On the recordRead 11 Oct 202621 facts
X-Dub
On the record
- Character support
- The project says it generalizes to stylized, non-human, and AI-generated characters.hjrphoebus.github.io · read 11 Oct 2026
- Community integration
- The repository links to community-maintained ComfyUI custom nodes with native video and audio inputs, standard VAE integration, and an isolated runtime.github.com · read 4 Oct 2026
- Cropping caveat
- The online DWPose-based cropping strategy may cause visible jitter or fail to follow faces during rapid head movement.github.com · read 4 Oct 2026
- Editing approach
- The project describes mask-free dubbing that uses full-frame temporal context without explicit masks or reference frames.hjrphoebus.github.io · read 11 Oct 2026
- Ethical use
- The repository warns of possible identity impersonation or deceptive synthetic media misuse and supports clear labeling of AI-generated content.github.com · read 11 Oct 2026
- Hardware requirement
- The repository says inference typically requires about 21 GB of VRAM.github.com · read 11 Oct 2026
- Input handling
- The inference pipeline accepts arbitrary-size input videos and automatically crops and resizes the face region to 512×512 before mapping the generated result back to the full video.github.com · read 4 Oct 2026
- Integration
- The repository links a community-maintained ComfyUI project with custom nodes for X-Dub.github.com · read 11 Oct 2026
- Intended users
- The project provides code, model weights, and command-line inference instructions for users setting up a local Python environment.github.com · read 4 Oct 2026
- Known limitations
- The public Wan-5B release may show flickering, identity or color drift, occasional noisy frames, and roughly twice the inference time of the internal version without acceleration.github.com · read 11 Oct 2026
- License
- The repository lists the Apache-2.0 license, which grants no-charge, royalty-free copyright permissions subject to its terms.github.com · read 11 Oct 2026
- Lip-sync
- The project says it produces speech-aligned lip movements while avoiding leakage and off-target edits.hjrphoebus.github.io · read 11 Oct 2026
- Output caveats
- The public release may show occasional flickering, identity or color drift, and severe noisy frames in roughly 2% of cases; the repository also reports roughly 2× slower inference than the internal version without acceleration strategies.github.com · read 4 Oct 2026
- Project affiliation
- The repository lists contributors affiliated with Tsinghua University, Kling Team at Kuaishou Technology, Beihang University, HKUST, and CUHK.github.com · read 4 Oct 2026
- Public release
- The repository provides a public X-Dub release based on Wan2.2-TI2V-5B and pretrained weights.github.com · read 11 Oct 2026
- Purpose
- X-Dub synchronizes a character’s lip movements in a video to match input audio.huggingface.co · read 11 Oct 2026
- Responsible use
- The project notes potential misuse for identity impersonation or deceptive synthetic media and encourages labeling AI-generated content.github.com · read 4 Oct 2026
- Single-person limit
- The current release supports single-person videos and does not support target tracking in multi-person scenes.github.com · read 4 Oct 2026
