view article Article ฯ0 and ฯ0-FAST: Vision-Language-Action Models for General Robot Control 6 days ago โข 80
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up Paper โข 2412.16112 โข Published Dec 20, 2024 โข 22
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion Paper โข 2402.03162 โข Published Feb 5, 2024 โข 19
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling Paper โข 2401.15977 โข Published Jan 29, 2024 โข 38
Running on Zero 1 1 FurnitureInpaintingDemo ๐ Remove and replace furniture in images using a reference
Running on Zero 1 1 FurnitureInpaintingDemo ๐ Remove and replace furniture in images using a reference
view reply I really like the style of your 1 minute video. I still remember the one you did for 3DGS a long time ago
view post Post 2966 I made a 1 minute video explaining the DeepSeek situationR1: deepseek-ai/DeepSeek-R1Janus Pro: deepseek-ai/Janus-Pro-7B See translation 3 replies ยท ๐ฅ 11 11 ๐ 5 5 ๐ค 2 2 โค๏ธ 2 2 + Reply
laion/CLIP-convnext_base_w_320-laion_aesthetic-s13B-b82K Zero-Shot Image Classification โข Updated Apr 18, 2023 โข 10k โข 3