[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
- large-language-models
- video-language-pretraining
- vision-language-pretraining
- blip2
132,241 visible repositories in the index
1–19 of 19 · Most stars
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Image to prompt with BLIP and CLIP
A tool for seeing your Internet latency. Try it at http://gfblip.appspot.com/
Official implementation of BLIP3o-Series
Static recompilation of Donkey Kong Bananza (Switch 2) to native Windows and Linux with Vulkan. 0.4.2 out; on bananza: local co-op, 16:10, Thai, shorter level-entry stalls on NVIDIA, faster replay on few-core CPUs and dedicated AMD cards, prompts that follow button swaps. Roadmap: #10. No game files included.
Open source gamepad-native game launcher and overlay
[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.
An Android library introducing a stack of Views with the first item being flippable.
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.
👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]
Open-source ARM64 execution lab in safe Rust: run programs on three CPU engines and prove the results match real hardware.
Zenless Zone Zero Mod Menu: Shape New Eridu Your Way
Dark Souls 3 Trainer — Single-Player Build Planner, Soul Calculator and Offline Presets
p3dkg: .NET NativeAOT tool for testing and verifying Prepar3D V5 V4 V3 activate-behavior
Rar-Password-Unlocker-Full-Version: Brute-Force, Mask, and Dictionary Attack Security Auditor
Avast Internet Security: Antivirus, Firewall, and Antispam Protection for Windows
RxJava binding APIs for Android's animations
Synthesis is a universal object mapper for Sitecore
Sample game project using the Godot engine.