Silent Snow

YouTube: https://youtu.be/vn0EnhevQDk Hey everyone! Bria just dropped Fibo 2, and right now it's ranked the #1 open-weights image editing model on Artificial Analysis. Even better, it runs completely locally on as little as 8GB of VRAM! Fibo 2 comes in two versions: Fibo 2 Dev: text-to-image and ima

Hey everybody, I think on this channel we usually talk about more fun stuff in regard to AI but I've always said that I do believe, in the long run, AI in the hands of humans as a whole will be more bad than it is good. And recently, that perspective is shifting to include independently adapting age

YouTube: https://youtu.be/cXaK5TddlA8 Hey everyone! First and foremost, before we get into the AI conversation of the day, I wanted to take a moment to update on where I've been, and where I'm going. For the last 8 weeks or so, I've been out and about with very little access to my computer. I've act

Hey everyone! Attached is our adapted version of the ComfyUI MiniMax H3 template. This workflow is very similar to the base template provided by Comfy, but adds a few additional elements identified by the community to help speed up and manage generation times. Before you can use the workflow, you'll

Hey everyone! Just wanted to come out and announce that the NSFW course is officially here! This is an addon to the SFW course and treats the SFW course as a prerequisite. For those who just need NSFW, everything you need is in the NSFW course, but we would highly encourage checking out SFW first. T

Hey everyone! The first part of the AI influencer course is FINALLY finished! This is the SFW course focused specifically on understanding the AI influencer landscape, strategies, information to know, workflows, tools, and more! See the breakdown and everything included below! Skool Link: https://ww

This is just a sneak peak at everything we've talked about with AI influencers. Want the full course? Check out the link below! https://www.skool.com/silent-snow-ai-influencers-6472 It's quite unfortunate to be making this right after the launch of the SFW AI Influencer course, but my job is to keep

Hey guys! We recently talked about how powerful Ideogram 4 character LoRas seem to be. I still stand by that claim, but with Krea 2 being released open source as well, I wanted to spend some time putting the two models head to head, and I was honestly shocked at how much it impressed me! I think tha

YouTube: https://youtu.be/18TZKLavetw Custom GPT for Prompting: https://chatgpt.com/g/g-6a30936d691881918f794fdfaebddc35-ideogram-4-lora-prompter Hey everybody! Ideogram 4 has been the talk of the town lately and, if you're anything like me, you probably ignored it for a little while because of the

Opening up to paid members first, then free members soon! I've heard a lot of good stuff about the GPT-2 Image model and, I had a rough start at first, but I was able to figure out how to make the most of it for AI influencer style content! To help, I've made a Free GPT available to anyone with an O

Hey everyone! With the world as it is (as an American, so sorry to literally everyone everywhere) I just needed to step away from the constant speed and work on something I've really wanted to work on - something fun. Since I was a kid, I've always loved music. I remember getting my first IPod touch

YouTube: https://youtu.be/qTNPQPOFjok Hey everyone! Stumbled across this really cool tool developed by Matteo, the original creator of IPAdapter which was popular back in the AUTO1111 days. GitHub Repo: GitHub - cubiq/ComfyUI_FaceAnalysis: Extension for ComfyUI to evaluate the similarity between two

YouTube Link: https://youtu.be/koHbTAXVM8c Hey everyone! LTX 2.3 by Lightricks dropped yesterday, and I spent some time putting usable workflows together and doing some basic tests. Here are some of the generations I was able to get out of LTX 2.3 entirely locally! A couple notes on these generation

YouTube Link: https://youtu.be/zvryriYLdhY The three image model in Google's line of Nano Banana image generation models has arrived! The question is, is it better than it's predecessor, Nano Banana Pro? In this video, we show you how to get Nano Banana 2 inside of ComfyUI, as well as a handful of t

Hey everyone! Big announcement for both Free and Paid members! I've tried to include all information here, but please reach out with any questions! Today, we’re introducing a new paid tier to the Patreon – The Alchemist as well as our Discord channel! Here is the summary, but read on for more detail

YouTube Video: https://youtu.be/NNW-UYAmvOs Hi everyone! I'm putting together a couple videos on OpenClaw/Clawdbot, and in that process I wanted to see if it could complete a task that I have been dreading doing myself for months. As the AI space continues to expand with new models on a weekly if no

Youtube Video: https://youtu.be/fQadB_s-UV0 Hi everyone! Here is the open-source free version of our newest master skin refiner workflow! As mentioned, this is a lighter version of the full workflow. While it does do the job and still makes an impact, especially for really plastic looking images, I

YouTube Video: https://youtu.be/921EUQxYl3Y Hi everyone! Here is the free version of the anime character sheet creator workflows. As mentioned in the video, this is not the master workflow, it's the broken down variation of it. What I will say is that the master workflow can be manually constructed

YouTube Video: https://youtu.be/1K8aemA8szE Hello everyone! Merry Christmas and happy early New Year to all who celebrate! Wishing everyone the very best this new year! The brand new Qwen Image Edit 2511 model just dropped and, like it's predecessor QIE 2509, is a mostly great alternative to Nano Ba

Good morning, afternoon, or evening everyone! We're very excited to officially announce the open public access to Silent Snow AI! Click the link below to make your account and get your free credits! New users get 100 credits (up from 45) until January 1st! silentsnow.net We wanted to give a special

Wanted to do a short post on Flux 2 within the context of all the other models we are seeing right now. In short, the answer to this question is, maybe. Flux 2 comes in at a whopping 60+ gigs base model and 30+ gigs for it's fp8 counterpart, not even to mention the text encoder sitting at 18 gigs in

YouTube Video: https://youtu.be/4gC4zAHFk0s Hi everyone! As I'm sure we've all heard, Nano Banana Pro is absolutely insane! Today, ComfyUI officially released native support for the model inside of Comfy, meaning we can now leverage the full force of Nano Banana Pro and Gemini 3 (great for auto prom

Hi everybody! Short update post here: Firstly, I won't lie, it's been hectic. So much work with the platform and thank you all for your support and continued testing for those in the beta round. Not to mention, AI seems to have had another explosive period. We have a ton we want to talk about and a

For the last couple of days, I've been messing around a bit with Mocha, the newest development in video character replacement, but as we've seen from across the internet, not just character replacement. When Wan animate first came out, don't get me wrong, it did (and does) a great job when used corr

Watch on YouTube for chapters and HD!: https://youtu.be/rDDqy2ocgT4 This is going to be quite a long post - buckle up. I wanted to start this off by saying thank you to each and every single one of you. Most of you are here from the original skin refiner workflows and, through the ups and downs, err

As AI search says, "AI never sleeps". Just a few weeks ago, we talked about how to access Nano Banana inside of ComfyUI to access direct API pricing rather than paying through online platforms offering the model at an upcharge. A few days later, ByteDance comes on to the scene with Seedream 4.0 to c

The wait is over, the mysterious Nano Banana has finally been revealed as Google's latest model, Gemini Image 2.5, and here's how you can access it in ComfyUI! How to Run Nano Banana in Comfy 1.) First, boot up ComfyUI. Go to your manager and click "Update All". Once the update has completed, return

Absolutely not. And after I tested myself, this statement is laughable at best. When talking about skin specifically, this model is comparable to GPT 4o. I think all this hype around the Krea model and skin texture can be summed up into this quote by Henry Ford: "If I asked people what they wanted,

Wan 2.2 is absolutely INSANE! Of course, with some caveats. The newest addition to the Wan family takes an interesting approach to video generations. In order to use the Wan 2.2 model, you'll need to download two different models, the "high noise" and "low noise" models. The good news is that these

If you're really into the AI space, you've probably heard the crazy recent discovery in regard to Wan 2.1, but if you haven't - allow us to break it down! Wan 2.1, the break through open-source video model released nearly 6 months ago was recently leveraged to generate just 1 frame (a single image)

Good morning everyone! We wanted to bring to attention a rather unknown update in the AI space for virtual try-on and virtual fashion. Today Good morning everyone! We wanted to bring to attention a rather unknown update in the AI space for virtual try-on and virtual fashion. Today we are taking a lo