AEIONic Diffusion Deluxe

All-in-one Enhanced Intelligent Omnimedia Neural-nets for Interactive Creativity

We’ve created a Full-Featured Flet/Flutter Application to make the most of all the latest Open-Source AI Art Generators in an intuitive, playful interface.

Make endless Images, Videos, Sound FX, Songs, Voices, Transcriptions, Styles, Custom Trained Models, GPT Prompts, and so much more! Designed to get experimental, and queue up mass batch Prompts List.  Get extra creative and crank out unique masterpieces with less effort or skills required…

AEIONic (pronounced AY-i-ON-ik) is a free Multi-Media AI Toolkit that offers a comprehensive suite of features for generating and manipulating images, videos, audio, and text using state-of-the-art AI models and techniques. With a user-friendly Material UI Flutter/Flet Gui, users can easily navigate and access the vast array of tools and models available in the application.

Key Features:

  • Enhanced Diffusers: Utilizes HuggingFace Diffusers in Material UI Flutter/Flet GUI with customizable Themes and SoundFX for an engaging user experience.
  • Stable Diffusion: Supports Stable Diffusion 3, XL, 2.1 or 1.5 for high-quality image generation.
  • Advanced Prompts List: Offers an advanced prompts list with overrides for precise control over AI-generated content.
  • Finetuned Community Models: Includes many finetuned community models for a diverse range of applications.
  • Dreambooth Library: Provides access to the Dreambooth Library for a wide selection of pre-built models and assets.
  • Prompt Tweening, Centipede Prompts & Seamless Tiling: Incorporates Prompt Tweening and Centipede Prompts as init-images for creative control over AI-generated content.
  • CLIP-Guided & Textual-Inversion Conceptualizer: Employs CLIP-Guided and Textual-Inversion Conceptualizer for versatile image generation and manipulation.
  • Dual Guided Versatile Diffusion: Offers Dual Guided Versatile Diffusion for improved image generation and variation.
  • Image Variation & iMagic: Includes Image Variation and iMagic for creating unique and diverse visuals.
  • Depth2Image & Composable: Supports Depth2Image and Composable features for advanced image manipulation and composition.
  • Self-Attention Guidance & Attend & Excite: Utilizes Self-Attention Guidance and Attend & Excite for improved AI-generated content.
  • Panorama & Safe Pipeline: Offers Panorama and Safe Pipeline features for seamless image stitching and secure processing.
  • DeepFloyd-IF & unCLIP Generator: Incorporates DeepFloyd-IF and unCLIP Generator for enhanced image generation and manipulation.
  • unCLIP Image Variations & Interpolation: Provides unCLIP Image Variations and Interpolation for smooth image transitions and variations.
  • Text-to-Video & Text2Video-Zero: Features Text-to-Video and Text2Video-Zero for converting text into engaging video content.
  • Potat1 Text-to-Video & Video-to-Video: Includes Potat1 Text-to-Video and Video-to-Video capabilities for versatile video generation and manipulation.
  • ROOP Face Swapper & Stable Animation: Offers ROOP Face Swapper and Stable Animation for realistic face swapping and smooth animations.
  • Stability-API & AIHorde-API: Integrates Stability-API and AIHorde-API for image generation on older GPUs.
  • Integrated Upscaling: Supports SD2 4X Upscale, Real-ESRGAN Upscaling on the fly or in batch.
  • Prompt Helpers: GPT-3 & ChatGPT Prompt Generator, Prompt Remixer, and more for improved creative prompts and content generation.
  • Training & Conversion: Features LoRA & Texual Inversion Trainer, Model Converter & Merger, and more for custom model training and compatibility.
  • Editing & Mixing: Includes EDICT Editor, DiffEdit, MagicMix, RePainter, Paint-by-Example, and more for advanced image editing and manipulation.
  • ControlNet & QRCode: Offers ControlNet Multi, ControlNet QRCode, Reference-Only, and Re-Segment Anything for precise control over AI-generated content.
  • Styling & Guidance: Features CLIP-Styler, Semantic Guidance, Material Diffusion, and more for creative control over image generation and manipulation.
  • 3D Generation: Includes DreamFusion 3D, Point-E 3D, Shap-E 3D, and InstantNGR for generating 3D models and visuals.
  •  Text-to-Speech & Speech-to-Text: Incorporates Tortoise TTS, Whisper STT, VoiceFixer, and more for converting text to speech and vice versa.
  • Audio & Music Generation: Offers Audio Diffusion, Bark, Riffusion, AudioLDM Text2Sound, MusicGen, Mubert Music, and more for creating and manipulating audio content.
  • Image2Text & DALL-E 2 API: Supports Image2Text Interrogator, DALL-E 2 API, Kandinsky 2.1 & Fuser, DeepDaze, and more for advanced image-to-text conversion and manipulation.
  • Background Removal & Metadata: Includes Background Remover, Metadata in png, smart filenames, and more for precise image editing and organization.
  • Batch Processing & Cache Management Extras: Features Batch Upscaler, Prompt Retriever, Cache Manager, Init Images from Folder or Video, and more for efficient processing and resource management.

Short Feature List (by tab):

  • Prompt Helpers: Prompt Writer, Prompt Generator, Prompt Remixer, Prompt Brainstormer, Prompt Styler, Negatives, Image2Text, Magic Prompt, SuperPrompt, Distil GPT-2, Retrieve Prompt from Image, Init Images from Folder, Init Images from Video and BLIP2 Image2Text
  • Image AIs: Instruct Pix2Pix, ControlNet SD, ControlNet SDXL, ControlNet SD3, ControlNet-XS, ControlNet FLUX.1, FLUX.1, Kandinsky, Kandinsky Fuse, Kandinsky ControlNet, QRCode, DALL•E, Ideogram, Lumina-Next, Hunyuan-DiT, Stable Cascade, Würstchen, aMUSEd, PixArt-Σ, PixArt-α, Kolors, AuraFlow, Layer Diffusion, Differential Diffusion, DemoFusion, DeepFloyd-IF, LMD+, LCM, LCM Interpolation, InstaFlow, PAG, unCLIP, unCLIP Interpolation, unCLIP Image Interpolation, unCLIP Image Variation, Image Variation, BLIP-Diffusion, HD-Painter, IP-Adapter, Reference-Only, Material Diffusion, Re-Segment-Anything, LEdits++, Null-Text, EDICT Edit, DiffEdit, AnyText, TaskMatrix, RePainter, MagicMix, Paint-by-Example, CLIP-Styler, Semantic Guidance, DiT and DeepDaze
  • Video AIs: AnimateDiff, Deforum FLUX, Stable Animation, SVD Image-to-Video, AnimateDiff to-Video, AnimateDiff SDXL, DiffSynth, EasyAnimate, Infinite Zoom, Open-Sora, Cinemo, CogVideoX, I2VGen-XL, PIA Image Animator, Text-to-Video, Text-to-Video Zero, Latte, Kandinsky Video, Potat1, ROOP Face-Swap, Hallo, Video-ReTalking, LivePortrait, Video-Infinity, FRESCO, StyleCrafter, RAVE, Rerender-a-Video, TokenFlow, Hotshot-XL, ControlNet Video2Video, Video-to-Video, TemporalNet-XL and ControlNet Init-Video
  • 3D AIs: DreamFusion 3D, Stable Fast 3D, Point-E 3D, Shap-E 3D, ZoeDepth 3D, MarigoldDepth, Tripo, InstantMesh, Splatter Image, CRM-3D, LDM3D, Instant-NGP, Meshy.ai and Luma Video-to-3D
  • Audio AIs: Tortoise-TTS, MusicLDM, Stable Audio, AudioLDM, AudioLDM-2, ZETA Editing, Bark, Riffusion, Audio Diffusion, MusicLang, MusicGen, Whisper-STT, OpenAI-TTS, Voice Fixer, HarmonAI Dance Diffusion and Mubert Music
  • AI Trainers: LoRA DreamBooth, LoRA, DreamBooth, Texual-Inversion, Model Converter and Checkpoint Merger
  • Extras: Real-ESRGAN Batch Upscaler, Model Manager, Cache Manager, Background Remover, Vectorizer and Horde Worker reGen

With regular updates and new features being added, Diffusion Deluxe is the ultimate multimedia AI application for creators, artists, and developers seeking a comprehensive, user-friendly solution for their AI-driven projects.