sd-wav2lip-uhq
sd-diffusion-and-dragons
sd-wav2lip-uhq | sd-diffusion-and-dragons | |
---|---|---|
1 | 1 | |
1,070 | 5 | |
- | - | |
7.8 | 7.1 | |
4 months ago | about 1 year ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sd-wav2lip-uhq
-
Time Travel Scene - Gen-2, ElevenLabs, Wav2Lip
Hi, Great job, If you need to remove the wav2lip blur, you can use : https://github.com/numz/sd-wav2lip-uhq
sd-diffusion-and-dragons
-
Implementations of REMO and other memory systems
My long term project is called Incarnate. Basically you feed the software a novel or wiki of a particular fictional universe and you can "incarnate" into it as anyone you wish. It would be a text adventure style game (or tool if you're a writer). I made a tiny PoC of a feature that allows GPT to use Stable Diffusion to generate images based on text descriptions it generates. This way it can generate rich visuals to go along with whatever scenario you're in. All of the in-game mechanics will be based on Dungeons and Dragons 5th edition, but I may make this modular later. A lot of custom tooling will probably be needed even with a full implementation of REMO.
What are some alternatives?
SadTalker - [CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
YourVision - AI-powered image editor
GeneFace - GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code
StableFusion - Transform text into images and images into new ones using AI. Our user-friendly web app, built with Diffusion, Python, and Streamlit, offers customizable outputs in various styles and formats
wav2lip-hq - Extension of Wav2Lip repository for processing high-quality videos.
pdfChatGPT - QA with the pdf using gpt-3.5
Wav2Lip-GFPGAN - High quality Lip sync
chatGPT-cheatsheet - An ever-evolving introduction to ChatGPT, AI, and machine learning (including prompt examples and Python-built chatbots)
CVPR2022-DaGAN - Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
CognitiveAtomV1 - CognitiveAtomV1: Integrating REMOv4-0 and CognitiveAgentV4-0 with atomv0-fullsample
batchlinks-webui - Download several Huggingface, MEGA, and CivitAI links at once. SD webui extension. For colab.
product-description-generator - Generate SEO-compliant product description using product title and meta- keywords provided by the user.