Enze Xie
@xieenze_jr
Followers
567
Following
40
Statuses
32
Sr. Research Scientist at NVIDIA, doing GenAI, CS PhD from HKU mmlab, interned at NVIDIA.
Boston, MA
Joined November 2023
Disclaimer: This SanaAI account is a copycat account❌and has nothing to do with me, NVIDIA/MIT Hanlab, or our SANA paper. Sana project aims to advancing the frontiers of generative AI research. It has never issued and will never issue any crypto coins. Don't be fooled.
Fair access, real ownership. We believe early opportunities shouldn’t be reserved for a select few. That’s why we’re launching Sana on @pumpdotfun, to level the playing field and let everyone grow with us. Be part of the future, not just a spectator.
0
5
22
SANA LoRA is coming！
We just shipped support for SANA LoRA fine-tuning in Diffusers. With `Sana_1600M_1024px`, 700 steps, and 18 images, fine-tuning is darn fast ⚡️ And it's accessible as SANA is a smol model compared to other beasts. The script should be compatible with the other SANA ckpts, too!
0
1
18
Hi everyone, I'm thrilled to announce that you can now try #SANA models in #ComfyUI🎉. We show video generation using SANA+CogVideoX. SANA now also supports Chinese and Emoji prompts. If you find SANA useful, we’d be grateful if you could give us a🌟at �
🥳⚡️SANA's code is released, enjoy it and welcome star⭐️! SANA is an efficient linear DiT that can generate images from 1K to 4K 🌆🎨 Code: Demo: Highlight: ⏩ 20 x smaller & 100x faster than FLUX 💻Deployable on laptop GPU
1
5
49
RT @lmxyy1999: Hi everyone, thank you for your patience! I'm thrilled to announce that you can now try 4-bit #SVDQuant FLUX models in #Comf…
0
22
0
🥳⚡️SANA's code is released, enjoy it and welcome star⭐️! SANA is an efficient linear DiT that can generate images from 1K to 4K 🌆🎨 Code: Demo: Highlight: ⏩ 20 x smaller & 100x faster than FLUX 💻Deployable on laptop GPU
0
5
19
RT @zhuoyang_zhang: 🥳 We're thrilled to announce that VILA-U is now open source! VILA-U is a Unified foundation model that integrates Vi…
0
52
0
RT @haotiant1998: 🚀 We're thrilled to introduce HART, an efficient AR model that generates stunning 1024x1024 images! 🎨✨ HART delivers: ⚡️…
0
27
0
RT @hancai_hm: 🥳 We are excited to introduce Deep Compression Autoencoder. It dramatically reduces the token number of the latent space, de…
0
6
0
@pom_X_moq The company is reviewing our open-source application; please wait patiently for the result. 😉
0
0
2