Polish README for public release: add tags, model link, features section, performance stats

README.md

@@ -7,45 +7,65 @@ sdk: gradio
 sdk_version: 5.23.0
 python_version: '3.12'
 app_file: app.py
-pinned: false
+pinned: true
 license: other
 license_name: ltx-2-community-license-agreement
 license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
-short_description: LTX-2.3 video+audio generation on free ZeroGPU
+short_description: Generate video + audio with LTX-2.3 (22B) on free ZeroGPU
+tags:
+  - video-generation
+  - audio-generation
+  - text-to-video
+  - image-to-video
+  - ltx
+  - lightricks
+  - zerogpu
+  - fp8
+  - distilled
+models:
+  - Lightricks/LTX-2.3
 ---
 
 # LTX-2.3 Turbo (ZeroGPU)
 
 Generate synchronized **video + audio** from text or images using
-[Lightricks/LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) — a 22B
-parameter DiT-based audio-video foundation model — running on **free ZeroGPU**
-hardware.
+[Lightricks/LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) — a **22B
+parameter** DiT-based audio-video foundation model — running entirely on
+**free ZeroGPU** hardware. No paid GPU required.
+
+**~10 seconds** to generate a 2-second video with audio at 768x512.
+
+## Features
+
+- **Text to Video** — describe a scene and get video with synchronized audio
+- **Image to Video** — provide a first frame and animate it with audio
+- **Prompt enhancement** — Gemma-3 12B rewrites your prompt for better results
+- **Multiple resolutions** — 16:9, 1:1, and 9:16 aspect ratios
+- **Reproducible** — set a seed for consistent outputs
 
 ## How it works
 
-This Space uses a **vendored packages + pre-loaded models** strategy
-(inspired by [alexnasa/ltx-2-TURBO](https://huggingface.co/spaces/alexnasa/ltx-2-TURBO))
-to run the massive 22B model on ZeroGPU:
+This Space uses a **vendored packages + pre-loaded models** strategy to fit
+the massive 22B model on ZeroGPU's A10G (40GB VRAM):
 
 1. **Startup**: Downloads model files, constructs `ModelLedger`, loads the
    Gemma-3 12B text encoder, and pre-loads the FP8-quantized transformer +
    video encoder into the pipeline cache.
-2. **Text Encoding** (`@spaces.GPU`): Uses the pre-loaded text encoder to
-   encode the prompt into video/audio context tensors, returned to CPU.
+2. **Text Encoding** (`@spaces.GPU`): Encodes the prompt into video/audio
+   context tensors using the pre-loaded text encoder, returned to CPU.
 3. **Video Generation** (`@spaces.GPU`): Runs the two-stage distilled
    denoising pipeline (8 steps low-res + 4 steps high-res with 2x spatial
    upscaling) using pre-encoded contexts, then decodes video and audio.
 
-### Key optimizations for ZeroGPU
+### Key optimizations
 
-- **Vendored packages**: `ltx-core` and `ltx-pipelines` are vendored directly
-  in the repo for faster builds and customized ZeroGPU compatibility.
-- **FP8 quantization**: Transformer weights are cast to `float8_e4m3fn`,
-  halving VRAM usage with minimal quality impact.
-- **Pre-loaded models**: Text encoder, transformer, and video encoder are
-  loaded once at startup and kept in memory across requests.
-- **Distilled pipeline**: Only 8+4 denoising steps (vs 30+ for the full model),
-  dramatically reducing inference time.
+| Optimization | Details |
+|---|---|
+| **FP8 quantization** | Transformer weights cast to `float8_e4m3fn`, halving VRAM usage |
+| **Distilled pipeline** | Only 8+4 denoising steps (vs 30+ for full model) |
+| **Pre-loaded models** | Text encoder, transformer, video encoder loaded once at startup |
+| **Two-stage upscaling** | Generates at half resolution, then upscales 2x with spatial upsampler |
+| **Vendored packages** | `ltx-core` and `ltx-pipelines` bundled for fast builds |
 
 ## Parameters
 
@@ -54,9 +74,9 @@ to run the massive 22B model on ZeroGPU:
 | Mode | Text to Video / Image to Video | Text to Video | |
 | Prompt | Free text | — | Describe scene, motion, and audio |
 | Resolution | 768x512, 512x512, 512x768 | 768x512 | Upscaled 2x by spatial upscaler |
-| Duration | 1–5 seconds | 2s | Shorter = more reliable on ZeroGPU |
-| Enhance prompt | On/Off | On | Uses Gemma to enhance the prompt |
-| Seed | 0–2^31 | Random | For reproducibility |
+| Duration | 1-5 seconds | 2s | Shorter = more reliable on ZeroGPU |
+| Enhance prompt | On/Off | On | Gemma-3 rewrites prompt for better results |
+| Seed | 0-2B | Random | For reproducibility |
 
 ## Limitations
 
@@ -69,6 +89,6 @@ to run the massive 22B model on ZeroGPU:
 
 ## Credits
 
-- Model: [Lightricks/LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3)
-- Codebase: [Lightricks/LTX-2](https://github.com/Lightricks/LTX-2)
-- ZeroGPU architecture inspired by [alexnasa/ltx-2-TURBO](https://huggingface.co/spaces/alexnasa/ltx-2-TURBO)
+- **Model**: [Lightricks/LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) (22B parameters)
+- **Codebase**: [Lightricks/LTX-2](https://github.com/Lightricks/LTX-2)
+- **ZeroGPU architecture** inspired by [alexnasa/ltx-2-TURBO](https://huggingface.co/spaces/alexnasa/ltx-2-TURBO)