Supercharge Z-Image Turbo with Qwen VL in ComfyUI: a new way to create AI images

Описание: In this video I explain how to use the new Z-Image Turbo model together with Video Language Models (VLM), more specifically with Qwen3 VL (4B FP8).

The new image generation models combine perfectly with (V)LLM's, but how to use them has been hardly explore. In this video we will try to have a 'conversation', as suggested in the QwenImageWan Bridge node, which I find excellent! Please check out its Github for more details and to learn better how to use the 'conversational' mode of Z-Image Turbo (ZIT):

⭐ ComfyUI-QwenImageWanBridge: https://tinyurl.com/3dm3npdu

=================================================================
👉 The workflow made in this tutorial FREE here: https://ko-fi.com/s/126263f3d8

Yet, a small tip is appreciated 🤑. You can also support using the Runpod links below:

🚨 Use this link to use RunPod: https://get.runpod.io/e0pn9e5rpbr4
⭐ Easier with the Runpod Template for RTX5090/P6000: https://tinyurl.com/KN-Blackwell-temp...

Test it for free: https://tinyurl.com/378d27z6 (2 generations, will take 3-4 minutes to start up)
Or run it without any installation or setup with Mimic PC: https://tinyurl.com/52ektmay

===========================================================
CONTENTS:
0:00 Intro: Z-image turbo ComfyUI with VLM (Qwen VL), some images
0:09 Loading the Z-image Turbo template of ComfyUI: installing models, Visual Language Models (VLM) possibilities, Qwen3 VL
0:47 Installing custom nodes: KJ nodes, QwenVL, QwenImageWan Bridge
1:15 Adding QwenVL custom node
1:46 Loading 3 images for Face, clothing and scene, and combining them
2:47 Writing down the prompt for QwenVL that combines the features of face, clothing and scene
3:28 Running the workflow and prompting from Qwen VL
4:30 Z-Image Text Encoder to replace CLIP Text encode in ComfyUI
4:52 How does the VLM interact with Z-Image: explanation of the new encoder
5:10 Testing system prompt templates
5:32 Conversation with Qwen3 VL in ComfyUI: using the Turn Builder
6:12 Creating a new image with the new instructions
6:48 Rinse and repeat: extending the conversation, adding details and improving the image
7:25 Continuing with the experimentation: adding more turns, changing prompts, new styles (system prompts)

Useful links:
🎥 Check out my tutorial how to run Runpod:    • Runpod ComfyUI in 5 min (Install with Netw...  

#z-image
#comfyui
#zit
============================================================
💪 Support this channel with a Super Thanks or a ko-fi! https://ko-fi.com/koalanation
☕ Amazing ComfyUI workflows: https://tinyurl.com/y9v2776r

🚨 Use Runpod and access powerful GPUs for best ComfyUI experience at a fraction of the price. https://tinyurl.com/58x2bpp5 🤗

☁️ Starting in ComfyUI? Run it on the cloud without installation, very easy! ☁️
👉 RunDiffusion: https://tinyurl.com/ypp84xjp 👉15% off first month with code 'koala15'
👉 ThinkDiffusion: https://tinyurl.com/4nh2yyen

============================================================
CREDITS
===========================================================
Pexels
https://www.pexels.com/photo/woman-st...
https://www.pexels.com/photo/landscap...
Shutterstock (under Standard license), assets ID's
2381320609 (Sep 15, 2025)
2042719760 (Aug 15, 2025)

✂️ Edited with Canva, and ClipChamp. I record the stuff in powerpoint.
========================================================
© 2025 Koala Nation
#comfyui #wan #videoai