CoolFace
Apppublic

Imosu/LTX-2.3-turboX

sourceHugging Faceotherupdated 7mo agoView on Hugging Face
3likes
App README

LTX-2.3 Turbo (ZeroGPU)

Generate synchronized video + audio from text or images using 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
  • —Interpolate Mode — provide first and last frames, generate video between them
  • —Audio Input — provide custom audio for lip-sync or soundtrack conditioning
  • —Prompt enhancement — Gemma-3 12B rewrites your prompt for better results
  • —Multiple resolutions — 16:9, 1:1, and 9:16 aspect ratios
  • —Duration presets — 2s, 3s, and 5s video clips
  • —Reproducible — set a seed for consistent outputs

How it works

This Space uses a vendored packages + pre-loaded models strategy to fit the massive 22B model on ZeroGPU's A10G (40GB VRAM):

  1. 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. 2.Text Encoding (@spaces.GPU): Encodes the prompt into video/audio context tensors using the pre-loaded text encoder, returned to CPU.
  3. 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

OptimizationDetails
FP8 quantizationTransformer weights cast to float8_e4m3fn, halving VRAM usage
Distilled pipelineOnly 8+4 denoising steps (vs 30+ for full model)
Pre-loaded modelsText encoder, transformer, video encoder loaded once at startup
Two-stage upscalingGenerates at half resolution, then upscales 2x with spatial upsampler
Vendored packagesltx-core and ltx-pipelines bundled for fast builds

Parameters

ParameterRangeDefaultNotes
ModeText to Video / Image to VideoText to Video
PromptFree text—Describe scene, motion, and audio
Resolution768x512, 512x512, 512x768768x512Upscaled 2x by spatial upscaler
Duration1-5 seconds2sShorter = more reliable on ZeroGPU
Enhance promptOn/OffOnGemma-3 rewrites prompt for better results
Seed0-2BRandomFor reproducibility

Limitations

  • —ZeroGPU time limits: Longer videos may exceed the GPU lease duration. Keep duration at 3 seconds or less for best reliability.
  • —VRAM constraints: Even with FP8 quantization, very high resolutions are not possible. The preset resolutions are tuned for ZeroGPU.
  • —No camera LoRAs: Camera LoRAs are only available for the 19B model, not the 22B 2.3 model.

Duplicating this Space

This Space uses google/gemma-3-12b-it-qat-q4_0-unquantized as the text encoder. Before duplicating, you must:

  1. 1.Accept the Gemma license on your HuggingFace account
  2. 2.Create a read-access HuggingFace token and add it as a Space secret named HF_TOKEN

Credits