TheVisiblemaker @visiblemaker

We made a short film that asks one question: "what is reality?" For a year, every AI film we made answered it for us: you could still tell. Then BytePlus handed us Seedance 2.0 in native 4K, and we couldn't. Filmmakers have a word for footage clean enough to ship: final pixel. AI video has never been there, because resolution was always the ceiling. This is the first time the frame held everything we asked of it. It finally looks the way we imagined it. "Reality is our workshop. Imagination is our tool." Watch REALITY in 4K, then try it yourself: @BytePlusGlobal @lumina_ai_aiart

I am old enough to remember an 18 year old Michael Owen scoring that incredible goal against Argentina in the 1998 world cup, it's burnt into the memory of many an Englishman. It's incredible, how nearly 30 years later, Seedance 2.5 has been used to bring that 18 year old back on the pitch. It looks fantastic and most viewers would not be able to tell that it was AI generated. Seedance 2.0 was already incredible, I am confident that 2.5 will get us to the point where anything we conceive, we can make. The technology has finally achieved the quality of production values that allow story and emotion to take center stage. COME ON ENGLAND ! (we are playing Argentina again tonight)

BytePlus @BytePlusGlobal

a week ago

Classic moments. Now within reach. We’re sharing a story with @themichaelowen , using Seedance 2.5 to revisit some of the defining moments of his legendary career. From signature moves on the pitch to limitless creative possibilities, Seedance 2.5 pushes the boundaries of what

355 556 4K 12.8M 1K

Today, together with @kyutai_labs, we’re introducing our new Audio-to-MIDI model. It takes a finished recording, identifies the instruments playing, and returns separate MIDI tracks for each — voice, drums, bass, keys, and more. Unlike most existing solutions, our model works directly from the full mix rather than requiring separate stems. It also detects chords, key, and tempo, giving producers broader musical context. We’ve written more about the model, the problem, and how it works here: mirelo.ai/blog/turning-a…

Introducing Muse Image and Muse Video, the first media generation models developed by Meta Superintelligence Labs. Muse Image is our most advanced image generation model yet. It follows instructions faithfully, edits with precision, composes from multiple references, and draws on Instagram for social context. It also brings agentic tool use capabilities to image generation and integrates with Muse Spark. You can try Muse Image in the Meta AI app and web, as well as in Instagram Stories and WhatsApp – starting in limited countries with more locations on the way. Today we’re also previewing Muse Video, which is built upon the same pretraining base as Muse Image to deliver exceptional visual fidelity with native audio support. Learn more about both models: go.meta.me/7f4427

This is getting ridiculous. You need to try this AI filmmaking workflow. My Blender reference is embarrassingly simple. You can drive a precise multi-character shot with nothing but basic shapes. 1. Generate a start frame in Midjourney 2. Block out the scene in Blender with boxes, animate the camera 3. Feed both to Seedance This feels like a real unlock. Your 3D reference doesn't need to look good.

Character sheets are great, but they only solve one part of the problem. They show you how your AI character looks. They do not show you how they perform. So I made a simple workflow and a system prompt to audition my AI characters before taking them into video generation, to test their voice, emotions, expressions, and screen presence. Here is my workflow:

Character studies with @higgsfield_ai Soul Image model, upscaled with Magnific. Getting great realism and diversity from it. Used the Veo3 JSON VISMAKER from the VISMAKER Prompt Toolkit, available here: explore.visiblemakers.com #visiblemakers #visiblemaker #vismaker #aifashion

keyboard_arrow_left Previous keyboard_arrow_right Next

Had some fun playing around with @higgsfield_ai new image model SOUL. + shines for people and fashion shots + uses over 50 presets for specific image and portrait / selfie styles #aivideo #visiblemaker #visiblemakers #higgsfieldsoul

Excited to share a Veo2 short by @visiblemaker - a parody car commercial that takes a different road: What happens when you swap gigabytes of data for a bit of grit? 🚀 Hope you enjoy the ride, and be sure to watch until the very end. ;) @GoogleDeepMind @elevenlabs #Veo2

@visiblemakers @higgsfield_ai 🔥🔥🔥

@higgsfield_ai dropped their new image model "Soul". Had big fun testing: It shines at fashionable and realistic images of people. 🔥 Put together this quick edit, all shots animated with Higgsfield Video, upscaled in Topaz Video AI, edited in Adobe Premiere. 🙏 #higgsfieldsoul

𝗩𝗼𝗿𝗲𝘅 | 𝗢𝗳𝗳𝗶𝗰𝗶𝗮𝗹 𝗧𝗿𝗮𝗶𝗹𝗲𝗿 🔴 This isn’t the future of filmmaking. It’s the present.

@Uncanny_Harry Oh yes!! Its getting real...

If you think things are going to slow down in the AI Generated video space... wait until next week 👀

Creating a video with Veo 3 costs around $3. That’s why coming up with a solid prompt can save you a ton of cash on your video project! Let me show you how using JSON prompting 🧵👇

@Uncanny_Harry @HeyGen_Official Cold Call reimagined, great Heygen Avatar IV shot, mate 🤓💪 I know how much work you put into it a year ago I think? Yes its incredible how far we come and what we can bring to life now with a lot less pain. 🔥

Using Heygen to bring my Frames generated characters to life.... @HeyGen_Official

Meet Higgsfield Ads: turn one product pic into a studio ad in seconds. Upload a product photo, pick one of 40+ templates, and walk away with a cinematic spot. Retweet, like, comment "Ads" and the link with a detailed guide and 150+ use-cases hits your DMs.

🧪 The Future Character Creator I have always been a huge fan of extensive character creators in video games. There is something extremely compelling about tailoring a character to one’s own interpretation of a story. References + Gen-4 unlock countless exciting use cases, many of which we have seen shared among the community in the past days. For me, I wanted to see how far I can push a single character across multiple story arcs, wardrobes, and emotional intent. As a world builder, this pipeline feels like a superpower. For a long time, we have been making compromises when working with generative tools. We generated until things were “close enough.” It feels like those times are finally changing, allowing us to execute on ideas the exact way we imagined them. This is Annabel. Generated entirely in Gen-4 and placed into different worlds with references.

@HeyGen_Official @visiblemakers Love Heygen Avatar IV!! 😍Finally I can make my Humanoids talk in a high quality they deserve :9. Thanks a lot for this fine release! 🙏Can´t wait for the next update.