Z-Image+Fun-ControlNet-Union+2.1 is a unified ControlNet model designed for ComfyUI workflows, enabling robust multi-condition control (including pose, edge, depth, and more) in Stable Diffusion video and image generation. It excels in applications such as precise character pose alignment, detailed line-art conditioning, depth-aware composition, and consistent visual guidance across frames—making it ideal for animation refinement, fashion prototyping, and AI-assisted creative direction.
The workflow is available to try online at:
https://www.runninghub.ai/post/2003347938057322498/?inviteCode=rh-v1015
Users who sign up via this link will receive 1,000 RH credits upon registration and an additional 100 credits daily for logging in—useful for testing or iterating without local GPU requirements.
Description
Initial public release of the Z-Image + Fun ControlNet Union 2.1.
This version provides unified multi-condition ControlNet support, including pose, edge, depth, and line-art guidance, optimized for ComfyUI workflows.
Designed for stable image and video generation with improved consistency and controllability.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.