Step-by-Step Guide Series:
Z-IMAGE - TXT to IMG Workflow

This article accompanies this workflow: link

This guide is intended to be as simple as possible, and certain terms will be simplified.

Workflow description :

This workflow allows you to generate images from text. It is optimized to integrate all metadata for simplified online publishing.

Prerequisites :

📂Files for "base" version :

Model : z_image_turbo_bf16.safetensors
in ComfyUI\models\diffusion_models

CLIP : qwen_3_4b.safetensors
in ComfyUI\models\clip

📂Files for GGUF version :

Model : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\unet

CLIP : Q6
in ComfyUI\models\clip

📂Common Files

VAE : ae.safetensors
in ComfyUI\models\vae

📦Custom Nodes :

• ComfyUI-GGUF

• rgthree-comfy

• ComfyUI_UltimateSDUpscale

• ComfyUI-KJNodes

• ComfyUI-mxToolkit

• ComfyUI Image Saver

Usage :

In this new version of the workflow everything is organized by color:

• Green is what you want to create, also called prompt,

• Red is what you dont want,

• Yellow is all the parameters to adjust the image,

• Blue are the model files used by the workflow,

• Purple is for LoRA.

We will now see how to use each node:

Write what you want in the “Positive” node :

Write what you dont want in the “Negative” node : (not used in turbo version)

Select image format :

For Z-IMG it is recommended to start at 1024x1024. Dimensions too far apart can cause problems.

Choose number of steps:

I recommend 8 steps for Z-image turbo.

Choose the guidance level :

I recommend 1.0 for Z-image turbo.

Choose denoise level:

For TXT to IMG it's always 1.

Choose a sampler :

I recommend euler. Usually, model designers recommend a sampler in their descriptions.

Choose a scheduler:

I recommend simple.

Define a seed or let comfy generate one:

The seed is the unique identification number of the random starting point of an image. With exactly the same settings (prompt, step, etc.) changing the seed allows you to obtain a new image and not exactly the same one.

Add how many LoRA you want to use, and define it :

LoRAs are sort of "mini models" that are added to a base model. They can be used to create certain characters or styles. If you dont know what is LoRA just dont active any.

Choose your model:

Activate or desactivate optional fonction:

• The upscaler increases the resolution of the generated image to produce a sharper one.

• The "add detail" option uses a second sampler to add more detail to the image.

For upscaler, choose upscale resolution:

This number corresponds to the length of the longest side of the image once upscaled.

For "add detail" fonction, choose detailer strengh:

I recommend starting at 1.0 and scaling up according to the desired result.

Now you're ready to create your image.

Just click on the “Queue” button to start:

Once rendering is complete, the image appears in the “image viewer” node.

If you have enabled upscaling, a slider will show the base image and the upscaled version.

Some additional information:

Organization of recordings:

All generated files are stored in comfyui/output/Z-IMG/YYYY-MM-DD.

Depending on the options chosen you will find:

• "YYYY-MM-DD-HH-MM_XXXXXXXXXX_Original" the basic file,

• "YYYY-MM-DD-HH-MM_XXXXXXXXXX_Upscale" the upscaled.

This guide is now complete. If you have any questions or suggestions, don't hesitate to post a comment.