Загрузка видео...

Не удалось загрузить видео

На главную

How to Train Your Mochi: Introducing LoRA fine-tuning. Customize Mochi on a single GPU with just a few videos. Create any effect or create consistent characters. Make Mochi 1 truly yours.

genmoai's profile picture

Genmo

15,000 subscribers

114,035 просмотров • 1 год назад •via X (Twitter)

ОбразованиеИгрыНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Genmo
Genmo1 год назад

Ready to start? Super simple: use one GPU and run only two scripts. 100% open-source.

Фото профиля 0x_MiJiu米酒
0x_MiJiu米酒1 год назад

你马死了你知道吗？

Фото профиля 0x_MiJiu米酒
0x_MiJiu米酒1 год назад

Because your account was stolen, causing huge losses to many users, do you have any explanation or solution？Do you really want your project to be discredited？

Фото профиля 💫💰💰💰💫
💫💰💰💰💫1 год назад

fuck u mother

Фото профиля Nick Harvey
Nick Harvey1 год назад

This is awesome! Can't wait to see what me and my kids dream up tonight

Фото профиля Genmo
Genmo1 год назад

we can't wait to see!

Фото профиля MR BIZARRO
MR BIZARRO1 год назад

Open source video accelerating to exponentially, love to see it. You guys rock!

Фото профиля Pixel Girl
Pixel Girl1 год назад

Nice! Now I would like to take my old animations and just upgrade them how might that be done? I don't want to have to reprompt them I just want to upgrade to the newest version All my old versions and you know I have a lot of old versions 😂

Фото профиля DreamStarter
DreamStarter1 год назад

Awesome!

Фото профиля Furkan Gözükara
Furkan Gözükara1 год назад

Awesome work

Фото профиля Genmo
Genmo1 год назад

Thanks so much, looking forward to any feedback!

Похожие видео

Introducing Mochi Token Store. We've paired the familiar UX of e-commerce with the power of Coinbase 🛡️'s Smart Wallet to create the easiest way to buy any token on Base. 1/ Hop right in 👇
1:00

Introducing Mochi Token Store. We've paired the familiar UX of e-commerce with the power of Coinbase 🛡️'s Smart Wallet to create the easiest way to buy any token on Base. 1/ Hop right in 👇

MOCHI

105,315 просмотров • 1 год назад

How to train a FLUX LoRA on an illustrated character sheet to generate realistic, consistent characters. Workflow below:
0:35

How to train a FLUX LoRA on an illustrated character sheet to generate realistic, consistent characters. Workflow below:

Heather Cooper

54,736 просмотров • 1 год назад

Less than 1 minute guide on how to train your own LoRA with LoRA Ease 🧞‍♂️⚡ Train high-quality LoRAs on objects 📦, faces 😊, styles 🎨 or characters 🧑‍🎤 effortlessly and super cheap ༄ ▶️
0:59

Less than 1 minute guide on how to train your own LoRA with LoRA Ease 🧞‍♂️⚡ Train high-quality LoRAs on objects 📦, faces 😊, styles 🎨 or characters 🧑‍🎤 effortlessly and super cheap ༄ ▶️

apolinario (poli)

90,980 просмотров • 2 лет назад

How to edit videos with a single sentence—and keep characters perfectly consistent ⬇️
0:57

How to edit videos with a single sentence—and keep characters perfectly consistent ⬇️

LovartAI

99,904 просмотров • 2 месяцев назад

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨
1:05

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨

Affogato AI

59,705 просмотров • 1 год назад

introducing LoRAs for Krea 2 (beta). our most powerful fine-tuning system to date; now you can train Krea 2 on a your own specific style, object, or character with incredible precision. learn how it works 👇
0:20

introducing LoRAs for Krea 2 (beta). our most powerful fine-tuning system to date; now you can train Krea 2 on a your own specific style, object, or character with incredible precision. learn how it works 👇

Krea

42,464 просмотров • 3 месяцев назад

Introducing 🎨 Design Systems in Stitch! Build a single source of truth to keep your screens visually consistent. Create your styles once, then instantly apply them to any new or existing designs. We’ve got more for design systems coming over the next few weeks, stay tuned! 👀
0:35

Introducing 🎨 Design Systems in Stitch! Build a single source of truth to keep your screens visually consistent. Create your styles once, then instantly apply them to any new or existing designs. We’ve got more for design systems coming over the next few weeks, stay tuned! 👀

Stitch by Google

294,057 просмотров • 6 месяцев назад

Just Recorded a 1-hour FULL Course on how to create STUNNING Animated websites with AI ❤️‍🔥You can literally make ANY Design with AI
1:25:06

Just Recorded a 1-hour FULL Course on how to create STUNNING Animated websites with AI ❤️‍🔥You can literally make ANY Design with AI

Viktor Oddy

55,785 просмотров • 6 месяцев назад

Finally built a workflow to create full comedy sitcoms with AI. Consistent characters. Consistent voices. Any length. Can’t wait to teach you all!! Waitlist below 👇
0:51

Finally built a workflow to create full comedy sitcoms with AI. Consistent characters. Consistent voices. Any length. Can’t wait to teach you all!! Waitlist below 👇

Framer 🇱🇹

190,042 просмотров • 9 месяцев назад

Koyal (koyal.ai (YC F25)) is an agentic AI Filmmaking platform that helps you create cinematic videos with consistent characters, settings, and storylines. It turns music, podcasts, and narration into short-form videos and full episodes with tooling to customize any detail.
2:09

Koyal (koyal.ai (YC F25)) is an agentic AI Filmmaking platform that helps you create cinematic videos with consistent characters, settings, and storylines. It turns music, podcasts, and narration into short-form videos and full episodes with tooling to customize any detail.

Y Combinator

24,261 просмотров • 10 месяцев назад

How To Use Google Flow to Create Consistent AI Characters & Videos | Full Tutorial for Beginners. In this video, you'll learn how to create consistent AI characters, generate images and videos with Nano Banana and Gemini Omni Flash, use Frames and Ingredients, and build longer AI video scenes while keeping character consistency across different shots. This information is for both new and existing Youtube creators, who want to learn how to create consistent characters for your story scenes. Like, Retweet and Bookmark. Follow BIG CHRIS
9:25

How To Use Google Flow to Create Consistent AI Characters & Videos | Full Tutorial for Beginners. In this video, you'll learn how to create consistent AI characters, generate images and videos with Nano Banana and Gemini Omni Flash, use Frames and Ingredients, and build longer AI video scenes while keeping character consistency across different shots. This information is for both new and existing Youtube creators, who want to learn how to create consistent characters for your story scenes. Like, Retweet and Bookmark. Follow BIG CHRIS

BIG CHRIS

12,474 просмотров • 2 месяцев назад

✨ 🖼️ Generate images with consistent characters without any fine tuning nor training. Consistory is a training-free approach to maintaining subject consistency between text-to-image generations on pretrained models. #NVIDIAResearch 🎨 Test it here:
2:36

✨ 🖼️ Generate images with consistent characters without any fine tuning nor training. Consistory is a training-free approach to maintaining subject consistency between text-to-image generations on pretrained models. #NVIDIAResearch 🎨 Test it here:

NVIDIA AI Developer

11,612 просмотров • 1 год назад

Make your game wishes real 🎮 create games with a single prompt Just use Neon Make.
0:39

Make your game wishes real 🎮 create games with a single prompt Just use Neon Make.

Opera

95,407 просмотров • 10 месяцев назад

Introducing Move One, an easy way to capture and create 3D animations with just a phone #MadeWithMove 🎥 Capture motion anywhere with a single camera ⚡️ Get your data back in minutes 🤖 Animate 3D characters Try for free👇
0:21

Introducing Move One, an easy way to capture and create 3D animations with just a phone #MadeWithMove 🎥 Capture motion anywhere with a single camera ⚡️ Get your data back in minutes 🤖 Animate 3D characters Try for free👇

Move AI

67,559 просмотров • 2 лет назад

introducing gpuup: you no longer have to put any effort into setting up CUDA toolkit + drivers on a node (single or multi gpu). just copy paste a short command (in replies)
0:37

introducing gpuup: you no longer have to put any effort into setting up CUDA toolkit + drivers on a node (single or multi gpu). just copy paste a short command (in replies)

Elliot Arledge

52,976 просмотров • 10 месяцев назад

What is PlayerZero? Imagine a single avatar that’s uniquely yours, everywhere. Then power it with a collectibles platform that lets you create, customize, & evolve your digital identity across virtual worlds & games. Here’s how it works 🔽
0:36

What is PlayerZero? Imagine a single avatar that’s uniquely yours, everywhere. Then power it with a collectibles platform that lets you create, customize, & evolve your digital identity across virtual worlds & games. Here’s how it works 🔽

PlayerZero

30,990 просмотров • 1 год назад

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.
0:30

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

22,200 просмотров • 1 месяц назад

Characters that truly come to life. With Akool’s Video Generator, you can now create videos where characters display a full range of natural facial expressions from subtle emotions to dramatic reactions. Whether you’re telling a story, creating marketing content, or building virtual presenters, your characters can now express emotions just like real people. Bring personality, emotion, and realism into every video, all powered by AI. Create more engaging content with Akool’s Video Generator.
0:25

Characters that truly come to life. With Akool’s Video Generator, you can now create videos where characters display a full range of natural facial expressions from subtle emotions to dramatic reactions. Whether you’re telling a story, creating marketing content, or building virtual presenters, your characters can now express emotions just like real people. Bring personality, emotion, and realism into every video, all powered by AI. Create more engaging content with Akool’s Video Generator.

Akool Inc

7,722,889 просмотров • 5 месяцев назад