In this video, we take a look at the latest SOTA video-generation software, WAN2.1. And yes, it’s as good as you’ve heard! Rocking both text-to-video and image-to-video faster and with higher quality than Hunyuan! Plus, by using the quantized models from Kijai and following these step-by-step ComfyUI installation instructions, you'll be generating content in no time at all. It’s available for systems with as little as 12GB of RAM (but we recommend 16GB–24GB for optimal performance).
2025-02-28 15:53:25 +0000 UTC
View Post
Hey guys! Wanting to tailor this a bit more to what the community is looking for.. This is your chance to be heard!
There are two questions below so pick multiple items to let me know your thoughts!
2025-02-28 12:38:02 +0000 UTC
View Post
Multi-robot collaboration,Grok 3 , smallest video language model, Generative AI Model for Gameplay, AI co-scientist, Mistral Saba, Fiverr Go, Step-Video-T2V and Step-Audio, Pikaswaps & more...
(This podcast was made with Google Notebook LLM from original content by: Diffusion Digest)
Be sure to support them and sign up for the digital digest at: https://diffusiondigest.beehiiv.com/
2025-02-28 12:27:30 +0000 UTC
View Post
OpenAI is finally making its video generation model, Sora, available to users in the European Union, the U.K., Switzerland, Norway, Liechtenstein and Iceland.
The company said on Friday that ChatGPT Plus and Pro subscribers in these regions will be abl...
2025-02-28 12:25:03 +0000 UTC
View Post
UPDATED Guys! So excited for this drop. The wan2.1 is everything you hoped it would be. Amazing graphics. motion, and flow. Includes is a QWEN Prompt Enhancer (high resource use).
We've updated the gradio app to work with the t2v 1.3b, 14b, and the i2v 14b 480p. It is not as fast as ComfyUI but will get the job done!
PROMPT ENHANCER INCLUDED!
For the full package (t2v, i2v, and v2v) check out the quantized versions for ComfyUI: 2025-02-28 02:43:29 +0000 UTC
View Post
Guys! So excited for this drop. The wan2.1 is everything you hoped it would be. Amazing graphics. motion, and flow. On top of that its quantized, which means you can run this with 16gb!
Text to Video
Image to Video
Video to Video
The ComfyUI model manager works with both the portable and manual ComfyUI installations. Workflows included!
FREE FOR ALL FARM HAND MEMBERS AND ABOVE
Ins...
2025-02-27 05:21:21 +0000 UTC
View Post
Hey everyone! Wanted to let you know that we've made changes to the comfyUI manual installation that we offer you all: particularly the CUDA 12 version.
The biggest change is that we've moved from a python virtual environment (venv) to that of a conda environment. The reason and benefits behind this are as follow:
This is a 1.3b parameter model and took about 4-5 minutes to generate on a 4090
2025-02-25 23:13:54 +0000 UTC
View Post
Welcome to Comfy Tutorials! In this video, we’ll introduce you to ComfyUI nodes—the building blocks of creating powerful AI workflows. We’ll guide you step-by-step through what nodes are, how they work, and how to use them to design your own image-processing pipelines. Along the way, we’ll help you comprehend the basics of classes in Python, explaining them in simple terms, and introduce you to a new word—instantiation—to better understand how nodes are created and used. Whether y...
2025-02-25 21:20:25 +0000 UTC
View Post
And You Can Do it Too!
Tools Used: Flux, Zonos, MemoAvatar
Memo-Avatar: https://www.patreon.com/posts/memo-avatar-best-122871739
Open-Source Scripts: Cognibuild.ai
Website: getgoingfast.pro
2025-02-25 06:02:37 +0000 UTC
View Post
🎭✨ Imagine bringing any character to life with seamless, ultra-expressive lip-syncing. That’s exactly what Memo-Avatar does—the most advanced open-source lip-syncing model we’ve ever used!
What sets it apart? It's expressiveness and lifelike movements! As well, unlike other tools that struggle with short phrases, Memo-Avatar can process several minutes of text at once, ensuring smooth, natural movement that keeps up with long conversations or monologues. Whether you’re crea...
2025-02-23 21:59:46 +0000 UTC
View Post
And You Can Do it Too!
Memo-Avatar: https://www.patreon.com/posts/memo-avatar-best-122871739
Open-Source Scripts: Cognibuild.ai
Website: getgoingfast.pro
Music: Whiskey & Warning Signs
Available on all Major Streaming Platforms
2025-02-23 20:23:32 +0000 UTC
View Post
With apologies, I had forgotten to add the gradio app to the installer. If this is the problem, simply delete the install folder (save your models if necessary) and run the installer again.
*Note: you dont need to run the entire installer again: let it run and you will see a file download. Once it has downloaded, you can exit the installer.
Thanks!
2025-02-23 19:37:03 +0000 UTC
View Post
And You Can Do it Too!
Tools Used: Flux, Zonos, MemoAvatar
Memo-Avatar: https://www.patreon.com/posts/memo-avatar-best-122871739
Open-Source Scripts: Cognibuild.ai
Website: getgoingfast.pro
2025-02-22 22:21:39 +0000 UTC
View Post
We’re thrilled to introduce the BEST open-source lip-syncing software to date! 🎭✨ This cutting-edge model is not only the most expressive we’ve ever used, but it can also process several minutes of text at a time—bringing characters to life like never before!
When combined with Flux for high-quality image generation and Zonos for natural-sounding text-to-speech, you get a fully integrated animation powe...
2025-02-22 20:58:50 +0000 UTC
View Post
🚀 Exciting News! 🚀
We’re thrilled to introduce the BEST open-source lip-syncing software to date! 🎭✨ This cutting-edge model is not only the most expressive we’ve ever used, but it can also process several minutes of text at a time—bringing characters to life like never before!
When combined with Flux for high-quality image generation and Zonos for natural-sounding text-to-spee...
2025-02-22 20:54:04 +0000 UTC
View Post
SANA IS NOW AVAILABE FOR WINDOWS!! – easily one of the most underrated applications of the year, the text-to-image tool that brings creativity to everyone, no matter your hardware! With versions tailored to different GPUs, Sana delivers stunning visuals up to 4096×4096 resolution, faster and more efficiently than ever.
Your Choice, Your Power:
🌟 Sana-1.6M: Perfect for GPUs with 12GB of VRAM, delivering high-quality images quickly and smoothly.
🌟 Sana-6M: Designed f...
2025-02-20 15:00:11 +0000 UTC
View Post
SANA IS NOW AVAILABE FOR WINDOWS!! – easily one of the most underrated applications of the year, the text-to-image tool that brings creativity to everyone, no matter your hardware! With versions tailored to different GPUs, Sana delivers stunning visuals up to 4096×4096 resolution, faster and more efficiently than ever.
Your Choice, Your Power:
🌟 Sana-1.6M: Perfect for GPUs with 12GB of VRAM, delivering high-quality images quickly an...
2025-02-20 01:56:53 +0000 UTC
View Post
OpenAI is changing how it trains AI models to explicitly embrace “intellectual freedom … no matter how challenging or controversial a topic may be,” the company says in a new policy.
As a result, ChatGPT will eventually be able to answer more questions, offer more perspectives, and reduce the number of topics the AI chatbot won’t talk about.
....
On Wednesday, OpenAI announced an update to its Model Spec, a 187-page document that lays ...
2025-02-19 13:43:14 +0000 UTC
View Post
And You Can Do it Too!
Open-Source Scripts: Cognibuild.ai
Website: getgoingfast.pro
Music: Dr. Period
Song: Money
Website: www.daysinging.com
2025-02-19 06:32:17 +0000 UTC
View Post
Grok 3 is leading the way!
2025-02-18 05:01:06 +0000 UTC
View Post
Zonos-v0.1 is the most refined open-weight text-to-speech model yet, trained on over 200,000 hours of multilingual speech. It delivers expressiveness and clarity that can possibly rival top commercial TTS providers. With just a few seconds of reference audio, Zonos can accurately mimic voices, capturing subtle inflections, tone shifts, and emotional nuance.
Unlike more accessible tools like f5-tts-plus, Zonos requires a WSL setup, but the tradeoff is higher-quality output with fine cont...
2025-02-18 04:55:21 +0000 UTC
View Post
Good news! Zonos is now able to be installed directly in your Windows Environment! Enjoy the groundbreaking text-to-audio software without the need for the WSL!
The installed can be found here
FREE FOR ALL FARM HAND MEMBERS
2025-02-18 02:25:09 +0000 UTC
View Post
In this video, we’re upgrading from CUDA 11.8 (or other versions) to 12.8 with a clean installation. While 11.8 has been a solid choice for the majority of open-source AI software we’ve been using, the time has come for a change. More and more newer applications are starting to require CUDA 12.8, and we’re here to make sure your system is ready for that shift.
The benefits include a lesser reliance on WSL.
This isn’t just a quick update—it’s a precise process. We’ll ...
2025-02-18 00:22:04 +0000 UTC
View Post
(This podcast was made with Google Notebook LLM from original content by: Diffusion Digest)
Be sure to support them and sign up for the digital digest at: https://diffusiondigest.beehiiv.com/
https://aibrews.substack.com/
2025-02-17 20:26:58 +0000 UTC
View Post
This was all made with getGoingFast open-source scripts. And you can do it too!e
2025-02-16 22:57:02 +0000 UTC
View Post
Single: Whiskey and Warning Signs
Band: Jim Day & the Better Stories
Produced: Jim Day
Website: www.daysinging.com
Single can be bought at:
https://jimday.bandcamp.com/track/whiskey-and-warning-signs
All rights reserved @Jim Day & the Better Stories
Lyrics:
(Verse 1)
I shoul...
2025-02-15 23:13:36 +0000 UTC
View Post
For this Valentines Day we encourage you to take care of the one you love... your AI System. Using a tongue-in-cheek metaphor of a relationship we talk about why quick-fix solutions like Pinokio are not helpful and cause more harm to your hobby than they do help. In short, take care of your system, avoid the pitfalls of too-good-to-be-true solutions, and your hobby will be much more fulfilling.
********************************
Membership & Intstallers: 2025-02-15 07:13:21 +0000 UTC
View Post
"The richest man in the world and a group of private equity and venture investors made an unsolicited offer for the nonprofit that controls OpenAI, led by Elon Musk’s former friend and business partner Sam Altman. But there are strings attached to the deal; Musk wants Altman to abandon a restructuring plan that would make the ChatGPT developer a for-profit business."
Read the rest online
2025-02-15 04:23:59 +0000 UTC
View Post
Zonos-v0.1 is the most refined open-weight text-to-speech model yet, trained on over 200,000 hours of multilingual speech. It delivers expressiveness and clarity that can possibly rival top commercial TTS providers. With just a few seconds of reference audio, Zonos can accurately mimic voices, capturing subtle inflections, tone shifts, and emotional nuance.
Unlike more accessible tools like f5-tts-plus, Zonos requires a WSL setup, but the tradeoff is higher-quality output with fine cont...
2025-02-14 03:36:36 +0000 UTC
View Post
