Video coming soon
ComfyUI Prompts Explained: CLIP Text Encode, Negative and Dynamic Prompts
What CLIP Text Encode does, positive and negative prompts, why the negative does nothing at CFG 1, Conditioning Zero Out, how to write a prompt for new models, why weights are ignored on Z-Image and Flux 2 Klein, random choices with {red|blue|green}, comments, and Text Pixaroma. Made with Z-Image Turbo.
To open one: drag the .json file onto ComfyUI, or use Workflow > Open. The Pixaroma version needs the free Pixaroma nodes. New to ComfyUI? Install it first.
Practice tasks
The same tasks as the notes in the Practice workflow.
- 1
Add
The negative prompt
Double-click inside the Task 1 box, search for CLIP Text Encode, and add it.
Connect the CLIP output of Load CLIP to its clip input, and its CONDITIONING output to the negative input of the KSampler. Type blurry, ugly, bad hands in its box.You know it worked when you press Run and get the panda, with no red error.
- 2
Experiment
CFG 1
Change the negative text to anything you like, and press Run.
You know it worked when the image does not change at all: at CFG 1 the K Sampler skips the negative.
- 3
Experiment
Random choices
In the positive prompt, change a navy beret to a {red|blue|green} beret, and press Run a few times.
You know it worked when the beret color changes from Run to Run (the same color can come up twice), and the panda stays the same.
- 4
Experiment
Weights
Change the beret part to a (red beret:0.3) and press Run, then try a (red beret:1.5).
You know it worked when both give the same red beret: Z-Image reads the weight as plain text. Then write a big, bright red beret and see the difference.
- 5
Save
Keep your work
Press Ctrl + S, type a name like My prompts practice, and press Enter.
You know it worked when your workflow shows in the Workflows panel on the left.
Models
Download each file and put it in its folder.
| Model file | Size | Put it in | Download |
|---|---|---|---|
| Diffusion model pick onez_image_turbo_int8_convrot.safetensorsint8, the one used in the video | 6.2 GB | ComfyUI/models/diffusion_models/z-image | Hugging Face |
| Diffusion model pick onez_image_turbo_bf16.safetensorsbf16, full detail, needs more video memory | 12.3 GB | ComfyUI/models/diffusion_models/z-image | Hugging Face |
| Diffusion model pick onez_image_turbo_nvfp4.safetensorsnvfp4, for RTX 50 cards | 4.5 GB | ComfyUI/models/diffusion_models/z-image | Hugging Face |
| Text encoder pick oneqwen_3_4b_fp8_mixed.safetensorsfp8, the one used in the video | 5.6 GB | ComfyUI/models/text_encoders | Hugging Face |
| Text encoder pick oneqwen_3_4b.safetensorsfull detail | 8.0 GB | ComfyUI/models/text_encoders | Hugging Face |
| VAEae.safetensors | 0.3 GB | ComfyUI/models/vae | Hugging Face |
| Checkpoint (optional, Task 4)z-image-turbo-fp8-aio.safetensorsall three parts in one file | 10.3 GB | ComfyUI/models/checkpoints | Hugging Face |
After the download, press R in ComfyUI (or restart it), so the new files show up in the loaders.
Z-Image Turbo is free (Apache 2.0). The Comfy-Org files download without an account.
Chapters
Click a time to jump there on YouTube.