Civitai | Discord | Twitch | Support | Merch

Greetings, Civitans! Welcome to the forty-fourth edition of Civitai Biweekly, your essential guide to all recent developments and updates within Civitai.

This week, we’ll cover some extremely exciting new Civitai & Generative AI developments, including…

• Stable Diffusion 3.5 Updates 🖌️

• New LoRA Training Options ⚙️

• Ad. Provider Update🪧

• An Upcoming Guest Stream! 🦄

…and more!

1️⃣ Stable Diffusion 3.5 Update

Exciting news! Stable Diffusion 3.5 is now available in Medium, Large, and Turbo for Text2Image generation on the Civitai Generator, with LoRA support! Plus, we’ve dropped the price of Large Turbo by 50%, making high-speed generation even more accessible. Try them out and experience SD 3.5 in all its forms!

2️⃣ Expanded LoRA Training Options

To enhance our Stable Diffusion 3.5 capabilities, we’re excited to announce that the Large and Medium models are now available for LoRA creation on the Civitai LoRA Trainer! In addition, we’ve introduced the popular anime and illustration-focused model, Illustrious XL, giving you even more creative options.

Further, we’ve added the concept of a dedicated Trigger Word to the LoRA Trainer; words entered into this field are prepended to all caption files, and act as an “activator” for your LoRA during generation;

Dive in and explore these new features for your next LoRA project!

3️⃣ Ad. Provider Update!

We’re committed to keeping ads on Civitai safe and seamless. Recently, some scammy redirect ads slipped through, so we paused ads temporarily. With assurances from our ad provider, ads (and Blue Buzz earnings!) are back on. We’re closely monitoring for any issues, so if you notice anything unusual redirection ads, please let us know! Thanks for your patience and support as we work to ensure ads enhance your experience!

🎃 The Great Halloween Contest 🎃

The Great Halloween Contest has wrapped up, and we’re now combing through all the tremendously spooky entries as we work to pick the winners!

📖 Text-Tacular Showdown Contest 📖

The Text-Tacular Showdown results are in! Our apologies for the delay - we had thousands upon thousands of images to look through, and they were all fantastic!

Check out the winners here! 🏆

A huge thank you to everyone who participated - we received some of the funniest and most creative images we’ve ever seen in a Civitai contest!

New Guides!

Civitai’s Quickstart Guide to Mochi 1 Preview

Open-source, Apache 2.0 licensed, locally-runnable, text2video with gorgeous outputs? Too good to be true, right? Wrong! Genmo’s Mochi 1 Preview model weights can now can be run locally on GPUs with as little as 12GB of VRAM! Pretty impressive, considering only 14 days ago the model required an incredible 3 x H100 GPUs to render videos!

The current models produce 480p outputs, but an HD model is slated for release later in the year.

For more information on how to get started with Mochi in ComfyUI, check out our Quickstart Guide!

Whether you're just beginning your Generative AI Art journey or you're already a seasoned pro, the Civitai Education Hub is your go-to destination for top-tier educational content - https://education.civitai.com 

Special Guest!

Mark your calendar for Tuesday, November 12th, at 2 PM EST as we welcome AstraliteHeart, the creative force behind the massively popular Pony Diffusion XL V6, for a special Twitch stream! Join us as AstraliteHeart shares an exclusive sneak peek into an eagerly anticipated new project (any guesses?), along with insights into his latest work and updates since our last stream. Don’t miss this chance to hear from one of the community’s favorite creators - it's going to be an event to remember!

Red Panda Revealed!

There was much excitement in the text2image space over the past couple of weeks as a mysterious model, codenamed “Red Panda” shot to the top of the text2image model arena! Eventually revealed to be “Recraft” from US/UK company Recraft.ai, it provides exceptional image generation within a suite of comprehensive design tools, catering to product design and marketing. Check it out!

PixelWave - Trained Flux Checkpoint

Creator humblemikey introduces one of the first finetunes for Flux - meet PixelWave! Building on the impressive Flux Dev foundation, PixelWave offers unique and eye-catching styles that Flux fans won’t want to miss.

Illustrious XL - SDXL Finetune

Looking for a solid anime/illustration style, with the flexibility of Pony Diffusion? Check out rising-star Illustrious XL from Creators Onoma AI! It’s also available to try out on the Civitai Generator!

• Models Uploaded: 21k

• Images & Videos Uploaded: 2.5M

• Reviews: 776k

• Comments: 35k (excluding spam!)

• Image Reactions: 14M

• New Users: 155k (excluding bots!)

• Support Tickets Resolved: 725 (we actually zeroed our ticket queue this week!)

• # of Minutes the Support Ticket Queue Remained Empty: 0.3

Changelog

You may not be aware that Civitai is an Open-Source project, and you can - should you wish - review all of our 12,000+ commits on the Civitai Github!

For a more condensed and curated view, check out our Changelog! Updated regularly throughout the month with the most relevant major and minor changes, it’s the perfect way to stay informed on all the important updates and improvements happening week by week.

Visit the Civitai Changelog

Want to connect directly with the Civitai team, learn more about our platform, or gain insights from leading experts in Generative AI?

📅 Check out our Twitch streaming schedule and mark your calendar! In addition to our regularly scheduled Office Hours and AI Video streams, we have some thrilling, must-see events lined up that you won't want to miss!

We look forward to seeing you there!

Newsletter Buzz Reward

Thanks for sticking with us all the way to the end! Here’s your well-earned Newsletter Buzz ⚡(Yellow Buzz, too!) - consider it a ‘thank you’ for being a valued, informed, member of the Civitai community!