ZinFede

I'm a Principal CX/UX Research Consultant and Product Manager in Generative AI and XR. I love stock trading!

[JSFILMZ @JSFILMZ0412]

Watch this before you use the new Seedance 2.5 Long video mode. This is 1 prompt 1 Minute clip. Mostly a good feature with some caveats.

Full review in the comments soon.

[Andrew Fox @afoxdesign]

Meta Phoenix looks cool n all but you’ll still need mods like this to make it comfy for VR / long sessions, right?

[fal @fal]

Grok Imagine Video 1.5 just got a major update on fal

Reference-to-Video: up to 7 reference images — every character stays consistent (720p)
Text-to-Video: now available on 1.5, up to native 1080p
Image-to-Video: native 1080p support

[Road to VR @RtoVR]

These XR Glasses Want to Be the Monitor You Wear All Day - Kickstarter Coming August 4th

See more 👉https://t.co/UMGXaQmZlJ

[Justine Moore @venturetwins]

Editing is so underrated as a feature of generative video models.

This is a great example from Seedance 2.5 - replicating a Timberland ad exactly and just swapping out the shoes.

Imagine the use cases here in advertising and even post-production - no more reshoots needed!

[Bilawal Sidhu @bilawalsidhu]

Pretty cool! Nano Banana is now inside Google Earth so you can reskin your home, city -- or even try your hand at time travel.

[Magnific @magnific]

MiniMax H3 syncs voice to lips natively, per character, in one generation

This 4-shot scene took one prompt and kept everything consistent

Powered by @MiniMAX_AI, now on Magnific

[fal @fal]

MiniMax H3 (Hailuo-03) is now available on fal.

- Open-weight multimodal video model with native stereo audio on every generation.
- Combines up to 9 images, 3 video clips, and 3 audio clips as references
- Holds subjects, motion, and audio consistent
- Weights will be released soon.

[fal @fal]

Product Photo API is live on fal.

Generate consistent, studio-quality product photos with 100% product fidelity.

Customize backgrounds, margins, shadows, and logo placement at a fraction of the cost, making it ideal for e-commerce teams managing product catalogs at scale.

[Curious Refuge @CuriousRefuge]

So @DecartAI just released Lucy 2.5, a real-time AI video editing model that lets you swap outfits, add VFX, relight scenes, and transform into different characters live.

The visuals still have room to improve, but the real-time performance makes this one of the most exciting AI demos we've seen lately.

[Mac10 @SuburbanDrone]

Earlier this week before the Kospi exploded I drew this chart and put the blue line at the March lows. That’s where I said it would bounce. And it’s bouncing now per the dotted line.

But here is what no bull pundits will say - It’s dead money. A -50% loss takes a 100% gain to break even.

The bubble has popped and Asian AI gamblers are wiped out.

[ByteDance Seed @ByteDanceSeed_]

Introducing Seedance 2.5, our new-generation video creation model!

With advancements in long-form storytelling, multimodal reference, and editing, Seedance 2.5 goes beyond longer single-pass video generation, delivering the journey from idea to finished video with greater control.

Key highlights include:
1. Users can generate high-quality, 30-second audio-video clips in a single pass, bringing a complete story to life in one take.
2. Users can input up to 30 images, 10 video clips, and 10 audio clips as reference materials in a single pass.
3. Seedance 2.5 offers timestamp-level control for targeted editing of audio and video content, notably improving efficiency and controllability.

Visit project homepage learn more： https://t.co/9DFsAaacd3

[Curious Refuge @CuriousRefuge]

So @bfl_ai dropped Flux 3, a new open-weights video model that you can download and run on your own GPU instead of paying for cloud credits.

We put it head-to-head with Seedance 2.0, the current leader in AI video generation, and LTX 2.3, one of the best open-source video models out there right now.

After putting it through a bunch of tests, it's clear Flux 3 still has some catching up to do. It fell behind both Seedance and LTX across dialogue scenes, product commercials, and multimodal workflows that combined video, audio, and text. It's also currently limited to 720p output.

That said, we're really excited to see another open-weights video model enter the space. The more powerful models creators can run locally, the better.

We're looking forward to seeing where Flux 3 goes from here.

[Dreamina AI @dreamina_ai]

🎬 Global Launch: Dreamina Seedance 2.5 is now live!

Our most cinematic video model yet has arrived, and Dreamina AI is your official platform. Step into a new era of precision control and long-take storytelling:
· Native 30s videos in a single generation
· A new interactive editing experience: reshape any part of the frame
· Long video mode: up to 3 minutes, with consistency that holds throughout
· Dreamina AI plugins for Maya and Blender, built for film-grade production pipelines
· Up to 50 multimodal references, now with support for 3D white models and green-screen footage — bringing AI generation into real production workflows
· More true-to-life lighting and shadows, richer motion detail, and precise timestamp control down to 1 second

Dreamina Seedance 2.5 is more than a model. It's an upgrade to what you can create. Now open to Dreamina AI subscribers.

🕐 Available now across Southeast Asia, the Middle East, Africa, Europe, and South America. More countries and regions coming soon.
✨ Watch @yingjian355352 in action with the new model
⏳ Limited time: save up to 32% on credits per generation
🎁 Repost and comment – first 300 users get 1,000 credits in 12 hours

#DreaminaSeedance25 #DreaminaAI

[JSFILMZ @JSFILMZ0412]

MiniMax H3 is #2 on my list. @Hailuo_AI #MiniMaxH3 @TopviewAIhq for the Seedance 2.0 clips.
https://t.co/C7KV1yqzhb

[Sarang Borude @doomdave]

Opus 5 created this Architectural model after looking at 34 images in about 1 hour using the official Blender MCP. More details below.

[VEED | AI Video Creation @veedstudio]

VEED now has loads of APIs live on @fal.

- Subtitle API
- Fabric 1.0 (Image → Video) API
- Fabric 1.0 (Text → Video) API
- Fabric 1.0 (Audio → Video) API
- LipSync API (1.0 and 2.0)
- Video background removal API

Everything you need to power your video tools & workflows 💥

[Fish Audio @FishAudio]

Today we’ve raised $52M Seed and we are announcing the public launch of S2.1 Pro.

>It can clone a voice from 5 seconds of audio
>2x faster than Cartesia & 1/6th the cost of Eleven Labs
>most expressive model with word level control over emotion, intonation, pacing etc

We support frontier AI companies including HeyGen, LiveKit, Retell, Sanas, and OpenArt all run our model in production.

If you're a business and we can't cut your voice AI costs by 50%, we'll give you 1 year of Fish Audio for free.
Book a demo: https://t.co/vHkyZf9JoG

To celebrate our first birthday, we'll give you 1 month of S2.1 Pro for free. Like, retweet, and comment “Fish” to get it.

[Ben Lang @benz145]

One thing that makes me bullish on XR glasses as display replacements:

Unlike compute, resolution has a perceptual ceiling.

That means XR glasses will inevitably “catch up” to the quality of the best displays in the world.

After that, one lightweight device can give you an unlimited number of physical displays, anywhere you want. That’s an undeniably massive value proposition.

Ironically, I think the biggest challenge isn’t image quality. It’s the fact that virtual displays aren’t instantly and effortlessly “shareable” like real displays.

The sad part is that we absolutely have the technology to make virtual displays effortlessly shareable (even today), but we don’t have the will.

The industry will never settle on a single standard method shared across all devices, which means XR glasses will never achieve the same easy shareability of real displays.

[Nathie @nathie]

Here’s an exclusive first look at Threads on the Meta Ray-Ban Display smart glasses. It lets you scroll through your feed, watch videos, heart and share them with friends. Hope X is next!