# apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors

> Apple DFN5B CLIP ViT-H/14 (fp16) · Vision encoder for MMAudio video-to-audio

This is Apple’s DFN5B CLIP ViT-H/14 image encoder in fp16, packaged by Kijai for ComfyUI-MMAudio. MMAudio uses it to read your video frames before generating matching sound. Put it in ComfyUI/models/mmaudio and select it as clip_model in MMAudio FeatureUtilsLoader.

Kijai’s repo also has an fp32 copy (3.95 GB). fp16 is enough for MMAudio.

## Facts

- **Type:** CLIP vision encoder
- **Format:** Safetensors · fp16
- **Size:** 1.97 GB (1,973,509,450 bytes)
- **SHA256:** d8ad903a79adc2b29bacfeedabfa3d78b03d36d3b4dcb885c0649fe8c5d763cb
- **ComfyUI folder:** ComfyUI/models/mmaudio/
- **Loader node:** MMAudio FeatureUtilsLoader
- **License:** Apple AMLR (upstream weights)

## What is apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors?

MMAudio generates audio that matches a video. To know what is on screen, it embeds the frames with a CLIP image encoder: Apple’s DFN5B ViT-H/14, a CLIP model trained on Apple’s filtered DFN-5B dataset. Kijai converted it to a single fp16 safetensors file for his ComfyUI-MMAudio nodes.

Searches often use the lowercase name apple_dfn5b-clip-vit-h-14-384_fp16.safetensors. Kijai’s file uses capitals; on Linux, rename it to match your workflow exactly.

## Download and install

- [Hugging Face · Kijai/MMAudio_safetensors](https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors) · saves as `apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors` · Packaged for ComfyUI-MMAudio. Recommended.

```sh
cd ComfyUI/models/mmaudio
wget -O apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors \
  https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors
sha256sum apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors
# d8ad903a79adc2b29bacfeedabfa3d78b03d36d3b4dcb885c0649fe8c5d763cb
```

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

## How to load it in ComfyUI

MMAudio FeatureUtilsLoader bundles three helper models from models/mmaudio: the audio VAE, Synchformer and this CLIP encoder. Its output feeds MMAudio Sampler with your video frames.

- **Frame size:** The CLIP encoder resizes frames to 384×384 and reads them at 8 fps.
- **Not a ComfyUI CLIP Vision model:** It does not go in models/clip_vision and Load CLIP Vision will not list it.

## Files MMAudio needs

The BigVGAN vocoder downloads itself on first run.

- [`mmaudio_large_44k_v2_fp16.safetensors`](https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/mmaudio_large_44k_v2_fp16.safetensors) · MMAudio model · `models/mmaudio/` · 2.06 GB
- [`mmaudio_vae_44k_fp16.safetensors`](https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/mmaudio_vae_44k_fp16.safetensors) · Audio VAE · `models/mmaudio/` · 611 MB
- [`mmaudio_synchformer_fp16.safetensors`](https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/mmaudio_synchformer_fp16.safetensors) · Synchformer (audio-video sync) · `models/mmaudio/` · 475 MB

## Workflows: Uses this exact file

These workflows already load apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors. Open one and run it as is.

- [WAN 2.2 Smooth Workflow v5.0 | AI Video Generator](https://www.runcomfy.com/comfyui-workflows/wan-2-2-smooth-workflow-v5-in-comfyui-multi-mode-video-gen)
- [MMAudio | Video-to-Audio](https://www.runcomfy.com/comfyui-workflows/mmaudio-video-to-audio-model)

## Same file, other names, and alternatives

- `apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors` · This page · fp16 · 1.97 GB · MMAudio in ComfyUI
- `apple_DFN5B-CLIP-ViT-H-14-384_fp32.safetensors` · Same encoder · fp32 · 3.95 GB · fp32 pipelines

## Common errors and fixes

### Value not in list: clip_model: 'apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/mmaudio. Usually the file is missing, sits in a different folder.

Fix: Move the file into ComfyUI/models/mmaudio/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

### Missing node type: MMAudioFeatureUtilsLoader

Why: MMAudio FeatureUtilsLoader is not built into ComfyUI. It comes from the ComfyUI-MMAudio custom node pack.

Fix: Install ComfyUI-MMAudio with ComfyUI Manager (or git clone it into ComfyUI/custom_nodes), then restart ComfyUI.

### SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 1,973,509,450 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · Kijai/MMAudio_safetensors if not.

## FAQ

### Which other MMAudio files do I need?

From the same Kijai repo: `mmaudio_large_44k_v2_fp16`, `mmaudio_vae_44k_fp16`, `mmaudio_synchformer_fp16` and this CLIP encoder, all in `models/mmaudio`. The BigVGAN vocoder downloads itself on first run.

### Where do I put apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors in ComfyUI?

In `ComfyUI/models/mmaudio/`. Then refresh the node list or restart ComfyUI so MMAudio FeatureUtilsLoader lists the file.

### Which ComfyUI node loads apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors?

[MMAudio FeatureUtilsLoader](/comfyui-nodes/ComfyUI-MMAudio/mm-audio-feature-utils-loader). It comes from the [ComfyUI-MMAudio](https://github.com/kijai/ComfyUI-MMAudio) custom node pack, so install that first.

### Can I use apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors commercially?

Be careful. Kijai’s repack is tagged MIT, but the weights come from Apple’s DFN5B release under the Apple Machine Learning Research license, and MMAudio’s own weights are CC BY-NC 4.0. Treat the MMAudio pipeline as non-commercial unless you have other rights.

## Sources

- [Kijai/MMAudio_safetensors](https://huggingface.co/Kijai/MMAudio_safetensors)
- [ComfyUI-MMAudio](https://github.com/kijai/ComfyUI-MMAudio)
- [apple/DFN5B-CLIP-ViT-H-14-378](https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14-378)

Canonical page: https://www.runcomfy.com/comfyui-workflows/model-files/apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors
