โจ Say goodbye to the tedious chore of splitting videos into pose images! LTX 2.5 Motion Sync is officially here, and it is a massive upgrade over LTX 2.3. This advanced workflow effortlessly transfers precise, lifelike motion from any source video directly onto your chosen characters in a single, fluid process! ๐
โ ๏ธ Heads up, creators: This setup handles realistic and 3D styles like a dream, but it may struggle with flat, 2D anime images.
๐ ๏ธ Changelog & Bug Fixes
Fixed in FlyV2.0: Better fidelity & motion adherence. Added a VideoStitch Node for comparison in Output & Original Input. Also added a Metadata Tracker node, for those who want to share their creations on CivitAI.
๐จ Why This Workflow Rules
Direct Motion Transfer: No more breaking down videos frame-by-frame.
Superior Precision: Noticeably cleaner and more accurate than older LTX 2.3 pipelines.
Hardware-Friendly Optimization: Built natively around the official, highly optimized distilled INT8 ConvRot architecture.
๐ง The Engine: Required Models
To make this magic happen, you will need to download and equip the following official models:
๐ LTX 2.5 Video VAE Conv BF16 โ The core video VAE.
๐ต LTX 2.5 Audio VAE BF16 โ Audio processor for complete sync.
๐ค Gemma 4 12B Text Encoder (Comfy INT8) โ Smart prompting alignment.
๐ค LTX 2.5 22B Distilled Transformer (Comfy INT8) โ The heavy-lifting generation model.
๐ LTX 2.5 Latent Spatial Upscaler X2 โ For crisp, high-fidelity output.
๐ฎ LTX 2.3 22B IC-LoRA Union Control (Ref 0.5) โ The secret sauce for fluid control.
LTX 2.5 Huggingface repository - https://huggingface.co/Lightricks/LTX-2.5/tree/main
๐ฌ Give it a Spin!
Take it for a test drive and push it to its limits! I would love to hear your feedback on the motion fidelity.
๐ Show off your motion transfers! Drop your original videos and your newly animated characters in the comments gallery below! ๐

