lukassteinwender / avatair
A pipeline to generate user-preferred photo-realistic avatars using stable-diffusion and bayesian-optimization.
☆18Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for avatair
- ☆10Updated 10 months ago
- Towards Robust Blind Face Restoration with Codebook Lookup Transformer☆27Updated 10 months ago
- Audio-Visual Lip Synthesis via Intermediate Landmark Representation☆14Updated last year
- ☆30Updated 9 months ago
- ☆28Updated 11 months ago
- ☆11Updated 11 months ago
- Talking head animation☆27Updated 11 months ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆23Updated 11 months ago
- Generate images from an initial frame and text☆37Updated last year
- ☆34Updated 6 months ago
- ☆30Updated 11 months ago
- Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models☆14Updated 10 months ago
- Animatediff implementation. Includes a ControlNet pipeline.☆19Updated 10 months ago
- lightweight LAMA inference wrapper☆24Updated last year
- ☆26Updated 5 months ago
- Use miniGPT-4 batch to generate captions for a lot of images! You should be able to create the best captions you always wanted!☆17Updated last year
- ☆30Updated last year
- ☆13Updated 8 months ago
- ☆11Updated last month
- ☆19Updated 7 months ago
- Implementation of Grounding DINO & Segment Anything, and it allows masking based on prompt, which is useful for programmed inpainting.☆34Updated last year
- Playground Web UI using segment-anything-2 models from the Meta.☆29Updated 3 weeks ago
- ☆27Updated last year
- ☆24Updated 11 months ago
- ☆40Updated last year
- ☆15Updated last year
- ☆14Updated 3 months ago
- ☆15Updated 11 months ago