 7

Features:

  • Easy installation via install.bat (Windows) or install.sh (Linux & MacOS)
  • You can use the application via your mobile device in localhost (Via IPv4) or anywhere online (Via Share)
  • Flexible and optimized interface (By Gradio)
  • Debug logging to logs from Install and Update files
  • Available in three languages
  • Support for Transformers, BNB, GPTQ, AWQ, ExLlamaV2 and llama.cpp models (LLM)
  • Support for diffusers and safetensors models (StableDiffusion) - txt2img, img2img, depth2img, marigold, pix2pix, controlnet, upscale (latent), refiner, inpaint, outpaint, gligen, diffedit, blip-diffusion, animatediff, hotshot-xl, video, ldm3d, sd3, cascade, t2i-ip-adapter, ip-adapter-faceid and riffusion tabs
  • Support for stable-diffusion-cpp models for FLUX and Stable Diffusion
  • Support of additional models for image generation: Kandinsky (txt2img, img2img, inpaint), Flux (txt2img with cpp quantize and LoRA support, img2img, inpaint, controlnet), HunyuanDiT (txt2img, controlnet), Lumina-T2X, Kolors (txt2img with LoRA support, img2img, ip-adapter-plus), AuraFlow (with LoRA and AuraSR support), Würstchen, DeepFloydIF (txt2img, img2img, inpaint), PixArt, CogView3-Plus and PlaygroundV2.5
  • Support Extras with Rembg, CodeFormer, PixelOE, DDColor, DownScale, Format changer, FaceSwap (Roop) and Upscale (Real-ESRGAN) models for image, video and audio
  • Support StableAudio
  • Support AudioCraft (Models: musicgen, audiogen and magnet)
  • Support AudioLDM 2 (Models: audio and music)
  • Supports TTS and Whisper models (For LLM and TTS-STT)
  • Support MMS for text-to-speech and speech-to-text
  • Supports Lora, Textual inversion (embedding), Vae, MagicPrompt, Img2img, Depth, Marigold, Pix2Pix, Controlnet, Upscale (latent), Refiner, Inpaint, Outpaint, GLIGEN, DiffEdit, BLIP-Diffusion, AnimateDiff, HotShot-XL, Videos, LDM3D, SD3, Cascade, T2I-IP-ADAPTER, IP-Adapter-FaceID and Riffusion models (For StableDiffusion)
  • Support Multiband Diffusion model (For AudioCraft)
  • Support LibreTranslate (Local API) and SeamlessM4Tv2 for language translations
  • Support ModelScope, ZeroScope 2, CogVideoX and Latte for video generation
  • Support SunoBark
  • Support Demucs and UVR for audio file separation
  • Support RVC for voice conversion
  • Support StableFast3D, Shap-E and Zero123Plus for 3D generation
  • Support Wav2Lip
  • Support LivePortrait for animate an image
  • Support Multimodal (Moondream 2, LLaVA-NeXT-Video, Qwen2-Audio), PDF-Parsing (OpenParse), TTS (CoquiTTS), STT (Whisper), LORA and WebSearch (with DuckDuckGo) for LLM
  • MetaData-Info viewer for generating image, video and audio
  • Model settings inside the interface
  • Online and offline Wiki
  • Gallery
  • ModelDownloader
  • Application settings
  • Ability to see system sensors

Required Dependencies:

Minimum System Requirements:

  • System: Windows, Linux or MacOS
  • GPU: 6GB+ or CPU: 8 core 3.6GHZ
  • RAM: 16GB+
  • Disk space: 20GB+
  • Internet for downloading models and installing

How to install:

Windows

  1. First install all RequiredDependencies
  2. Git clone https://github.com/Dartvauder/NeuroSandboxWebUI.git to any location
  3. Run the Install.bat, select your version and wait for installation
  4. After installation, run Start.bat and go through the initial setup
  5. Wait for the application to launch and follow the link from the terminal
  6. Now you can start generating. Enjoy!
  • To get update, run Update.bat
  • To work with the virtual environment through the terminal, run Venv.bat

Linux & MacOS

  1. First install all RequiredDependencies
  2. Git clone https://github.com/Dartvauder/NeuroSandboxWebUI.git to any location
  3. Run the ./Install.sh, select your version and wait for installation
  4. After installation, run ./Start.sh and go through the initial setup
  5. Wait for the application to launch and follow the link from the terminal
  6. Now you can start generating. Enjoy!
  • To get update, run ./Update.sh
  • To work with the virtual environment through the terminal, run ./Venv.sh

Wiki

Acknowledgment to developers

Many thanks to these projects because thanks to their applications/libraries, i was able to create my application:

First of all, I want to thank the developers of PyCharm and GitHub. With the help of their applications, i was able to create and share my code

Third Party Licenses:

Many models have their own license for use. Before using it, I advise you to familiarize yourself with them:

These third-party repository codes are also used in my project:

Donation

If you liked my project and want to donate, here is options to donate. Thank you very much in advance!

  • "Buy Me A Coffee"

Star History

Star History Chart

About

(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 languages

dartvauder.github.io/NeuroSandboxWebUI/

Topics

python flux neural-network transformers tts webui rvc gradio whisper demucs wav2lip llm stable-diffusion diffusers audioldm llamacpp seamlessm4t stableaudio cogvideox stablefast3d

Resources

Readme

License

MIT license

Code of conduct

Code of conduct

Security policy

Security policy
Activity

Stars

73 stars

Watchers

8 watching

Forks

11 forks
Report repository

Releases 28

Release 1.0.7 (MacOS) Latest
Nov 7, 2024
+ 27 releases

Contributors 2

Languages