LTX 2.3 Ultra Video Pipeline (Pose Control + Face/Hand Detailer)
This is a highly optimized, production-ready video-to-Video workflow for LTX-Video 2.3. It perfectly syncs dance motions using IC-LoRA Union Control while preventing any facial or hand distortion through a dedicated post-processing detailer pipeline.
Key Features
Base Engine: LTX-Video 2.3
Motion Control: Integrated
IC-LoRA-Union-Controlfor flawless pose tracking.Quality Preservation: Advanced Face & Hand Detailer pipeline to fix distortion during intense movements.
Hardware Friendly: Tailored for mid-tier GPUs (e.g., RTX 4060) using FP8 Scaled Transformer.
Nodes description & caution
Please strictly follow these parameter rules to avoid artifact burning or system errors:
1st Sampler Strength Adjustment
For dynamic videos, you need to adjust the strength level slightly. Lowering the strength reduces distortion of the human body, but it may decrease the accuracy of the pose.
Face and Hand Detailer
Denoise : You can draw faces and hands more accurately by adjusting the denoise value. A maximum value of 0.2 is recommended.
Additional files required : face_yolo8, hand_yolo8
Upscaling
Upscaling is not yet perfect. If you have a good sigma value, please adjust it or replace the scale model to make adjustments.
📦 Required Models
Z Image Turboltx-2.3-22b-dev_transformer_only_fp8_scaled.safetensors
Description
FAQ
Comments (1)
well i have a question.....
there is an uplad base image
there is a last image upload
and video upload.....
question what i need to put in those upload nodes ?
i get upload video is for pose ....okay but for the images ?