Apply your AI Toolkit-trained Z-Image LoRA in ComfyUI through a single RCZimage pipeline node for training-matched output.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning — you still choose inputs, prompts, and settings.<h3 id="open-preloaded-workflow-on-runcomfy">Open preloaded workflow on RunComfy</h3><a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/z-image-base-ai-toolkit-lora-inference-in-comfyui-training-matched-results?utm_source=civitai&amp;utm_medium=referral">Open preloaded workflow on RunComfy (browser)</a>Why RunComfy first - Fewer missing-node surprises — run the graph in a managed environment before you mirror it locally. - Quick GPU tryout — useful if your local VRAM or install time is the bottleneck. - Matches the published JSON — the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense — you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI) 1. Load inputs (images/video/audio) in the marked loader nodes. 2. Set prompts, resolution, and seeds; start with a short test run. 3. Export from the Save / Write nodes shown in the graph.Expectations — First run may pull large weights; cloud runs may require a free RunComfy account.<hr /><h3 id="overview">Overview</h3>Deploy AI Toolkit-trained Z-Image LoRAs inside ComfyUI with pipeline-level accuracy. The RCZimage node encapsulates the Tongyi-MAI/Z-Image inference pipeline—including FlowMatchEulerDiscrete scheduling and internal LoRA injection—so generation stays consistent with AI Toolkit preview behavior rather than drifting through a generic sampling setup. Load your adapter from a local file in models/loras, a direct .safetensors URL, or a Hugging Face path, and set lora_scale to control adapter strength. For the closest match to your training previews, mirror the resolution, step count, guidance scale, and seed from your sample config. The workflow outputs standard images through SaveImage for straightforward comparison.Important nodes:<ul><li>SaveImage</li></ul><h3 id="notes">Notes</h3>Z-Image Base LoRA ComfyUI Inference | RunComfy Workflow (Training-Matched Results) — see <a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/z-image-base-ai-toolkit-lora-inference-in-comfyui-training-matched-results?utm_source=civitai&amp;utm_medium=referral">RunComfy page</a> for the latest node requirements.

Z-Image Base LoRA ComfyUI Inference | RunComfy Workflow (Training-Matched Results)

Initial release — Z-Image-Base-LoRA-ComfyUI-Inference.

Files with SHA256: 95abc42b2b81c10f6d6ed3b7bb8c221f5419acadfe0a729aecc2a66480f6098d