Replicate

LTX-2.3 by @ltx_model is here → Crisper fidelity & on-screen text → Complex multi-subject prompts that stick → Start + end frame I2V with smooth motion → Cleaner audio + native portrait + 24/48 fps

@replicate just got name-dropped at the GTC keynote

I have a arsenal of apps that I built for myself that I use everyday.... One of my favorites is "VibeCloud", my SoundCloud downloader replacement I often create awesome videos that need a bed of dope music and all my music comes from SC. So I use my app to download or listen to or PUSH to my devices the mp3 of the song that I wish. It sync's with my playlist and it simply downloads the music. Nothing else. One Job. Download dope music. I even added a feature where you can get just the instrumental (using /cjwbw/demucs on @replicate), so that the music I have is always in the clear. Build apps for yourself.... You will be surprise how often they get traction. #BuildInPublic #TheAIMogul

P-video just got an update! Same price, same speed, better ... 👇 - Better character consistency - Better sound + audio in draft mode - Better quality overall 🎠 Try our free demos: dub.sh/sEN7i8c 💜 Sign up for our events: dub.sh/BDmCNBx 🎉 Find all of our models: dub.sh/OP90LS6 ⭐️ Star our OSS GitHub: dub.sh/ZA6N6YS

Nano Banana 2 model is ahead of any other trully impressed with the images I can generate with it for only $0.07 via @replicate API I'm in the two sides of the acuation: - As a SaaS founder (generate and schedule media) - As a short-term rental biz founder (promote villas)

The era of agents is here. We're hosting a private fireside chat at SXSW: Cloudflare CEO @eastdakota and Rapid Response host @rsafian on how agents are transforming the web. Learn more and RSVP below. schedule.sxsw.com/events/OE46813

Cute me,I love this style Try it 👇 Prompt by @fofrAI A digitally sketched color doodle of a the person in the photo as an anime character in the style of the reference, no text, no embellishments. Eyes must be widely separated small black dots (no white). Keep the same hairstyle and clothing from the photo, a cute ditto-like character with gloopy hair (but not drippy!), long arms, full body shot, short legs. wide mouth

Try Max here: replicate.com/inworld/tts-1.…

Try it Mini here: replicate.com/inworld/tts-1.…

Inworld TTS is here Two models from @inworld_ai, ranked #1 on Artificial Analysis: → Mini: built for real-time voice agents → Max: built for when voice quality is everything Both support 15 languages, emotion control, and non-verbal sounds

Try pro: replicate.com/vidu/q3-pro

Try turbo: replicate.com/vidu/q3-turbo

Vidu Q3 is now on Replicate Fast video generation with text, image, and start/end frame to video, all in one endpoint. Up to 16 seconds and 1080p with synchronized audio. Great for anime, cartoons, and cinematic storytelling.

ghibli era is over. we're all ditto now

And here how much my pet projects spend on @replicate Mostly image and a bit of small video generation (usually videos are 4s bytedance/seedance-1-pro-fast that costs 0.06$, nothing crazy)

gave my AI agents one job: make a music video about LGTM Music: Minimax Music 2.5 🎧 Video: Grok Imagine 🎥 LGTM 🚀

Ежедневно генерирую ~100 изображений через API @replicate. Вот отчёт по ежемесячным затратам: 👉 t.me/myitnotes #AI #генеративныеМодели #разработка #бюджет

Been using Kokoro-82M for text-to-speech and added it to @replicate with word-level timestamps (for English). That way you don't need to run TTS through Whisper and then merge the word timings back in. Great for captions, karaoke-style highlighting, or anything that needs precise word timing. Open weight. replicate.com/siegerts/kokor…

Try LTX-2.3 Pro here: replicate.com/lightricks/ltx…

Try the new "speed" and "precision" modes in Video Translate: replicate.com/heygen/video-t…

Kling Video 3.0 Motion Control by @Kling_ai Take any face and lock it in: perfect identity from every angle, complex emotions reproduced exactly, high-fidelity restoration even through occlusions, and crystal clear detail no matter how wild the framing gets.