ykk648 / miaoya_pipelineLinks
猜测妙鸭实现证件照生成的pipeline
☆14Updated 2 years ago
Alternatives and similar repositories for miaoya_pipeline
Users that are interested in miaoya_pipeline are comparing it to the libraries listed below
Sorting:
- The first high-definition cloth retouching dataset CRHD-3K.☆94Updated 2 years ago
- Official PyTorch Implementation of XMP-Font (CVPR 2022)☆31Updated 3 years ago
- 这是一个基于stable diffusion的扩展绘画工具（outpainting）☆36Updated 2 years ago
- Official Implementation of 'E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion'☆143Updated last year
- Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion☆49Updated last year
- forked from damo/cv_unet_face_fusion_torch☆32Updated 2 years ago
- Unofficial PyTorch implementation of the Try-On algorithm (tryondiffusion, sd+cn, PIDM).☆89Updated last year
- 基于roop与codeFormer的换脸一体脚本☆21Updated 5 months ago
- A pre-trained face parser based on SegNeXt☆50Updated 2 years ago
- An updated version of virtual model making☆91Updated 3 years ago
- We are committed to building an cartoon community using deep generative models☆14Updated 2 years ago
- Proof of concept for control landmarks in diffusion models!☆90Updated 2 years ago
- 📷 EasyPhoto | Your Smart AI Photo Generator. Without Stable-Diffusion-Webui☆289Updated last year
- Code for project DS-Fusion☆161Updated 2 years ago
- 【MODNet-entry】开箱即用的人像抠图工具☆177Updated 2 years ago
- repository for dreamoving-phantom https://www.modelscope.cn/studios/vigen/DreaMoving_Phantom/summary. DreaMoving-Phantom is a general and…☆136Updated last year
- Better model，Better performance☆108Updated 3 years ago
- ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations☆32Updated 5 months ago
- Unofficial pytorch implementation of TryOnDiffusion☆62Updated 2 years ago
- Text-To-Image Generation with Chinese Characters☆131Updated 2 years ago
- 这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。☆31Updated this week
- SDXL-based ControlNet implementation☆29Updated 2 years ago
- ☆24Updated last year
- 基于wav2lip进行虚拟数字人训练，唇形驱动，包括数据处理流程等，模型包括96x96，192x192，192x288，288x288。☆20Updated last year
- ☆47Updated 2 years ago
- ☆27Updated 2 years ago
- [CVPR2024] Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth☆80Updated 7 months ago
- The GFPGAN network consists of two networks. Actually GFPGAN and StyleGAN2☆40Updated 3 years ago
- Matting by Generation☆36Updated last year
- Unofficial implementation of DragGAN with StyleGAN2/3 pretrained models☆96Updated 2 years ago