Update README.md

README.md

@@ -1,124 +1,170 @@
- <p align="center">
-    <img
-  src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/YJHpzH436J828nNymCNk7.png"
-  width="600" />
+<p align="center">
+      <img
+    src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/YJHpzH436J828nNymCNk7.png"
+    width="600" />
   </p>
 
-# Visione
-
-A local-first AI creative production suite for consumer GPUs.
-Read the full documentation [here](https://www.notion.so/Visione-Technical-Documentation-3194a74185bb8015b154e234606497e2)
+  <p align="center">
+    <strong>Full creative production suite that runs entirely on your GPU.</strong><br/>
+    No cloud. No API keys. No subscriptions. Every model runs on-device.
+  </p>
 
----
+  <p align="center">
+    <a
+  href="https://www.notion.so/Visione-Technical-Documentation-3194a74185bb8015b154e234606497e2">Documentation</a>
+  </p>
 
-## What is Visione?
+  ---
 
-Visione is a self-contained desktop application for AI-driven creative production. It runs entirely on local hardware: no cloud services, no external APIs, no subscriptions. Every model runs on-device; inference never leaves your machine.
+  ## Why Visione
 
-The pipeline covers the full creative arc: text-to-image and video generation, retouching, stylization, enhancement, and sound design, all within a single application.
+  Most AI creative tools are fragmented: one app for image gen, another for video, another for audio, each with its
+  own cloud dependency and pricing tier. Visione puts the entire pipeline — from concept to final export — inside a
+  single desktop application that runs on a consumer NVIDIA GPU (16GB VRAM).
 
-**Stack:** Python 3.12 + FastAPI + SSE · React 18 + TypeScript + Zustand · Tauri 2 desktop shell · ComfyUI headless for video inference · PyTorch 2.7 + CUDA
+  You own your hardware, your models, and your outputs. Nothing is transmitted externally. Ever.
 
   <table align="center"><tr>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/X0pIezsKwIRl-Guw3k58A.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/X0pIezsKwIRl-Guw3k58
+  A.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/X0pIezsKwIRl-Guw3k58A.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/euOPxXTNWxjmRl-C88uU2.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/euOPxXTNWxjmRl-C88uU
+  2.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/euOPxXTNWxjmRl-C88uU2.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/lW_zGi1O8HblIoamV0RLr.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/lW_zGi1O8HblIoamV0RL
+  r.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/lW_zGi1O8HblIoamV0RLr.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/qKWonqa8ZQvl3CTdD0Pje.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/qKWonqa8ZQvl3CTdD0Pj
+  e.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/qKWonqa8ZQvl3CTdD0Pje.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/IjNbVVpnLepr9NI8cdxA3.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/IjNbVVpnLepr9NI8cdxA
+  3.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/IjNbVVpnLepr9NI8cdxA3.png"
   width="300" /></a></td>
   </tr></table>
 
----
+  ---
 
-## Components
+  ## What You Can Do
 
-| Tab | What it does |
-|-----|-------------|
-| **Imagine** | Image and video generation from text or reference image |
-| **Retouch** | Image editing — upscaling, denoising, face restore, multi-reference compositing, LUT, adjustments, background removal |
-| **Retexture** | Video style transfer — LoRA-based preset styles and reference-image stylization via depth conditioning |
-| **Enhance** | Image and video enhancement — upscaling, denoising, frame interpolation |
-| **Storyboard** | 12-stage AI-assisted filmmaking pipeline: multi-agent concept development, character library, shot generation, and export |
-| **Sound Studio** | Music generation, voiceover (preset, cloned, and voice-designed), and video-to-audio foley |
-| **Characters** | Persistent character library with 5-shot reference generation for cross-shot consistency |
-| **Gallery** | Unified asset browser across all components |
+  | Component | Description |
+  |---|---|
+  | **Imagine** | Text-to-image generation with 90+ style LoRAs across 3 model tiers (Z-Image Turbo, Klein 4B, Klein 9B). Character `@mentions` for consistent subjects. |
+  | **Animate** | Image-to-video and text-to-video via LTX 2.3. 5 workflow modes: standard I2V/T2V, Best 3-stage, first-last-frame, audio-conditioned. |
+  | **Retouch** | Full image editor — inpainting, upscaling, reframing, face swap (InsightFace + FaceFusion), background removal, LUT color grading, optical realism effects, multi-reference compositing, and smart selection (SAM). |
+  | **Retexture** | Apply any of 90+ preset styles to existing images via LoRA, or transfer the style of a reference image using depth-conditioned generation. |
+  | **Enhance** | SeedVR2 video enhancement (3B/7B models), Real-ESRGAN upscaling, and RIFE frame interpolation. |
+  | **Storyboard** | 12-stage AI filmmaking pipeline: concept development with multi-agent LLM collaboration, character library, shot-by-shot generation, and ZIP export. |
+  | **Sound Studio** | ACE-Step music generation, Qwen3-TTS voiceover (28 preset voices + clone + design), and HunyuanVideo-Foley for video-to-audio. |
+  | **Characters** | Persistent character library with full-body 5-shot reference generation for visual consistency across shots and components. |
+  | **Styles** | Browse and install LoRAs from CivitAI directly inside the app. Manage custom styles with per-preset strength tuning. |
+  | **Gallery** | Unified asset browser across all components with metadata, output modal, and send-to integration for cross-component workflows. |
 
-<table align="center"><tr>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/No1ABmspTrCWqpvsukafQ.
-  png"><img
+  <table align="center"><tr>
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/No1ABmspTrCWqpvsukaf
+  Q.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/No1ABmspTrCWqpvsukafQ.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/mXVAiuj8Vpik0a_UNREIU.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/mXVAiuj8Vpik0a_UNREI
+  U.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/mXVAiuj8Vpik0a_UNREIU.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/Gmzmavqm9antFHYsbl4Ka.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/Gmzmavqm9antFHYsbl4K
+  a.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/Gmzmavqm9antFHYsbl4Ka.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/BbYSmMGcXZENjW-LBiIUz.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/BbYSmMGcXZENjW-LBiIU
+  z.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/BbYSmMGcXZENjW-LBiIUz.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/jcy5-_cKf0oa_Utf3ZXbK.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/jcy5-_cKf0oa_Utf3ZXb
+  K.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/jcy5-_cKf0oa_Utf3ZXbK.png"
   width="300" /></a></td>
   </tr></table>
 
----
+  ---
+
+  ## Key Features
+
+  - **90+ style presets** — LoRA-based styles spanning cinematic, illustration, animation, photography, design, and
+  artist-specific looks. Browse and install more from CivitAI directly inside the app.
+  - **Character consistency** — Generate a persistent character once, then reference them by name across Imagine,
+  Retouch, and Storyboard with `@mentions`.
+  - **Smart VRAM management** — Models load and unload sequentially to fit within 16GB. One active model at a time,
+  no manual memory management needed.
+  - **Multilingual UI** — English, Italian, Spanish, French, German.
+  - **Local LLM + VLM** — Qwen3.5-4B handles prompt enhancement, image captioning, and storyboard agents. Falls back
+   to Llama 3.2 3B on CPU if needed. No external API calls.
+  - **Optical realism** — Client-side film emulation: grain, halation, vignette, pro-mist, chromatic aberration,
+  highlight roll-off, color temperature and tint.
 
-## Architecture
+  ---
 
-Visione runs as a local client-server application. The React frontend communicates with a FastAPI backend over localhost; real-time progress streams back via SSE. Heavy inference runs in-process (diffusers, PyTorch) or via a ComfyUI headless subprocess for video pipelines. Models load and unload sequentially to fit within a 16GB VRAM budget, one active model at a time.
+  ## Architecture
 
-The desktop shell (Tauri 2) wraps the frontend as a native window and manages backend process lifecycle. All assets, models, and outputs live on local storage; nothing is transmitted externally.
+  Visione is a local client-server desktop app. The React frontend talks to a FastAPI backend over localhost;
+  real-time progress streams via SSE. Heavy inference runs in-process (diffusers/PyTorch) or through a headless
+  ComfyUI subprocess for video pipelines. The Tauri 2 shell wraps it as a native window and manages the backend
+  lifecycle.
 
-Components share models where possible. Image generation models are reused across Imagine, Retouch, Retexture, and Storyboard; video models feed through from Imagine into Retexture and Sound Studio. The Video Editor and Gallery operate CPU-side, assembling outputs produced by the GPU components.
+  Models are shared across components wherever possible — the same image generation backbone serves Imagine,
+  Retouch, Retexture, and Storyboard. All assets, models, and outputs stay on local storage.
+
+  **Stack:** Python 3.12 + FastAPI + SSE / React 18 + TypeScript + Zustand / Tauri 2 / ComfyUI headless / PyTorch
+  2.7 + CUDA
 
   <table align="center"><tr>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/7_CDVBV6B08IosFIkr5jq.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/7_CDVBV6B08IosFIkr5j
+  q.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/7_CDVBV6B08IosFIkr5jq.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/fRhZcUYtK_TE8uIlXyPH-.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/fRhZcUYtK_TE8uIlXyPH
+  -.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/fRhZcUYtK_TE8uIlXyPH-.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/B1J7kJuRPiPY12-Wja0jW.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/B1J7kJuRPiPY12-Wja0j
+  W.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/B1J7kJuRPiPY12-Wja0jW.png"
   width="300" /></a></td>
-  <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/MXtHgy7hlq9YZVaQED_WA.
-  png"><img
+    <td><a href="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/MXtHgy7hlq9YZVaQED_W
+  A.png"><img
   src="https://cdn-uploads.huggingface.co/production/uploads/695017bb0c3fc8b9c78497e9/MXtHgy7hlq9YZVaQED_WA.png"
   width="300" /></a></td>
   </tr></table>
 
----
-
-## License
-
-MIT
-
-
----
-license: mit
-tags:
-- art
-- agent
----
+  ---
+
+  ## Hardware Requirements
+
+  | | Minimum | Recommended |
+  |---|---|---|
+  | **GPU** | NVIDIA 12GB VRAM (RTX 3060) | NVIDIA 16GB VRAM (RTX 4080) |
+  | **RAM** | 16GB | 32GB |
+  | **Storage** | ~50GB (core models) | ~210GB (all models) |
+  | **OS** | Windows 10/11 | Windows 11 |
+
+  ---
+
+  ## License
+
+  MIT
+
+  ---
+  license: mit
+  tags:
+  - art
+  - agent
+  - image-generation
+  - video-generation
+  - text-to-image
+  - text-to-video
+  - style-transfer
+  - image-editing
+  - tts
+  - local-inference
+  ---