Replicate retweeted
Introducing P-Video-2-Pro-Avatar, based on @MiniMax_AI H3 !
Turn a single portrait into a realistic talking video with natural expressions and accurate lip sync.
And for launch, it's 50% off for the first two weeks, until November 5 at 18:00 CET!
• 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: $0.02/s at 480p · $0.04/s at 768p
• 𝗦𝗽𝗲𝗲𝗱: ~0.97 s at 480p · ~2.2 s at 768p per second of output video
• 𝗜𝗻𝗽𝘂𝘁: One portrait with a text script or uploaded audio
• 𝗩𝗼𝗶𝗰𝗲𝘀: 30 voices across 10 languages
• 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 1s–3min at 24 fps, in 480p or 768p
• 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: Voice delivery, scene motion, seed, and prompt upsampling
One image, two ways to bring it to life. Use your own audio or generate speech directly from text.
Available via our inference partners @replicate, @eachlabs, @Cloudflare, @scenario_gg, @wavespeed_ai, @WiroAI, Sociaro, @TellersAI, and @togethercompute.
📚 Model docs: docs.api.pruna.ai/guides/mod…
🧩 Try the model through the API or Playground: dashboard.pruna.ai/login
Replicate retweeted
Join us for coffee at SOHN on Thursday, Oct 15 before Cloudflare Connect for the hallway track before the hallway track
👉 luma.com/k72rpi3a
Replicate retweeted
Nano Banana 2.1 came out this morning and it's already up on Replicate thanks to @lucataco and @shridharath.
For a good time, give your agent this prompt:
```
Let's use these skills to take Nano Banana 2.1 for a spin:
github.com/replicate/skills
github.com/zeke/replicate-lo…
replicate.com/google/nano-ba…
```
Replicate retweeted
I published a new agent skill: Replicate local workflow.
Whenever I run @replicate models from my local computer, I invariably end up repeating a lot of the same instructions to my agent harness. This includes stuff like making sure to run models in parallel to keep things snappy, saving all the the outputs locally, using sensible filenames, etc. Today I wrapped those instructions up into a new agent skill, so I don't have to repeat myself.
Check it out at github.com/zeke/replicate-lo…
Replicate retweeted
a wizard-duel show at a fantasy castle theme park
🤖 Made with AI
Replicate retweeted
I'll be speaking at Cloudflare Immerse in Stockholm next week. Still some spots left if you're in town, should be fun.
fieldmarketing.www.cloudflar…
Replicate retweeted
Added two new official Replicate skills: build-models + publish-models.
They teach agents (and humans) how to package custom AI models with Cog and push them to Replicate, using the patterns and tools we use internally for production models.
$ npx skills add replicate/skills
github.com/replicate/skills
Replicate retweeted
Day 5/30 Tools & resources I use as a startup founder in SF
Today: @replicate. One API call to run any AI model. Image gen, video, audio. No GPU, no infra. Pay per second. It's how I ship AI features fast.
#startupfounder #aitools #buildinpublic #replicate
Replicate retweeted
Inworlds new Realtime TTS-2 model just dropped
Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation.
It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention.
The result is voice AI that feels as good as it sounds.
Try it out: tinyurl.com/RealtimeAI
Learn More: tinyurl.com/TTS-2Blog
Replicate retweeted
✨ Clarity Upscaler now has a Pro version
It's the first upscaler that can add realism without changing a person's identity
Two years ago I launched Clarity Upscaler, which has since made 30 million runs. I still can't really believe it 🤩
It's great for creative upscaling but it always changes people's identity too much. I made Crystal to solve that, but it's not able to add details or realism.
Now we have Clarity Pro Upscaler which finally solves all that and can enhance images without changing the content.
In the coming days I will make it even more powerful by adding parameters and increasing the max resolution even further (it's already at 8K!)
Happy to hear your feedback
Replicate retweeted
Made a video explainer for @Cloudflare vibeSDK using:
🎙️ Inworld TTS (via @replicate)
🎬 Manim skill
🌥️ Cloudflare aesthetic
AI explaining AI infra, narrated by AI
Replicate retweeted
Free P-Video-Avatar usage until Sunday 23:59 CET at @replicate: replicate.com/prunaai/p-vide…
Replicate retweeted
Cloudflare just shipped Dynamic Workflows: durable, hibernating execution where the workflow code itself is dispatched at runtime
if you're running Replicate predictions, this is your new stack
expensive remote steps that take minutes and sometimes fail? That's the whole pitch
blog.cloudflare.com/dynamic-…
Replicate retweeted
P-Video-Avatar is now the fastest model for top-quality and diverse avatar generation.
- It costs 0.025$ per second of video, making it up 6× cheaper than similar avatar tools
- It takes 1.83s generation time per second of video, making it up to 18x faster than similar avatar tools.
- It offers full-body control, integrated audio support in 20+ languages, and is long-form video-ready for up to 3-minute consecutive clips.
We are launching with free usage until Sunday 23:59 CET at @replicate, @WiroAI, @inference_sh, @Runware, @Scenario_gg
And with general availability at:
@deepinfra, @Eachlabs
Try it now: p-video-playground-productio…
📚 API & quickstart for Pruna API: docs.api.pruna.ai/guides/qui…
⭐️ Star our OSS: github.com/PrunaAI/pruna
🌐 Website: pruna.ai/
Replicate retweeted
🎉 replicate/cog 0.19 is out with:
- new `cog doctor` command to fix broken setups/migrate from old cog sdk code
- static schema gen is now the default. users can still optin to legacy (runtime) openapi schema gen
- bunch of bug fixes
👇
Replicate retweeted
3 weeks ago we shipped cog 0.17
today: cog 0.18.0
@replicate + @Cloudflare velocity is real
github.com/replicate/cog/rel…
Replicate retweeted
companies use an average of 3.5 AI models across multiple providers
that's multiple SDKs, multiple bills, multiple points of failure
AI Gateway gives you one API for all of them:
blog.cloudflare.com/ai-platf…
Replicate retweeted
VEED Fabric 1.0 API.
Now on @Replicate⚡️
Get the most realistic AI talking videos in seconds 💥
• Faster, better, & cheaper
• Natural eye movement
• Real facial expressions
Comment "API" and we'll send DM the link.