Introducing Replay v0.2 with a new image-to-video mode.
What’s new?
1) Prompting with an image
2) 3x longer AI video
3) 2.7x higher resolution
Available today. Share your Replay creation below 👇
Announcing Genmo Chat, a creative copilot that uses GPT-4 and a large suite of generative AI tools to create and then edit any video or image you ask for.
💬 "Help me direct a short movie Snack to the Future"
➡️ 📽️ creates a fully edited 30 second trailer
Generative video models are rapidly improving in quality. Meet Replay, a new AI model that can generate stunning videos from text.
Replay v0.1 is designed to create ultrasmooth HD videos with a new interface. Available today for everyone.
What's New?
1. Replay understands plain…
Announcing Genmo Video, a generative media platform with a new text-to-video model that can generate immersive live artwork from any prompt or any image.
What will you create? 🎨▶️
Free public access:
Discord:
👇1/n
Genmo Chat just got a big upgrade. Generate 3D meshes and 360 degree videos from text.
Upload anything (image or prompt) and get a 3D object. It's ready for export to Blender or ARKit (GLB).
Find your creative AI agent at
Image Blending is now live on Genmo Chat. Combine any number of image and text prompts into a blended image.
Baby + Yoda = ?
Abe Lincoln + Gotham City = ?
Knight + Spaceship = ?
Dog + Cactus = ?
Sign up at
Diffusion for virtual worlds: we've trained a new model to create 3D objects from text. And it's 50x faster than any alternative.
We made each of these cute characters in just one minute with Genmo's new text-to-3D model.
Build your own world at
Camera movement drives emotion, pace, and mood in filmmaking.
Announcing Replay Camera Controls. Starting today, zoom, pan, roll and tilt the virtual camera to render gorgeous, swooping effects. 💫
Yesterday, you met Replay, our new, ultra-crisp video model. Now, take even more…
AI just learned to draw better ✏️
Introducing our upgraded V3 image generator
Type in an idea and Genmo Chat will help you with the rest, including automatic prompt engineering
Join the waitlist at
Under the hood, Genmo works by combining GPT-4 with a toolbox of 8+ generative models including our V2 image and video generators and open source models. Our aligned tool director sets dozens of model hyperparameters automatically.
Genmo Chat enables anybody to use generative AI tools with zero friction. It’s trained to proactively ask for feedback to improve your generations. Creation with Genmo Chat feels like collaborating with a colleague in Slack or Figma.
💬 "Make app icons for a creative copilot"
We've put out a blog post describing the new features in Replay v0.2, including image prompts, and some tips for getting the best results. Check it out if you missed our Twitter announcement yesterday.
Replay now suggests follow-up prompts after every video you create.
Just like DALL-E 3, riff on ideas with our AI copilot. Suggestions are rolling out now - never have writer’s block again.
🧑🎨 “A close up of an astronaut in orbit viewing the aurora” ⤵️
✨ “Close-up of a space…
Replace parts of images and ideate with the agent to accelerate your creative process. Fix mistakes just by asking.
💬 "Replace the hat with four different options"
Genmo Chat is a prototype of our approach to creative general intelligence where a human and a generative model work together seamlessly. With human collaboration, the results are more creative than generative models can achieve by themselves.
💬 "Godfather: The Lunar Family"
"a painting of flowers and trees in a field. flower, plant, sky, cloud, plant community, light, leaf, natural landscape, natural environment, people in nature"
By WhiteHawk
Replay now streams AI-generated videos for fast iteration. Your clips will start rendering and streaming almost as soon as you click "submit".
Genmo's infrastructure ships pixels straight off the GPU to your computer screen 📦
We're previewing Replay FX Pack 2. FX was a new way to control dynamic patterns in your AI videos for mesmerizing effects.
FX Pack 2 is another set of presets:
💓 Heartbeat (our favorite)
✨ Stars
🔹 Ninja
🌀 Spiral
*️⃣ Whirls
⚞ Tunnel
Try out the new video effects today on…
All over the world, people are creating **incredible** art with Genmo
Learn how to make:
3D assets 🧊 Animations and videos 🎥 Images 🖼️ and more
For inspiration, start with . What will you imagine?
🖼️ Hot off the presses: V2 image generation! We've been hard at work on Genmo's new text-to-image model. It generates gorgeous 1024x1024 pictures, with improved coherence and style.
Check out our community's results at . Who wants access?
Genmo text-to-video
Text prompts + camera motion
1) aerial view of a cosy cottage, snow fall, christmas
2) christmas tree in a cosy cottage
3) long hallway, cosy cottage, christmas decorations
4) top view, celebratory meal, dinner table, cosy cottage, christmas
5) Full moon,…
Go beyond 2D image generation. Start with a prompt or a photograph and create beautiful, funny and creative animations. 💬→ 🎥
For example, Genmo made this anime-style generation, “black and white pen and ink. Johnny Depp x Ryan Gosling”
2/n
Genmo Replay now understands Japanese prompts.
Genmo Replayが日本語を理解するようになりました!にアクセスして、"王冠をかぶったカエル"からビデオを作成してください。1分後に、あなたのプロンプトからAIビデオを見ることができます!
We'll have a deeper dive soon…
@vkuoo
The artist created a helpful overview of Replay's "preserve" parameter. At high preserve values, Replay will more strongly use the uploaded image. At lower values, you can change the text prompt to alter the visual appearance of your video.
Comparing videos generated from the same image with different 'Preserve' parameters and prompts, currently,
#Genmo
doesn't have a seed number. If it had a seed number, there might be even more control.
@genmoai
This is a fun and easy UI for videos. You can sign up to be invited at
It's in alpha so wondering how much they'll charge later to get rid of the watermark ... but seriously, easy to understand controls and the option to add multiple prompts
@genmoai
Our community of artists, architects, directors, game designers and more have been creating some incredible Gens.
By
@WillowmoonArt
, “wolf, colorful”
5/n
We're holding office hours today at 2pm PT/5pm ET in our Discord server!
Join the discord at , or click the event link here to join & receive a reminder about the event when it starts🙌
Having a blast in New Orleans! Crazy to think that we presented DDPM as a virtual poster just 3 years ago at NeurIPS 2020. In person food is much better 😋 Check out these beignets I made in a few minutes on Genmo.
Come find / DM me to chat about big diffusion models for video.…
Interested in Genmo's direction or want the opportunity to ask questions and receive answers live? Join us at 6pm ET today for our community office hours!
Genmo is free to use. We’re rapidly adding people from the waitlist as fast as we can add GPU capacity today.
Create video now:
Discord:
Genmo, from
@ajayj_
and
@_parasj
7/7
Just played with
@genmoai
's Replay v0.2 and I’m impressed.
This free AI video tool generates 1080p videos up to 6 seconds (longer than Pika & Runway’s default).
Plus, you can make up to 3 videos at once – with live previews!
6 more awesome clips below + how to access it 🧵
Genmo Chat just got a big upgrade. Generate 3D meshes and 360 degree videos from text.
Upload anything (image or prompt) and get a 3D object. It's ready for export to Blender or ARKit (GLB).
Find your creative AI agent at
@ProperPrompter
@MagikChance
We're working to improve it rapidly! We have batch mode where you can create 3 videos with one click. This should help you iterate faster to find good examples.
Thank you
@genmoai
for the private beta access to the new feature - Genmo Replay video. Love that it allows us to create smooth and coherent motion. The quality is insane.
Music by
@mytracksy
We've released a sheet for our users to access and leave feedback for us 🎉
Join us and help us steer our (metaphorical) ship in the right direction for 2024!
@0x_Vivek
Absolutely. Genmo is an AI collaborator that works with users to ideate, create and edit visual content across formats. Today, we allow users to make images, videos, animations and 3D meshes in an intuitive interface, for free.
For teams and commercial use, consider our Turbo…
We've used
@Cloudflare
R2 + Workers from day 1 for
@genmoai
. Our launch yesterday was so explosive that
@Cloudflare
just banned our account.
Users: all of your content is safe
Support confirmed this is a mistake but cannot fix it. Case ID 2749735
@eastdakota
@jgrahamc
@zatlyn
@WilliamLamkin
Users get free unlimited generations right now -- they just queue up after you run out of fast fuel for the day. So 20-40 seconds of video in fast mode per day, unlimited after that ⛽️