I've worked with @kylancodes to put together a little dedicated Replicate model that gives you: - all the face images - a sprite/grid of all the faces - vanilla HTML, JS and CSS to render the effect - a preview video https://t.co/cdY4HaUEzk

One day I'll work out how @mattrothenberg built the infinite scrolling in https://t.co/OYS0m4o0fg.

Get it on the Mac App Store, or learn more at https://t.co/dycG4mMgwu, and thanks for supporting indie software. 😊

Big day for the little app that could—Pika 1.1.0 is out. It includes APCA contrast calculation support (the spiritual successor to WCAG), along with a bunch of features and fixes.

Lovely to see Pika ( https://t.co/dycG4mMgwu) get a shout out in the April edition of Mac & i ( https://t.co/IzaHO6VQ6H). Thanks, Wolfgang Kreutz / @heiseonline!

My experience with Claude Code lately:

Introducing Kontext Chat. Edit images by just chatting with them. Kontext was crying out for a chat interface, so we made one. Check it out: https://t.co/2upYgR0PnM

Absolutely bananas. We are living in the future. https://t.co/bb80WQ0JIk prompt: "Make this image into an oil painting with heavy brush strokes while keeping the person in the exact same position, scale, and pose. Maintain identical subject placement, camera angle, framing, and

Did you know you can now generate audio in our playground? https://t.co/aeoLfX8oEg Try it with text to speech: https://t.co/wAm7kZWWOS Or make music: https://t.co/xDno0X94rm

Feeling inspired to add a 'Leave a tip' option to my website after watching Taken on my recent flight back from SF. Nothing like Liam Neeson to spark some fun UI/UX ideas

We're teaming up with @replicate and @OpenAIDevs in SF for a Dumb Things AI Hackathon in early May! Interested? Hope to see you there! https://t.co/quNGu6tsoD

You can fine-tune video models now on Replicate. But what can they do? We built Repflix to answer that question. Each video is generated using a different fine-tuned model, showing how the same prompt can produce different styles and interpretations. Try it at the link below:

The @replicate playground supports video models! 1. Generate an image (e.g. with your Flux fine-tune) 2. Use it as a starting frame for a video 3. Kick off several generations at once 4. Kick back and enjoy the show Links in next post...

Thanks to everyone who has shared, contributed, given feedback, or encouraged the tiny little colour picker that could. Means a lot, as always. 😊 If you'd like to support its ongoing development, you can:

So, it's the weird window between Christmas and New Year, so I've been noodling on Pika.

AI video is having its Stable Diffusion moment. OpenAI's Sora made everyone realize what is possible, and now there are loads of models that are just as good. Some are even open-source, so you can tinker on them, fine-tune them, and build upon them. Read more in 🧵

It'll be on sale til the end of December, and you can grab it here: https://t.co/E0oxP76EFP And you can learn more about Pika here: https://t.co/dycG4mLIGW Either way, thank you to everyone who has supported, encouraged, suggested, tested, and made Pika part of their workflow.

Pika has been noodling along for almost four years now and I've finally kicked it over to version 1.0. To celebrate the milestone, I'm releasing it on the Mac App Store. You can still get it for free, but if you'd like to pay to support it, you now can.

The fortnightly changelog is how we document the perpetual motion machine of @replicate. See what we've been up to lately:

How i make memes with @replicate and @ideogram_ai: - open the playground - add the ideogram model - upload template - inpaint the spots i want to change - describe the changes i want Amazingly you can just type the caption and Ideogram will add it too 🙀 who needs any other app