Teaching Murphy how to high-five. 😁 PS: The new model update for img2vid is fantastic, love the results so much!

✨ MIND = BLOWN! Just discovered this AI platform 🤯

Turn your Ghibli style images into animated videos on Morphic. 1. Paste the image on Canvas 2. Select the image 3. Change to 'Video' option on Focus Mode 4. Write the prompt mentioning the action and hit Generate Originally animated by Kunal Bagaria. What will you animate?

I discovered Morphic yesterday, and it's incredible. I often draft stories, comics, game narratives to satisfy my creative juices. I made using the image model from #GPT4o and animations from Morphic. Voice from ElevenLabs. Morphic is the Figma for Animations.

Whoever decided Cursor should have Agent mode as default in the chat clearly has more trust in AI than they should

More cool video tools coming Morphic soon....

Vision models have been smaller than language models; what if we scale them up? Introducing Web-SSL: A family of billion-scale SSL vision models (up to 7B parameters) trained on billions of images without language supervision, using VQA to evaluate the learned representation.

In 1997, Christopher Nolan made a short film called Doodlebug. He made it during his university days with a super low budget, and is 3 minutes long, but it is one of the most interesting things I've ever watched. As a personal experiment and side project, I recreated Doodblebug

Aside from the improved quality, we managed to get this one run 3x faster. Sub 3 min multi-image interpolation really speeds up iteration for animators

This week, we're excited to roll out a new Interpolation update—with faster, smoother, and improved results than ever.

I'm not sure how Google search indexing works but LLMs can probably help

We find training unified multimodal understanding and generation models is so easy, you do not need to tune MLLMs at all. MLLM's knowledge/reasoning/in-context learning can be transferred from multimodal understanding (text output) to generation (pixel output) even it is FROZEN!

Recipe for the soul. Generated on Morphic Studio.

Image and animation generated with @Morphic Using natural language, one chat session.

AI Startup Morphic to Produce Anime Series 'DQN,' Launches $1 Million Creator Fund for Emerging Filmmakers (EXCLUSIVE) variety.com/2025/global/ne…

morphic.com/blog/video-mod… We wrote about some of our experience doing large scale data processing for training Video Gen models. We'll be releasing more tech blogs, and open source some of this in the future

This is peak Morphic enabled storytelling

You can now refer character in Morphic copilot to do consistent iterations. Try it! studio.morphic.com/chat

One of those experiments which showed incredible promise very early - we pushed a lot to make ensure robustness across dimensions/video types. Do give this a shot

AI benchmarking culture is completely out of control. Tables with dozens of methods, datasets, and bold numbers, trying to answer a question that perhaps no one should be asking anymore.