@dabit3 Building Afterparty. a QR-powered mini platform for real-world events. Everyone at a trip/party/wedding uploads photos, completes ridiculous challenges and leaves messages; afterward it becomes an interactive little time capsule for the group.
@OfficialLoganK hi @OfficialLoganK
there's a serious issue in aistudio for right-to-left languages, here for example "Arabic" is written left-to-right and it's hard to read specially when there's english words in the middle, it messes up all the order
We’re excited to announce new editing features in Stable Assistant, our user-friendly chatbot. Leveraging the power of Stable Diffusion 3, these advanced text-to-image capabilities produce higher quality outputs.
Explore all the features here: https://t.co/zhO8brV07r
Iranian President Ebrahim Raisi is dead and the world is a safer place.
Raisi was responsible for the murder of thousands of Iranian political prisoners he ordered executed in 1988, 1,500 Iranians slaughtered in the 2019 protests and the years of terrorist violence sown by Iran across the region that claimed American lives.
My hope and prayer is that Raisi’s death will give the people of Iran a chance to claim their birthright of freedom and end Iran’s long reign of terror.
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt.
Explore the model and start creating for free at: https://t.co/AdYJxsG66R
Read the blogpost here: https://t.co/T4xYsmG4Jo (1/3)
The Stability AI Developer Platform now offers a comprehensive suite of API services, setting new standards in image generation, upscaling, and editing, with additional services forthcoming.
Learn more here: https://t.co/uVIx7SXeMN (1/4)
Delighted to enable more control via the @StabilityAI API 🤠
1. Search & replace 🔎
2. Editing, with inpaint 🎨
3. Creative upscaling 🆙
4. Stable Video 🎥
More releases 🔜 🚀
https://t.co/gXamC0mbx2
Announcing Stable Diffusion 3, our most capable text-to-image model, utilizing a diffusion transformer architecture for greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
Today, we are opening the waitlist for early preview. This phase is crucial for gathering insights to improve its performance and safety ahead of open release.
You can sign up to join the waitlist and learn more here: https://t.co/lX8z1UTc8s #stablediffusion3
Prompt: Epic anime artwork of a wizard atop a mountain at night casting a cosmic spell into the dark sky that says "Stable Diffusion 3" made out of colorful energy
So, from two years ago when we had 0 developers and 0 researchers, now we have @StabilityAI among the best models for:
Image ✅
Video✅
3D✅
Language✅
Code✅
Music✅
Speech✅
Mind-reading✅
Now we make them better quality, faster, cheaper & get them everywhere 🚀✨
Today, we are adding Stable Video Diffusion, our foundation model for generative video to the Stability AI Developer Platform API.
The model can generate 2 seconds of video, comprising of 25 generated frames and 24 frames of FILM interpolation, within an average time of 41 seconds.
Developers interested in utilizing Stable Video Diffusion through an API can access it now on the Stability AI Developer Platform.
Learn more here: https://t.co/WqJOH5Mq53
@jeremyphoward One severe case i saw of this is @MarioNawfal account, there’s 10s of auto generated replies seconds after he posts.
I’m sure there is some easy to use service they’re signing up for
Feeling overwhelmed by ComfyUI? You're not alone - our host @amli_art does too!
Tune in tomorrow on Stable Stage where Scott will guide us through basic setup to creating a workflow, and more!
There'll be laughs, shared insights, and oodles of fun!🔗⤵️🧵