【Z-IMG】TXT to IMG — v1.1

【Z-IMG】TXT to IMG — v1.1 is a ComfyUI text-to-image workflow: enter a written prompt and provide a model, text encoder, and VAE to generate images with ZImageTurbo, with optional tiled upscaling and embedded generation parameters.

The workflow is described as an 8-node ComfyUI setup built for the Nodes 2.0 (Vue) interface.

It includes a Detail Refiner sampler, SeedVarianceEnhancer, built-in SeedVR2 tiled upscaling, and an auto version that can download models automatically.

The base option lists z_image_turbo_bf16.safetensors, qwen_3_4b.safetensors, and ae.safetensors; the GGUF option lists z_image_turbo-Q8_0.gguf, Qwen3-4B-UD-Q6_K_XL.gguf, and ae.safetensors.

Generated images can be upscaled in tiles and saved with generation parameters embedded in their metadata.

In ComfyUI, enable “Use Nodes V2 (Vue)” in Settings, refresh, and then load the workflow; without it, display problems may occur.

Vorschlag · nicht geprüft

Install the ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.

Vorschlag · nicht geprüft

Listed node-pack names are: comfyui_ultimatesdupscale; comfyui-detail-daemon; comfyui-easy-use; ComfyUI-GGUF; comfyui-image-saver; comfyui-kjnodes; comfyui-mxtoolkit; rgthree-comfy; and seedvarianceenhancer.

Listed model filenames are: 4x_NMKD-Siax_200k.pth, ae.safetensors, Qwen3-4B-UD-Q6_K_XL.gguf, z_image_turbo-Q8_0.gguf, qwen_3_4b.safetensors, and z_image_turbo_bf16.safetensors.

Toggle the built-in SeedVR2 tiled upscaler on or off.

Use three LoRA slots with individual on/off toggles and strength controls, and connect additional LoRA modules.

Before loading, verify that the workflow is titled 【Z-IMG】TXT to IMG — v1.1 and confirm the model and text-encoder filenames for your selected option.

Vorschlag · nicht geprüft

For GGUF, verify the ComfyUI-GGUF package you use and check that the model and text-encoder filenames are z_image_turbo-Q8_0.gguf and Qwen3-4B-UD-Q6_K_XL.gguf before loading.

Vorschlag · nicht geprüft