Hana Suzuki
hanasuzuki05
ยท
AI & ML interests
VLMs + text-to-image + super-resolution + img2img :)
Recent Activity
liked a model about 3 hours ago
umd-vt-nyu/image_editing_100epoch liked a model about 3 hours ago
Image-editing/Emu3-Base-SFT-reasoning_super_concise-Apr17_rinp_lr1e-5-checkpoint-11200 upvoted a paper about 3 hours ago
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash SpeedOrganizations
None yet