All updates

A free, open-source tool that gets you the exact shot before you generate, plus the fix for when 3D-guided AI video comes out stiff. And a secret AI video model just turned up in blind tests on the Arena, swinging big on motion. Also this week: Kling's reported IPO, Ideogram's…

In this video of ComfyUI Nodes Explained, you will learn what a model is, what the file names mean (bf16, fp8, int8, GGUF), where each file goes, and how to load it, with Load Checkpoint or with Load Diffusion Model, Load CLIP and Load VAE. Everything is shown with Z-Image…

In this episode, we test FLUX 3 Klein, the new image model from Black Forest Labs, in ComfyUI with 19 free workflows. One model can generate an image, edit it, and combine several images into one. We start with text to image: photos and illustrations from a prompt, a Z-Image…

ComfyUI now supports the use of Ming Image Design models, with tiny INT8 and larger BF16 models available. What makes Ming Image stand out from other models is the text generation and positional capabilities, plus this MIT Licensed released is even better than restricted models…

Text to image and image editing · 1K, 2K · up to 4 reference images · from $0.018 per image

Text to image and image editing · 1K, 2K · up to 4 reference images · from $0.046 per image

Text to image and image editing · 1K, 2K · up to 8 reference images · from $0.030 per image

ByteDance's new world model, Sora returns?, Krea 3 is here, OmniHuman 2.0 is back, Pico Space Pro, World Gacha, and LTX-2.5's new post tools. ByteDance's unreleased world model took a scene from Stephen Chow's King of Comedy and re-shot it from new camera angles off one drawn…

Krea’s reference-driven image model — multi-reference inputs, targeted edits that hold the details you name, and fast iteration — lands in ComfyUI as a Partner Node.

5.6B parameters — base and distilled open weights — bounding boxes and multi-reference editing — FLUX 3 Image Klein runs natively in ComfyUI.

Text to image and image editing · 768, 1K, 1.5K, 2K, 4K · up to 10 reference images · from $0.008 per image

In this episode, I'll show you 50 free ComfyUI workflows that automate the boring parts of working with images. Instead of editing images one by one, you point a workflow at a folder, press Run, and it does the whole folder for you. We'll start with simple image folder…

hi everyone! We're testing a new "Thinking Mode" for image generation on our Alpha website ( alpha.midjourney.com ) and we'd love your feedback. To run it go under the lightbox for a job and click "Rerun (Thinking)" in the lower right corner

Hi everyone, here's this week's round of changes on alpha.midjourney.com . The highlight this week is shared folders, a new way to collaborate on Midjourney. Many of these improvements came straight from #alpha-ideas-and-bugs and office hours, so keep your thoughts coming! 🆕

1K to 4K output — Minimal, Medium and High thinking — instruction-based editing — Google's Gemini Nano Banana 2.1 lands in ComfyUI as a Partner Node.

Text to image and image editing · 1K, 2K, 4K · up to 14 reference images · $30.00 per 1M output image tokens

In this episode, I’ll show you how to use Ming Image 0.1 in ComfyUI, a free image generation model focused on graphic design, text, layouts, and image editing. Ming Image is especially interesting for designs that contain a lot of text. I’ll test it with posters, infographics…

Text to image and image editing · 1K, 1.5K, 2K, 4K · up to 20 reference images · $1.60 per 1M output image tokens

ICYMI – last week, we launched a few features on alpha.midjourney.com that we're really excited about: style previews in the sidebar so you can see what you’ll get before you generate, larger images in create, and setting default parameters in a folder. Mostly focused

Text to image and image editing · 1K, 2K · up to 14 reference images · from $0.018 per image

Four is your lucky number today. Kling 4 is here — kinda. But, I ran it through the usual tests: text-to-video, image-to-video, Omni with Flamethrower Girl, a noir scene in Malloy's office, and my keyframes-plus-Omni trick. Then Google wakes up with Gemini 4 Argon (announced…

Text to image and image editing · 768, 1K, 1.5K, 2K, 4K · up to 10 reference images · from $0.041 per image

In this ComfyUI tutorial, I’ll show you Qwen Image 2.1 with more than 20 workflows for image generation and editing. We’ll start with text-to-image, including different image sizes, low VRAM workflows, prompt enhancement, image-to-prompt, transparent PNG generation, and Turbo…

Despite the name, Qwen Image 2.1 isn't only for text-to-image tasks, but also has great image editing capabilities as well! Supporting up to 10 image references, you can provide inputs for your main characters, their clothing and a background - or anything else you fancy. Swap…

Hi everyone! A few updates to share with you today We're experimenting with fast models in the interface on alpha.midjourney.com . The Styles sidebar can now preview what your latest prompt looks like across styles. Turn on "Live previews" and see a preview of your

Hi everyone, here are the latest round of changes on alpha.midjourney.com . Many of these came directly from your feedback in #alpha-ideas-and-bugs . Please keep it coming! STYLE PREVIEWS We're experimenting with fast models in the interface. The Styles sidebar can now preview…

Text to image · from $0.007 per image

Learn how to use MiniMax Fast H3 in ComfyUI with three video workflows: text to video, first frame to video, and first and last frame to video. I’ll show you how to set up the model, choose your video size and duration, create prompts with Google Gemini, and run each workflow…

7B parameters, native 2K output, RGBA transparency, and editing across up to 10 input images — Qwen-Image-2.1 runs natively in ComfyUI.