README.md

metadata

title: 10Eros LTX 2.3 Image-to-Video
emoji: 🎬
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.44.1
python_version: '3.12'
app_file: app.py
pinned: true
short_description: 10eros ltx 2.3 image-to-video with native audio

10Eros LTX 2.3 image-to-video space.

runs an in-process comfy workflow against the 10eros LTX 2.3 fp8 checkpoint. the underlying model is LTX 2.3 audio-video, so audio is generated alongside the video and muxed into the output by default. an audio toggle is exposed if you want a silent mp4.

quick usage:

• upload a starting image
• write a prompt
• pick a preset (tuned is the default)
• generate

face targeting modes:

• anchor only: broad latent anchor, no per-face guide
• auto face: mediapipe face detection, likeness guide + anchor
• manual bbox: paste x1,y1,x2,y2 normalized 0-1

keep generations short on first try. larger frames and longer durations spend more zerogpu time.