I'm a creative technologist working in real-time 3D and generative AI. My practice combines Unreal Engine, MetaHumans, Vicon motion capture, Blender, Octane, and ComfyUI with image and video generation models.
Selected work spans film, fashion, music, and exhibition; shown internationally and featured in editorial press. I also teach on YouTube and Instagram.
Open to commissions, collaborations, and R&D partnerships.
Based between Tel Aviv and Paris. Specializing in 3D animation, modeling, rendering, immersive video, GenAI, and AR.
Source above. Restyled below. Matched moments from the completed project.A local LTX-2.5 pipeline that carries a new visual style through source footage using keyframe anchors and structural guidance.
The current toolkit turns source footage into a newly directed visual treatment with LTX-2.5. Styled keyframe anchors establish the look, while source-derived Canny edges and Video-Depth-Anything guidance constrain composition and camera movement.
A configurable local workflow handles shot planning, render submission, retrieval, transitions and stitching. Verification checks frame alignment, frozen spans and source-audio preservation. The toolkit was developed from a completed restyle project; different footage requires its own tuning.
The comparison reel below shows the earlier 3D-to-stylized IC-LoRA study that led to this work. That experiment combined pose, depth and edge guidance with keyframe references, including aspect normalization to preserve the character proportions.
A chain of styled reference frames establishes appearance across shots and transitions.
Canny and video-depth control maps guide the scene geometry and camera movement.
Per-project configuration, transition planning, stitching and verification connect generation to a finished sequence.
Earlier IC-LoRA study: personal fan-art and R&D. The showcase character remains the property of its rights holders.




