Linoy Tsaban

@linoy_tsaban • 6,071 subscribers

Exploring the world of AI Art as a ML engineer @HuggingFace 🤗

Shorts

374,270 views

156,628 views

130,160 views

30,005 views

27,504 views

17,600 views

107,955 views

15,384 views

12,374 views

13,057 views

14,426 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

58,675 views • 1 month ago

90,316 views • 9 months ago

56,496 views • 1 year ago

19,608 views • 9 months ago

17,573 views • 8 months ago

19,564 views • 10 months ago

18,552 views • 9 months ago

14,493 views • 9 months ago

14,991 views • 1 year ago

10,387 views • 1 year ago

No more content to load

Live Cam

Linoy Tsaban

Shorts

adding camera control to the list of things Qwen Image Edit is great at + with a specialized multi-angle LoRA it's even better✨ &gt; rotate the camera &gt; tilt between bird’s-eye and worm’s-eye views &gt; adjust lens (wide, close-up) of course we built a demo for it 🤝📹

Camera angle editing has never been this intuitive &amp; fast 🔥 Just added apolinario 🌐 's 3D interactive component to the Qwen Camera Angle Control demo, using 大雄's Qwen-Edit-2509-Multiple-Angles LoRA Simply drag the camera around 👇

turns out it works with paintings too 🤯

My favorite editing model, FLUX.2 [klein] 9B, just got 2x faster: Meet FLUX.2 [klein] 9B-KV 😍💨 &gt; Using KV-Cache Optimization to reduce computation &amp; speed up inference by up to 2.5 times for multi-reference editing love how well it edits "around" the bullets

now with audio input support too 🔊

Really impressed by this outpaint IC-LoRA for LTX 2.3 from Mohamed Oumoumad, it fills in quite seamlessly 🔥 demo coming ✨

meme possibilities are ♾️ having too much fun with this face expression editor →

this is amazing (and it's the first generation with this prompt) the raised eyebrows at the end haha, so on point

this LoRA is awesome for portraits with z image! love the aesthetic &amp; details built a demo for it 👇✨

Wan 2.2 Speech-to-Video 14B just landed &gt; audio-driven cinematic video generation &gt; weights &amp; demo on the hub &gt; apache 2.0 license + looks like it could be compatiable with Wan 2.x LoRAs out-of-the-box

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥

Videos

Watch Anya Live

It's out, and it comes with a demo🔥 Introducing Flux.2 [klein] Move ✨ &gt; specialized move &amp; resize LoRA for Flux.2 [klein] 9B &gt; draw boxes manually or pick from auto-detected objects &gt; works with fast 4-8 step inference 💨

Inpainting with Qwen Image Edit takes it next level it's sooo precise this is also a great reminder that when a good model is open sourced - the coumminty will build with it to enhace it even more ✨

just landed on hugging face: Step1X-Edit ✍️ & it's honestly one of the best open source image editors I've tried ✨ combines Multimodal LLM (Qwen VL) with Diffusion transformers to process and perform edit instructions ✨ apache 2.0 license ✨ new benchmark for image editing: GEdit-Bench

We're releasing ✨Qwen Image Edit Relight✨ a dedicated Qwen Image Edit app for image relighting fast, precise and optimized for relighting no more need for a complex workflows when you can get sota outputs with as little as 8 steps

yet ANOTHER release from ByteDance just landed on the hub ✨HuMo✨ &gt; video generation w/ multi-modal conditioning: audio, text &amp; image &gt; supports consistent subject preservation, synchronized audio-driven motion &gt; based on Wan 2.1 &amp; Whisper Large v3

OmniSVG demo &amp; weights finally dropped on Hugging Face🔥🔥 ✨ end-to-end multimodal SVG generator ✨ leverages pre-trained VLMs ✨ works all the way from simple icons to intricate anime characters

Alibaba just dropped the code &amp; weights for FantasyPortrait ✨ multi-character portrait animation ✨ comes with Multi-Expr Dataset - first dataset for multi-portrait facial expression ✨ apache 2.0 license

Inpainting with Qwen Edit is like working with a magic brush amazing how well it works out of the box

just in time for the holidays 🎄🎁 RF inversion demo is here ✨ edit &amp; stylize with Flux 🖌️ super cool work from Litu Rout , Nataniel Ruiz, now open w/ 🧨diffusers support thanks to an awesome community effort 🙌🏻

vibe coding ---&gt; vibe drawing ✍️ co-drawing with gemini is incredible 🤯

adding camera control to the list of things Qwen Image Edit is great at + with a specialized multi-angle LoRA it's even better✨ > rotate the camera > tilt between bird’s-eye and worm’s-eye views > adjust lens (wide, close-up) of course we built a demo for it 🤝📹

Camera angle editing has never been this intuitive & fast 🔥 Just added apolinario 🌐 's 3D interactive component to the Qwen Camera Angle Control demo, using 大雄's Qwen-Edit-2509-Multiple-Angles LoRA Simply drag the camera around 👇

My favorite editing model, FLUX.2 [klein] 9B, just got 2x faster: Meet FLUX.2 [klein] 9B-KV 😍💨 > Using KV-Cache Optimization to reduce computation & speed up inference by up to 2.5 times for multi-reference editing love how well it edits "around" the bullets

this LoRA is awesome for portraits with z image! love the aesthetic & details built a demo for it 👇✨

Wan 2.2 Speech-to-Video 14B just landed > audio-driven cinematic video generation > weights & demo on the hub > apache 2.0 license + looks like it could be compatiable with Wan 2.x LoRAs out-of-the-box

It's out, and it comes with a demo🔥 Introducing Flux.2 [klein] Move ✨ > specialized move & resize LoRA for Flux.2 [klein] 9B > draw boxes manually or pick from auto-detected objects > works with fast 4-8 step inference 💨

yet ANOTHER release from ByteDance just landed on the hub ✨HuMo✨ > video generation w/ multi-modal conditioning: audio, text & image > supports consistent subject preservation, synchronized audio-driven motion > based on Wan 2.1 & Whisper Large v3

OmniSVG demo & weights finally dropped on Hugging Face🔥🔥 ✨ end-to-end multimodal SVG generator ✨ leverages pre-trained VLMs ✨ works all the way from simple icons to intricate anime characters

Alibaba just dropped the code & weights for FantasyPortrait ✨ multi-character portrait animation ✨ comes with Multi-Expr Dataset - first dataset for multi-portrait facial expression ✨ apache 2.0 license

just in time for the holidays 🎄🎁 RF inversion demo is here ✨ edit & stylize with Flux 🖌️ super cool work from Litu Rout , Nataniel Ruiz, now open w/ 🧨diffusers support thanks to an awesome community effort 🙌🏻

vibe coding ---> vibe drawing ✍️ co-drawing with gemini is incredible 🤯