Separate loaders: diffusion model, text encoder, VAE
Why newer models come as three or four files, and which node loads each.
In plain words
A checkpoint packs the drawing model, the text encoder and the VAE into one file. Newer families do not: their parts are large and shared between versions, so authors publish them apart. One text encoder file can serve several model versions; one VAE serves a whole family. You then load each part with its own node and join them in the graph.
Where you meet it in a graph
| Part | Node (title on screen) | Class | Folder | Output |
|---|---|---|---|---|
| Diffusion model | Load Diffusion Model | UNETLoader | models/diffusion_models (older: models/unet) | MODEL |
| One text encoder | Load CLIP | CLIPLoader | models/text_encoders (older: models/clip) | CLIP |
| Two text encoders | DualCLIPLoader | DualCLIPLoader | models/text_encoders | CLIP |
| VAE | Load VAE | VAELoader | models/vae | VAE |
Load CLIP and DualCLIPLoader have a type field that must name the family: for example wan, qwen_image, flux, hunyuan_video, sd3. Load Diffusion Model has weight_dtype: default keeps the file's own precision; the fp8 choices store the weights in 8 bits to save memory, at a small cost in quality.
Typical sets:
- Flux.1: Load Diffusion Model (
flux1-dev), DualCLIPLoader withclip_landt5xxl(typeflux), Load VAE withae.safetensors. - Wan 2.1 / 2.2 14B: Load Diffusion Model (two for Wan 2.2), Load CLIP with
umt5_xxl(typewan), Load VAE withwan_2.1_vae. - Qwen-Image: Load Diffusion Model, Load CLIP with Qwen2.5-VL (type
qwen_image), Load VAE withqwen_image_vae. - Z-Image Turbo: Load Diffusion Model, Load CLIP with
qwen_3_4b, Load VAE withae.safetensors.
Some packs ship loaders of their own (for example GGUF loaders, or the WanVideoWrapper loaders); their outputs may have other types.
Typical mistakes
- The wrong
typeon Load CLIP: the model gets meaningless numbers and draws noise or something unrelated. - A text encoder or VAE of another family: errors about shapes ("size mismatch"), or broken colours.
- The diffusion model in
checkpoints: Load Diffusion Model will not list it. Move it todiffusion_models. - Forgetting one part: the model alone does nothing; all three must be from the same family.
How the app helps
- Node descriptions say which folder each loader reads and which
typevalues exist. - The lesson Which loader for which file sorts the loaders; the video and picture-model lessons check
typeand the kind of each file. - Check lists model files that are not on disk and models of different families in one path.
- In Properties, a field with a built-in note has a button What this field does next to its name; it opens the note under the field: what the field does and what to put in it.