ambientocclusion (Allen Brower)

liked a model about 1 month ago

ali-vilab/In-Context-LoRA

Text-to-Image • Updated 10 days ago • 122k • • 503

updated a model 3 months ago

ambientocclusion/fsk1

Text-to-Image • Updated Sep 13 • 8

updated 4 models 4 months ago

liked a model 6 months ago

jasperai/flash-sd3

Text-to-Image • Updated Jun 27 • 1.26k • 109

liked a Space 7 months ago

Running on CPU Upgrade

141

🏠💻💌🤗

AI Town on HuggingFace

liked a model 7 months ago

Bin12345/AutoCoder

Text Generation • Updated Jun 4 • 373 • 95

reacted to DmitryRyumin's post with 🔥 7 months ago

Post

832

🚀🎭🌟 New Research Alert - InstructAvatar (Avatars Collection)! 🌟🎭🚀
📄 Title: InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation 🔝

📝 Description: InstructAvatar is a novel method for generating emotionally expressive 2D avatars using text-guided instructions, offering improved emotion control, lip-sync quality, and naturalness. It uses a two-branch diffusion-based generator to predict avatars based on both audio and text input.

👥 Authors: Yuchi Wang et al.

📄 Paper: InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation (2405.15758)

🌐 Github Page: https://wangyuchi369.github.io/InstructAvatar/
📁 Repository: https://github.com/wangyuchi369/InstructAvatar

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

🔍 Keywords: #InstructAvatar #AvatarGeneration #EmotionControl #FacialMotion #LipSynchronization #NaturalLanguageInterface #DiffusionBasedGenerator #TextGuidedInstructions #2DAvatars #VideoSynthesis #Interactivity #ComputerGraphics #DeepLearning #ComputerVision #Innovation