akbartus / DepthAnything-on-Browser
This repository demonstrates browser based implementation of DepthAnything and DepthAnythingV2 models. It is powered by Onnx and does not require any web servers or APIs.
☆17Updated last week
Alternatives and similar repositories for DepthAnything-on-Browser:
Users that are interested in DepthAnything-on-Browser are comparing it to the libraries listed below
- STDFormer: Spatio Temporal Disentanglement Learning for 3D Human Mesh Recovery from Monocular Videos with Transformer☆41Updated last year
- [IEEE/CVF CVPR'2022] "ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation", Duolikun Danier, Fan Zhang, David Bull☆13Updated last year
- Animefy: ComfyUI workflow designed to convert images or videos into an anime-like style automatically.☆21Updated 8 months ago
- ☆12Updated 5 months ago
- Use Stable Diffusion intrinsic lora to render texture maps (normal, albedo, shade, depth)☆15Updated last year
- ☆24Updated 9 months ago
- ☆13Updated last year
- ☆19Updated last year
- ☆12Updated last year
- ☆13Updated 10 months ago
- ☆13Updated last year
- ☆31Updated last year
- ☆9Updated last year
- Pytorch implementation of "PersonaCraft: Personalized Full-Body Image Synthesis for Multiple Identities from Single References Using 3D-M…☆44Updated last week
- ☆18Updated last year
- ☆10Updated last year
- Text-Guided Generation of Full-Body Image with Preserved Reference Face for Customized Animation☆23Updated 8 months ago
- ☆22Updated last year
- ☆12Updated last year
- ☆15Updated 11 months ago
- Gradio app to track objects in video and add visual effects☆16Updated 6 months ago
- [SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization☆10Updated 8 months ago
- ☆46Updated 4 months ago
- ☆46Updated last year
- ☆11Updated last year
- ☆14Updated 9 months ago
- ☆20Updated last year