CIVITAI / Workflows

Z-Image-Controlnet-2.1-8-step text-to-image+lora face fix & paste-back+upscale

This workflow enhances local inpainting for the Z-Image model by using a two-stage rendering process to improve character consistency, especially in challenging scenarios like small faces in a large frame. In the first "high-noise" pass, ControlNet 2.1 guides the overall structure while a character LoRA at low strength establishes the foundational facial features. The second "low-noise" pass increases the LoRA's strength to full to accurately restore the character's identity, bypassing ControlNet to allow for finer aesthetic refinement. To use this, you provide an image and mask the region for inpainting. The workflow also supports two upscaling options for the final output: a diffusion-based tiled upscaler (TTP) and SeedVR2, which offers a more faithful, high-resolution enlargement. This dual-pass approach balances strong structural control with high-fidelity detail, making it effective for complex inpainting tasks. πŸŽ₯ YouTube Video Tutorial Want to know what this workflow actually does and how to start fast? This video explains what the tool is, how to launch the workflow instantly, and shares my core design logic β€” no local setup, no complicated environment. Everything starts directly on RunningHub, so you can experience it in action first. πŸ‘‰ YouTube Tutorial: https://youtu.be/NzMIK3p3aKM Before you begin, I recommend watching the video thoroughly β€” getting the full context helps you understand the tool faster and avoid common detours. βš™οΈ RunningHub Workflow Try the workflow online right now β€” no installation required. πŸ‘‰ Workflow: https://www.runninghub.ai/post/2003343268333092866/?inviteCode=rh-v1111 If the results meet your expectations, you can later deploy it locally for customization. 🎁 Fan Benefits: Register to get 1000 points + daily login 100 points β€” enjoy 4090 performance and 48 GB super power! πŸ“Ί Bilibili Updates (Mainland China & Asia-Pacific) If you’re in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown. πŸ“Ί Bilibili Video: https://www.bilibili.com/video/BV1iEBuB1EbB/ β˜• Support Me on Ko-fi If you find my content helpful and want to support future creations, you can buy me a coffee β˜•. Every bit of support helps me keep creating β€” just like a spark that can ignite a blazing flame. πŸ‘‰ Ko-fi: https://ko-fi.com/aiksk πŸ’Ό Business Contact For collaboration or inquiries, ple

ZImageTurbo #character
View original on Civitai
Z-Image-Controlnet-2.1-8-step text-to-image+lora face fix & paste-back+upscale

Public versions

v1.0

ZImageTurbo