Home Creators Posts Import Register Favorites Logout

Downloads

Content

Hello friends,

I'm excited to finally share my Krea 2 tutorial with you! 🎉 This is also the very first real video on my new channel, Into the Latent, and I couldn't think of a better way to kick things off.(Yes I released the ComfyUI video earlier but this is the install tutorial)

Krea 2 is an incredibly fast image model that produces fantastic results, supports many well-known characters, and is surprisingly easy to train with your own LoRAs. One of my favorite improvements is that, unlike the original Krea Turbo, you can now combine multiple LoRAs without completely breaking the image. That opens up a lot of creative possibilities.

As always, all Patreon members have access to my one-click installer, which takes care of everything for you:

Downloads all required models automatically

Places them into the correct folders

Installs all required custom nodes

Copies my workflows directly into your ComfyUI installation

You can grab everything here:https://www.patreon.com/AIKnowledgeCentral/posts/krea-2-just-got-164115678

If you prefer the Manual Installation here are the custom nodes I used

📦 Git Repositories You Need

Main Repository (ComfyUI):

https://github.com/comfyanonymous/ComfyUI

Additional Repositories

ComfyUI-AI2Go-Utils

https://github.com/Little-God1983/ComfyUI-AI2Go-Utils

gguf

https://github.com/calcuis/gguf

ComfyUI_UltimateSDUpscale

https://github.com/ssitu/ComfyUI_UltimateSDUpscale

ComfyUI-KJNodes

https://github.com/kijai/ComfyUI-KJNodes

rgthree-comfy

https://github.com/rgthree/rgthree-comfy

ComfyUI-Manager

https://github.com/Comfy-Org/ComfyUI-Manager

ComfyUI-Krea2Edit

https://github.com/lbouaraba/comfyui-krea2edit

ComfyUI-Crystools

https://github.com/crystian/ComfyUI-Crystools

cg-use-everywhere

https://github.com/chrisgoringe/cg-use-everywhere

🎨 Models You Need

🖼 Diffusion Models

(Tip: Place in your models\diffusion_models folder)

📥 Krea2 GGUF

VRAM Options (pick one that fits your VRAM):

8GB https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/blob/main/krea2_turbo-Q3_K_S.gguf

12GB https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/blob/main/krea2_turbo-Q4_K_S.gguf

16GB https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/blob/main/krea2_turbo-Q5_K_S.gguf

24GB https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/blob/main/krea2_turbo-Q6_K.gguf

32GB https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/blob/main/krea2_turbo-Q8_0.gguf

📝 Text Encoders

(Tip: Place in your models\text_encoders folder)

📥 qwen3vl_4b_fp8_scaled

https://huggingface.co/Comfy-Org/Krea-2/resolve/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors

🎭 VAEs

(Tip: Place in your models\vae folder)

📥 qwen_image_vae

https://huggingface.co/Comfy-Org/Krea-2/resolve/main/vae/qwen_image_vae.safetensors

🔧 LoRAs

(Tip: Place in your models\loras folder)

📥 Krea 2 Identity Edit

https://civitai.com/models/2761113/krea-2-identity-edit

🔍 Upscale Models

(Tip: Place in your models\upscale_models folder)

📥 4x-UltraSharp

https://huggingface.co/Kim2091/UltraSharp/resolve/main/4x-UltraSharp.pth

I hope you enjoy the tutorial, and I can't wait to see what you create with Krea 2.

Have fun creating something amazing!

Chris

Files

How to Run Krea 2 on Your PC (ComfyUI Tutorial + Image Editing)

Generate stunning AI images locally with Krea 2 inside ComfyUI—completely free, with no subscriptions or generation limits. In this tutorial I'll show you how to install the models, load my custom workflows, generate photorealistic images, perform powerful image editing, use multiple LoRAs, automate prompt generation with my Batch Prompt node, and finish everything off with AI upscaling for even sharper results. 📩 Stay up to date with Local AI & Open Source AI https://intothelatent.com/newsletter 🎁 Free Downloads & Resources https://intothelatent.com ❤️ Support the channel & get exclusive workflows, guides and early access https://patreon.com/intothelatent 📅 Need help getting started? Book a personal 2-hour 1-on-1 AI coaching session (paid offer) where we'll solve your specific workflow, ComfyUI, Stable Diffusion, or local AI questions together. https://koalendar.com/e/1hr-1-on-1-stable-diffusion Chapters 00:00 Intro 00:55 Text 2 Image - Prompting Basics 05:40 Lora Usage 07:40 Image Edit 11:40 Amazing Batch Prompting 15:15 Upscale

Comments

AICharGen SFW

been meaning to ask, have you found a good way to generate longer (7+ seconds) of ITV animations without the loop back to the initial image?

AI Knowledge Central

LTX 2.3 Is still the best. Especially if you want sound. The Director nodes got a huge update and it got some Kind of Identity lora that helps preserve identity. Maybe I will make another video about it in the future. But that was what got my old channel in trouble.