Zimage seamlessly integrates LORA and ControlNet, scaling up to 8K rendering to deliver commercial-grade image quality.
✨ Register on RunningHub to get 1000 FREE RH Coins!
💰 Plus, claim 100 extra coins every single day just by logging in.
🚀 Try it Now:
1️⃣ AI APP: Z_image_I2I_controlnet_8K version_image remix:
[https://www.runninghub.ai/ai-detail/1996948046745374721/?inviteCode=rh-v1291]
🔽Free download of workflow models/Loras 🔽
Download link for Qwen3VL Cracked version: https://pan.quark.cn/s/71503112e6e8)
Download link for Z-image: https://pan.quark.cn/s/ad363418fbe8
Download link for Detailed Eyes for Z-image: https://pan.quark.cn/s/7247741c5bbb
Download link for Z-image-controlnet: https://pan.quark.cn/s/44c431952b9e
Download link for ComfyUI_Qwen3-VL-Instruct-abliterated: https://github.com/T8mars/ComfyUI_Qwen3-VL-Instruct-abliterated
- - - - - - - - - - - - - - - - - - - - - - - - - -
💡 Workflow Features:
* Two-Pass Sampling: Separates "Control" from "Quality" to eliminate degradation. *
Detail Injection: Integrated "DetailedEyes" LoRA for realistic textures. *
3 Modes: One-click switch between Canny, Pose, and Depth. *
8K Upscaling: Built-in high-res fix for commercial-grade output. If this workflow saved your images, please
SMASH that LIKE button and SUBSCRIBE for more advanced ComfyUI tutorials!
Description
FAQ
Comments (2)
Very "professional" to put in download links to chinese websites where we need to register to download the needed files. Thumbs up! 👍🏼
Bro, did you know these models can be downloaded directly from Hugging Face? I've shared the Hugging Face download links in other posts—just not in this one. The workflow is already set up. If you don't plan on downloading the models yourself, there's nothing I can do about it.