First impressions of Qwen Edit Plus (2509) Running on kaijugen. ComfyUI Workflow to follow
ByteDance has been on fire lately — and now they’ve released Qwen Edit Plus (2509), their most powerful AI image editing model yet. In this video, I share my first impressions, run real-world tests, and compare it to Nano Banana and Seed Dance.
Here’s what I cover:
▸Multi-image ...
2025-09-25 20:26:47 +0000 UTC View Post
The incredibly popular popular Wan Vace has been updated to 2.2 bringing with it all the incredible capabilities of the all in one editing model of Vace to the improvement to 2.2
Below is my all in one workflow updated to fix issues that arose from some comfyiu updates breaking some of the kijai nodes, as well as a new section to cover all the wan vace improvements.
Over the ...
2025-09-16 19:16:46 +0000 UTC View Post
Learn how to train WAN 2.2 LoRA for images both locally and on RunPod! In this step-by-step guide, I’ll show you how to set up the tuner, prepare your datasets, and train your own character LoRAs. Whether you’re using a powerful local GPU or renting one in the cloud, this tutorial will give you everything you need to get started.
💡 What you’ll learn: ▸ How to train LoRAs on WAN...
2025-09-11 13:10:21 +0000 UTC View Post
In this video I break down the BEST ways to use Nano Banana, how to handle issues with Google AI Studio, and other tools that are making incredible use of Nano Banana
Official Prompting Guide:https://ai.google.dev/gemini-api/docs/image-generation#prompt-guide
Mentioned in the Video
...
2025-09-03 20:57:34 +0000 UTC View Post
I’ll show you my all-in-one Wan 2.2 workflow for text-to-video, image-to-video, text-to-image, and upscaling — all inside ComfyUI. You’ll learn how to cut video generation time in half, get insane image fidelity (even better than Flux), and integrate LoRA optimizations for speed and quality.
...
2025-08-12 19:17:31 +0000 UTC View Post![ComfyUI SuperManager 0.02 [Beta]](https://img5.fansofall.com/storage/9/ny/zb/7f3446-019e8c39-0350-724b-9c72-3eb6e27d4f23.png)
Thanks to those of you who reported issues setting up & installing the supermanager. especially squee who provided me valuable information on the installation issues. I have tried to resolve the issues, and have them working on my devices. I've also provided some instructions to resolve some common user-side issues.
Thanks again!
Fixes:
Fixed Windows installation ...
2025-08-12 16:10:40 +0000 UTC View Post
Check out the free video on youtube here https://youtu.be/rev1UOLM2-E
WAN 2.2 is here! In this hands-on tutorial, we dive into the latest open-source breakthrough in AI-powered video creation. Learn how to install models, optimize your pipeline, and generate high-quality videos using WAN 2.2's new capabilities!
...
2025-08-10 14:00:13 +0000 UTC View Post
WAN 2.2 is here! Wan has gotten a major upgrade! In this video we do some basic testing & comfyui Installation using both default ComfyUI nodes and the Kijai Wan Wrapper.
Whether you're deploying via RunPod cloud infrastructure or building locally with ComfyUI nodes, this guide walks you through the full setup and workflow. Learn how to install models, optimize you...
2025-08-08 17:00:26 +0000 UTC View Post
Learn how to use FusionX, the most powerful upgrade for the WAN model in ComfyUI. In this full tutorial, I’ll show you how to boost your AI video quality, reduce generation time, and get smoother motion by combining the best LoRAs—like CosVid, MovieGen, ACCVid, and more!
💡 What you’ll learn:
▸What FusionX is and how it works
▸How to install and use FusionX in Comf...
2025-08-04 10:59:52 +0000 UTC View Post
Midjourney has officially released its Video 1.0 model, and it’s now available even on the $10 Basic Plan. In this video, I walk you through exactly how it works, from selecting an image, setting motion intensity, and generating your first AI animation.
You’ll learn how to use the new “Animate” button, what Low vs High motion means, and what kinds of images work best. I also test ...
2025-06-24 10:51:03 +0000 UTC View Post
This guide will show you how to use Phantom AI 14B, a powerful AI tool based on the WAN video model. You’ll learn how to run it both on KaijuGen, and on your own PC with ComfyUI.
Phantom lets you mix characters, change clothes, or move people to new places, all in a video. It’s great for creators who want more control over their AI vi...
2025-06-20 20:33:59 +0000 UTC View Post
You won't believe what Flux Kontext can do! This is the latest AI image editor and generator from Black Forest Labs—the same team behind the original Flux model. And in this video, I’m showing you how to use it via API inside KaijuGen!
Why Use KaijuGen?
KaijuGen makes it super easy to work with Flux Kontext—edit your images, add logos, mix characters, change up s...
This video is your complete guide to WAN Vace, a leading offline AI video model. We will walk through installation, setup, and advanced workflows using KaijuGen, ComfyUI, and RunPod — compatible with GPUs like the H200 or even 24GB GPUs!
🔍 What You’ll Learn in This Video:
▸How to run WAN Vace on local GPUs and cloud platforms
▸Full installation and setup using Kaiju...
2025-06-10 16:30:32 +0000 UTC View Post
In this video, I test and compare some of the most popular AI tools to see how well they keep a character consistent using just one image!
Tools tested:
• Infinite You (ByteDance)
• DreamO
• Instant Character (Tencent)
• MidJourney Omni
• Runway ML
• ChatGPT’s image tool
• LoRA models
What I looked at:
•...
DreamO by ByteDance enables you to combine character identity, styles, and even objects using just two reference images. In this video, we go into great detail on using DreamO on Kaiju Gen, GRadio, and ComfyUI!
🔍 What You'll Learn:
• Use Kaiju Gen to test DreamO for generating consistent characters from just 1–2 images
• Combine two characters or objects...
UPDATE: Workflows were not working. I have replaced them with a single updated workfow
In this video, we take a comprehensive look at Tencent’s Instant Character — a powerful AI tool designed to generate consistent character images from a single reference. It offers several unique features, especially when combined with LoRA styles like Makoto Shinkai and Ghibli!
This is the free comfyui workflow from https://youtu.be/C2Zcgcvx9hA
2025-05-09 16:00:16 +0000 UTC View Post
In this easy-to-follow guide, I’ll walk you through how to set up Infinite You on comfyUI using RunPod, a cloud service where you can rent powerful GPUs. Whether you’re just getting started or are already experienced, I’ll show you how to launch your setup, load the workflow, and create your first AI-generated image step by step!
📌 What you’ll learn:
•What Infinite You ...
2025-05-09 08:44:59 +0000 UTC View Post
This is the free version of the basic HiDream workflow available on the HiDream post
2025-05-06 07:20:19 +0000 UTC View Post
I just added a major UI update to Kaijugen! The UI is a lot cleaner, a bunch of visual bugs have been fixed, and a lot of features streamlined!
I've also added:
- Chat GPT image Gen
- HiDream Image Gen
- Kling 2.0 Video Gen
- Infinite You character clning
- Instant Character character cloning
- There is also a character creator template (more parameters added to th...
What if you could turn a single photo into an entire set of consistent, stylized character images—without training a custom AI model? In this video, we dive into Infinite You, ByteDance’s cutting-edge solution for one-image character creation, designed to work with the Flux model ecosystem.
📌 What you’ll learn:
• What Infinite You is
• How to run Infinite You o...
2025-05-02 20:50:08 +0000 UTC View PostThis is the basic freepack workflow available for all! I'm also releasing it here for easy access
2025-04-27 21:34:34 +0000 UTC View Post
Update 1: Fixed Framepack runpod template link & added new Advanced Framepack template with advanced features like Frame Start, Frame End, Batch creation and more. However be warned that the advanced template takes about 20 minutes to spin up.
I also fixed that it did not work with RTX5090's Now both versions work.
I've also added a Framepack Windows Installer. PLEA...
2025-04-27 11:24:50 +0000 UTC View Post
In this tutorial, I walk you through how to run the open-source HiDream image generation model on ComfyUI, including support for both full and quantized versions. Whether you're using a powerful GPU or working with limited VRAM, this guide is designed to help you get the most out of HiDream's advanced capabilities.
HiDream Gradio & model comparison: 2025-04-22 18:25:05 +0000 UTC View Post
OpenAI just dropped their most powerful image generation model yet—and it's changing the game. In this in-depth video, we test the new ChatGPT-4o image generator against top competitors like Midjourney, Reeve, and Google’s Imagen. From text accuracy and prompt adherence to complex multi-character scenes and UI tricks, we cover it all. We also show you how to use it through ChatGPT and Sora,...
2025-03-29 15:15:16 +0000 UTC View Post
Discover Reve AI, the groundbreaking image generator that’s dominating leaderboards with its speed, affordability, and unmatched prompt adherence! In this video, we pit Reve against giants like Midjourney, Flux, and Google’s imagen3 to see how it handles everything from pop culture icons to complex group scenes. Spoiler: It’s a game-changer. 🔥
🔗 Links & Resources 2025-03-28 10:59:46 +0000 UTC View Post
AI-generated videos are evolving fast! With WAN 2.1, you can now create AI videos on low-end PCs or rent powerful GPUs for high-quality results. In this video, I’ll show you:
✅ How to use WAN 2.1 on Kaiju Gen
✅ Running WAN 2.1 on RunPod
✅ Setting up a local Web UI with Comfy UI
✅ Tips for better AI video quality
🔗 Resources & Links:
▸Si...
2025-03-13 06:21:40 +0000 UTC View Post