Keep on to blur preview images; turn off to show them clearly
StyleSculptor Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance
discuss with author: https://t.co/OfTFUNt9gz
No way bruh how could that happen again after PaLM 2 maybe it's not Gemini Pro tho
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
https://t.co/rrMR254fyS
Founder/CEO @Gumroad
This is very cool @leothecurious I think this largely vindicates me re your condemnation of VLM vision being premature and lots of low-hanging fruit even in this crippled paradigm
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
Third piece to the line of research I expect much from (+ Machine Mental Imagery + Perception Tokens): multimodal CoTs (instead of mumbling VLMs). Based on BAGEL (in turn based on Qwen 2.5-VL-7B), so pretty bounded. And very hand-crafted. But! They get emergent manipulations!
This is very cool @leothecurious I think this largely vindicates me re your condemnation of VLM vision being premature and lots of low-hanging fruit even in this crippled paradigm
Don't just take my words for it!
Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
