Posts by Linoy Tsaban 🎗️
Welcome⚡️Fast Flux.1 Redux ⚡️
Flux Redux 🤝 Hyper Flux LoRA
creative image variations using 8 steps only🏎️💨
🆕 and now with:
✅ prompt support 📝
✅ attention masking for better prompt adherence 🎯
✅ multiple image interpolation 🏞️🌇
Flux Fill for outpainting is so on point 🎯
the alignment with the artistic style of the last one is 👇🤯
« Is Our project is working properly as a HF @huggingface.bsky.social Space ? » should be your very important latest check before publishing a Paper nowadays 🤗 Tell your mentors
'tis the season of open-source video models 🎄📹⚡️
Tencent just dropped the weights for ✨HunyuanVideo✨
- 13B parameters
- competitive with closed source
- code & weights released
- demo coming soon 🔥
tweaking the scales makes a nice semantic grid
interpolating famous artworks with Flux redux creates very cool hybrids
(🧨 diffusers support coming soon ✨)
love Fill's blending & context understanding
▶️ Fill huggingface.co/spaces/black...
▶️ Canny huggingface.co/spaces/black...
▶️ Redux huggingface.co/spaces/black...
▶️ Depth huggingface.co/spaces/black...
Flux tools demos are now available on Spaces 🚀
▶️ Fill
▶️ Canny
▶️ Redux
▶️ Depth
Let's go 🔥
Let's make AI more inclusive.
At @huggingface.bsky.social we'll launch a huge community sprint soon to build high-quality training datasets for many languages.
We're looking for Language Leads to help with outreach.
Find your language and nominate yourself:
forms.gle/iAJVauUQ3FN8...
FLUX.1 Tools are now officially supported by 🧨diffusers 🎉
✅ just make sure to install from `main`
check them all 👇
huggingface.co/collections/...
The magical loop of trying to catch up on ~2 weeks of AI when every 2 hours smth new comes out 🤯
Lightricks just released LTX-Video 📹 the first DiT-based video model generating high-quality videos in real-time ⚡️
and it's open sourced 🔥
Lightricks just announced LTX Video, a new open-source, community-driven model for video generation, and claims 5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100! ⚡
🥹🥹