xiankgx/controlnet-tile-image-detailer
![](https://tjzk.replicate.delivery/models_models_cover_image/73b9d027-6238-4490-a4f7-2deb0c1927f0/voice-tools.webp)
xiankgx/voice-tools
Text-to-speech with OpenAI or MetaVoice-1B and voice clone with OpenVoice v2
![](https://tjzk.replicate.delivery/models_models_cover_image/711d44c8-3982-48cf-abf6-7e6801dbce3f/musetalk_arc.jpg)
xiankgx/musetalk
MuseTalk: Real-Time High Quality Lip Synchronization with Latent Space Inpainting
![](https://tjzk.replicate.delivery/models_models_cover_image/feaacf50-9e2a-4ae2-8503-ae97cd3a0254/architecture.png)
xiankgx/panda-70m-video-captioning
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
![](https://replicate.delivery/pbxt/KgRH4AoijNe7h1lU84m4YwghJNdZ520I7qhGe0ip1ufa9CSA/tgt.jpg)
xiankgx/face-swap
![](https://replicate.delivery/pbxt/fZio7iD3LgwYKyeQ1iv0fXcFHNU4bzPuIxx6QDHoEXyYf8YKB/0000.jpg)
xiankgx/sdxl-evolution-0.1
Genetic algorithm like mixing of SDXL models
![](https://tjzk.replicate.delivery/models_models_cover_image/7b9d0a82-9037-4e14-a6cf-2101a80a544f/image_14.png)
xiankgx/lcm-lora-sd-img2img
LCM-LoRA Lycon Dreamshaper8 img2img
![](https://tjzk.replicate.delivery/models_models_cover_image/98cf1605-993d-490a-9bed-3d92b34331b2/arch.png)
xiankgx/saliency-crop
Saliency cropping using TranSalNet
![](https://tjzk.replicate.delivery/models_models_cover_image/72af9904-99a3-4229-9791-dd6d7d14b5e0/video-retalking.png)
xiankgx/video-retalking
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing in the Wild
![](https://tjzk.replicate.delivery/models_models_cover_image/77a94ec3-7a62-4b96-bb33-a8293d98d110/seine.gif)
xiankgx/short-to-long-video-diffusion
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
![](https://tjzk.replicate.delivery/models_models_cover_image/018f1c9a-19e0-4d49-80b9-d2377ff52f03/LipSickYouTube.jpg)
xiankgx/lipsick
Fast, High Quality, Low Resource Lipsync Tool