This account is no longer active. Please follow @ltx_io for the latest updates.
Joined July 2025
- Tweets768
- Following256
- Followers14K
- Likes1.9K
LTX retweeted
Last week @fal and LTX.io joined us at @Techweek_ to make the case for open generative media. Good turnout, great room, amazing sushi by #BondiSushi. Some of the jokes could have been better, @gilshefler 😉
We got into how open models meet production reality — background removal at scale, generative fill, eraser, structured generation with FIBO and LORAs. Dun-dun-DUNNN, @blendibyl even created a microdrama. This is the power of community, this is the power of AI.
#BriaAI #GenerativeAI #VisualAI #OpenSource #ResponsibleAI
LTX retweeted
Can you build creative tools on models you don't control?
Join Bria AI, @ltx_model, @AiImagen, and @nvidia. June 22. Kickoff starts at 18:00.
Keynote + panel on the future of generative media. Rooftop World Cup watch party to follow.
📅 June 22
🕕 18:00
📍 Bria AI Loft
➡️ RSVP: eu1.hubs.ly/H0v_DXQ0
#GenerativeAI #VisualAI #BriaAI #GenerativeMedia #WorldCup2026
LTX retweeted
Audio-reactive CRT dance experiment: created with LTX 2.3 Quality on fal + my CRT LoRA + the LTX-2.3 Audio-Reactive LoRA.
@fal @Lightricks
LTX retweeted
LTX2.3 FPV motion LoRA
Captures low-speed FPV flight really well, smooth movement
huggingface.co/chsengni/ltx2…
(4/5) This is what open weights enables 🔓 We love to see this from our community.
I spent $30k and 3 months RL post-training an anime video model.
This is only step 30 out of a planned 1000 step run.
All samples are local text-to-video with no reference image/audio. Since it's based on LTX-2.3, each output takes under a minute on a single GPU.
I'm 19 and a solo researcher. Most of the budget went into ablations, reward design, and trying different configurations before reaching this setup.
The run is still extremely early, but the results already look much better than I expected.
It's compute-limited, not idea-limited.
I'm starting a company to continue scaling this and build frontier stylized video models.
If you're an investor, compute partner, video team, or someone who wants to help build this, DMs are open.
LTX retweeted
locked n loaded🔒
Made in @comfyUI, @AdobeAE + @Photoshop, @suno
Vid models: @Alibaba_Wan 2.2, @ltx_model 2.3 @thesystms FLW
Img models: @openai GPT 2.0, @googleai Nano Banana 2, @krea 2, @grok
GFX: @thesystms TimeSlice (see link below ⏬) + GFX nodes, @meta Sam3 + Sapiens2
LTX retweeted
I spent $30k and 3 months RL post-training an anime video model.
This is only step 30 out of a planned 1000 step run.
All samples are local text-to-video with no reference image/audio. Since it's based on LTX-2.3, each output takes under a minute on a single GPU.
I'm 19 and a solo researcher. Most of the budget went into ablations, reward design, and trying different configurations before reaching this setup.
The run is still extremely early, but the results already look much better than I expected.
It's compute-limited, not idea-limited.
I'm starting a company to continue scaling this and build frontier stylized video models.
If you're an investor, compute partner, video team, or someone who wants to help build this, DMs are open.
(5/7) World building 🤝 LTX-2.3
Built this animation in LTX 2.3. (In @ComfyUI Cloud).
A futuristic city buried inside a colossal canyon.
Feels like the kind of place where signals, stories, and narratives never sleep.
Ragnar Crypto Channel is just getting started.
