Video coming soon
ComfyUI Models Explained: Download, Folders and Model Loaders
What a model is, what the file names mean (bf16, fp8, int8, GGUF), where each file goes, and how to load it with Load Checkpoint, or with Load Diffusion Model, Load CLIP and Load VAE. Made with Z-Image Turbo.
To open one: drag the .json file onto ComfyUI, or use Workflow > Open. New to ComfyUI? Install it first.
Practice tasks
The same tasks as the notes in the Practice workflow.
- 1
Add
The painter
Double-click inside the Task 1 box, search for Load Diffusion Model, and add it.
Pick the z_image_turbo_int8_convrot file, and connect its MODEL output to the model input of the KSampler.You know it worked when the KSampler's model input has a wire.
- 2
Connect
The translator
In Load CLIP, set type to lumina2, the type for Z-Image.
Connect its CLIP output to the clip input of CLIP Text Encode (Prompt).You know it worked when the prompt node has a wire on clip.
- 3
Fix it
Run and read the error
Press Run. ComfyUI stops with Required input missing: VAE Decode has no VAE.
Connect the VAE output of Load VAE to the vae input of VAE Decode, and press Run again.You know it worked when the orange panda painter appears in Save Image.
- 4
Save
Keep your work
Press Ctrl + S, type a name like My models practice, and press Enter.
You know it worked when your workflow shows in the Workflows panel on the left.
- 5
Experiment (optional)
One file
Download the one file version (the link is on the page) into ComfyUI/models/checkpoints, and press R.
Add Load Checkpoint, pick that file, and connect its MODEL, CLIP and VAE outputs in place of the three loaders. Run with the same seed.You know it worked when you get the same panda, with small differences in the details.
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.