toto222 / DICE-Talk
DICE-Talk is a diffusion-based emotional talking head generation method that can generate vivid and diverse emotions for speaking portraits.
☆18Updated this week
Alternatives and similar repositories for DICE-Talk:
Users that are interested in DICE-Talk are comparing it to the libraries listed below
- ☆24Updated last year
- ☆23Updated this week
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (arXiv, 2024)☆50Updated 5 months ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆24Updated last year
- Pytorch implementation of Towards Consistent and Controllable Image Synthesis for Face Editing☆54Updated last week
- [ACM MM24] Official implementation of ACM MM 2024 paper: "ZePo: Zero-Shot Portrait Stylization with Faster Sampling"☆40Updated 8 months ago
- [ECCVW 2024] Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models☆28Updated 3 months ago
- Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)☆17Updated 8 months ago
- Animatediff implementation. Includes a ControlNet pipeline.☆19Updated last year
- Code for full fintuing Mochi model with FSDP (and CP)☆17Updated 3 weeks ago
- Paper: "From Text to Pose to Image: Improving Diffusion Model Control and Quality"☆46Updated 5 months ago
- Fine-tune of Florence-2 for shot categorization.☆24Updated 2 months ago
- Explore how Flux Dev responds when you change the strengths of layers in the model.☆20Updated 7 months ago
- Official implementation of MagicFace: Training-free Universal-Style Human Image Customized Synthesis.☆62Updated 4 months ago
- ☆46Updated 5 months ago
- Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"☆37Updated 5 months ago
- ☆14Updated 4 months ago
- ☆25Updated last year
- ☆83Updated 8 months ago
- A example pipeline to use InstructPix2Pix and the associated fine-tuned motion module☆31Updated last year
- [CVPR'25] Official PyTorch implementation of AvatarArtist: Open-Domain 4D Avatarization.☆46Updated last month
- Generate images from an initial frame and text☆37Updated last year
- An attempt at a SVD inpainting pipeline☆51Updated last year
- This is the official repository for "LatentMan: Generating Consistent Animated Characters using Image Diffusion Models" [CVPRW 2024]☆23Updated 9 months ago
- ☆28Updated 9 months ago
- ☆22Updated last year
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆86Updated last year
- Website source code for our ACM MM'23 paper "Hierarchical Masked 3D Diffusion Model for Video Outpainting".☆42Updated last year
- Collection of scripts to build small-scale datasets for fine-tuning video generation models.☆53Updated last month
- ☆32Updated last year