Genmo

Mochi 1, the SOTA open-source video generation model. We're hiring:

[Genmo @genmoai]

Introducing Mochi 1 preview. A new SOTA in open-source video generation. Apache 2.0.

magnet:?xt=urn:btih:441da1af7a16bcaa4f556964f8028d7113d21cbb&dn=weights&tr=udp://tracker.opentrackr.org:1337/announce

[Ronald van Loon @Ronald_vanLoon]

What if video AI finally felt real?

For years, we’ve seen “AI video” that looked more like animated slideshows — stilted motion, broken physics, and prompts that miss the mark.

That just changed.

Mochi 1 from @genmoai is an open-source breakthrough in video generation — and it solves 3 barriers that have held AI back for years:

➤ Motion realism → Models now generate 30 FPS clips with fluid, physics-aware movement. Water flows, fur ripples, dancers move like humans.

➤ Prompt precision → It listens to creative direction — from dragons to city streets, outputs finally align with intent.

➤ Accessibility → It’s open-source under Apache 2.0. No gatekeeping. Anyone can build on it.

This isn’t just prettier video.
It’s the moment AI starts understanding how the world moves.

Don't miss out on the latest AI advancements! Sign up here to stay informed! https://t.co/t9RuioDLt9

[𝐙𝐞𝐧𝐠 💜 @zeng_wt]

Generated with Mochi from @genmoai

[ANKIT PATEL 🇮🇳 | AI @Ankit_patel211]

More Nature Sunlight 🌞 testing in @genmoai

Improved Mochi Model

[ANKIT PATEL 🇮🇳 | AI @Ankit_patel211]

New updated Mochi flourish aniamtion and cinematic lighting! @genmoai

Nature sun LIGHT test are so impressive and foot movement too. ☀️

[𝐙𝐞𝐧𝐠 💜 @zeng_wt]

Mochi from @genmoai is back with an updated model.
They called it a small update, but I think it's huge! ✨

The video quality is excellent, with natural, realistic movement.

The barista's milk pour is 99% accurate to real latte art, and the foam's movement, pushing the crema aside, is impressive!

[Brent Lynch @BrentLynch]

SURPRISE! GENMO Mochi is back y'all!

A big improvement over their older model.

bright social media video, roller coaster car that says "MOCHI" plunging down a steep drop, then whipping around sharp turns, with two attractive adult female women in intricate outfits and their pet black cat. COHERENT I IMAX CLARITY, CRISP, VIVID.

[Genmo @genmoai]

Do more with Mochi 🎬
We've pushed a small update to Mochi; allowing your creativity to flourish with this tiny tune up!
Post your new generations in the quotes or comments 👀 We love to see them!

[Genmo @genmoai]

Built on Mochi 1 by our friends at @getcaptionsapp!

[Mirage @trymirage]

Read the full report here:

https://t.co/PmEJ0QtB5Z

[Genmo @genmoai]

We collaborated with @ywen99 and @PandaAshwinee on this exciting project extending the capabilities of Mochi 1. Check it out!

[Ashwinee Panda @PandaAshwinee]

fine-grained editing of videos is hard. if I use a Video Diffusion Transformer to make my videos, just adding "red" to the prompt totally changes the video. in our new paper, we dive deep into the attention maps of VDiTs and find a way to do fine-grained editing, and other stuff!

[Genmo @genmoai]

Take a look at this! With Mochi 1 as a base model; this fine tunes and unlocks image-to-video, keyframes, and longer videos! 👀

[Yaofang Liu @stephenajason]

Never seen a R1 moment in video diffusion models??😰Can't things just emerge using very low cost??🧐Certainly can!!!!

🚀 Introducing Pusa now!
Pusa: Thousands Timesteps Video Diffusion Model — A ​​single model​​ that unlocks:
Text-to-Video​​ → ​​
• Image-to-Video​​
​​• Start/End Frames to Video
• Video Transitions
• Video Extensions​​
• Next-frame prediction​​
​​• Novel sampling algorithms(frame-independent noise)​
• ...
Also note that the model still can do text-to-video generation!!
All for just ~$0.1k training cost (about 100 H800 GPU hours)!​

🔍 ​​Key Innovations:​​
​​- Frame-level noise control​​ (FVDM-inspired) → Unmatched flexibility
​​- Non-destructive adaptation​​ → Preserves base T2V capabilities
​​- Universal methodology​​ → Applicable to other SOTA models (e.g., Wan2.1, Hunyuan Video)

💡 ​​100% Open-source​​—code, data, and training scripts ​​release today!​​

📽 ​​Demos and details below ↓​

#AI #VideoGen #OpenSource

[Genmo @genmoai]

Incredible work! 🤩

[Susung Hong @SusungHong]

Text-to-video models are silent🔇, but does that mean they don't know music, beat, and tempo🎶?

I'm excited to present MusicInfuser🎹, an adapter network which aligns silent dancing videos to music.

Check out our paper, examples, code, and weights here: https://t.co/6jvEb9H40x

[Genmo @genmoai]

Happy St. Paddy's Day to all who enjoy!
All videos made with Genmo on Mochi v1 🍀

[ANKIT PATEL 🇮🇳 | AI @Ankit_patel211]

T2V-Model in @genmoai

[こば@AIBridge Lab @doerstokyo342]

Mochi-1(@genmoai )でユニークなシーンが作れたのでプロンプトをシェアします🎥

Prompt:瞑想からトランジションシーン
young monk in meditation, temple surroundings gradually dissolving into light, consciousness expansion visualization, physical space morphing into abstract luminous realm, temple outlines melting into radiant energy, slow ethereal transition, face remaining centered as world transforms around, dimensional shift effect, red and gold essence persisting through transformation

トランジションから山に映るシーン
monk's consciousness expanding into grand Himalayan mountains, abstract luminous realm materializing into snow-covered peaks, aerial perspective gradually widening, morning sunlight cresting over mountaintops, vibrant blue sky with pristine white clouds, monk's essence merging with vast natural landscape, spiritual unity visualization, meditative awakening, majestic scale reveal

#genmo #mochi

[𝐙𝐞𝐧𝐠 💜 @zeng_wt]

It’s the weekend, so I made this chill AI lo-fi music video with @genmoai ’s text-to-video tool.
Just a little something to help you unwind, relax, and shake off the week’s stress.
Kick back and enjoy! 💜

[Genmo @genmoai]

The first Genmo offsite of 2025 ✅

We brought the team together for an incredible three-day retreat in Calistoga! From exploring a beautiful winery and enjoying amazing dinners to board games and relaxing spas, it was the perfect way to unwind and reflect on our goals for this upcoming year 😌

We’ve had a busy start to 2025—and we’re still hiring across all teams ✨

Join us 🥂

[こば@AIBridge Lab @doerstokyo342]

🐱Mochi-1(@genmoai )で生成した15秒の動画に
MMAudioとFilmoraのAIオーディオで効果音とBGMを追加

どちらのツールも動画のシーンが切り替わっても全体を通して一括で音付けしてくれるのが楽ですね！
#genmoai #mochi

[ANKIT PATEL 🇮🇳 | AI @Ankit_patel211]

T2V Model in @genmoai

Mochi Maker

Candy Love

[jamie @jamiebaooo]

a cozy video i made back in november that i never got to share! all videos were made with @genmoai , of course :)