license: apache-2.0
library_name: mlx
pipeline_tag: image-to-image
base_model: hustvl/Moebius
tags:
- mlx
- image-inpainting
- inpainting
- diffusion
- moebius
- ft_celebahq
- q4
Moebius ft_celebahq MLX q4
This folder contains a converted MLX version of the ft_celebahq Moebius checkpoint in q4 form. ft_celebahq means the Moebius checkpoint fine-tuned on CelebA-HQ, for face and portrait inpainting.
Original upstream model: hustvl/Moebius
Original source repository: hustvl/Moebius
Moebius checkpoint fine-tuned on CelebA-HQ. This variant is intended for face and portrait inpainting distributions.
Identity
| Field | Value |
|---|---|
| Variant name | ft_celebahq-q4 |
| Checkpoint meaning | Fine-tuned on CelebA-HQ for face and portrait inpainting. |
| Original Moebius checkpoint family | ft_celebahq |
| Original checkpoint type | CelebA-HQ fine-tune |
| Source PyTorch checkpoint | Moebius-Models/ft_celebahq/diffusion_pytorch_model.bin |
| MLX precision / quantization label | q4 |
| Image size | 512 x 512 |
| Latent size | 64 x 64 |
| Latent channels | 4 |
| Mask channels | 1 |
| Conditioning IDs | 20 |
| VAE scaling factor | 0.13025 |
| Noise offset | 0.0357 |
Quantization
4-bit MLX quantized export. The manifest selects a quantized UNet safetensors file. Standard q4 variants keep VAE encoder and decoder as regular f16 safetensors; special candidate variants can also select quantized VAE files and broader convolution packing.
- UNet precision mode:
q4. - MLX grouped quantization is used for supported linear layers; grouped quantized weights are loaded through the Moebius-MLX manifest/runtime.
- Quantization config: 4 bits, group size 64, standard MLX quantized mode.
- The VAE encoder and decoder remain regular f16 safetensors for this variant.
Manifest-selected deployment files
These are the files selected by manifest.json when the Moebius-MLX runtime loads this variant.
| Component | File | Size |
|---|---|---|
| UNet | unet_quantized.safetensors |
422.41 MB |
| VAE encoder | vae_encoder.safetensors |
68.34 MB |
| VAE decoder | vae_decoder.safetensors |
99.00 MB |
Files in this folder
unet.safetensorsunet_quantized.safetensors(selected by manifest)vae_decoder.safetensors(selected by manifest)vae_encoder.safetensors(selected by manifest)manifest.json(runtime metadata and file selection)
A minimal runtime package needs manifest.json and the manifest-selected files above. Extra source or fallback files are optional and are not required for inference.
Runtime expectations
This is not a Transformers or Diffusers-native checkpoint. It is intended for the Swift/MLX runtime in Moebius-MLX. The runtime reads manifest.json, loads the selected safetensors files, builds the Moebius UNet and VAE modules, and runs the DDIM inpainting pipeline.
Pipeline constants must match the manifest:
- DDIM scheduler:
scaled_linear, beta start 0.00085, beta end 0.012, 1000 train timesteps, clip sample false - 512 x 512 image resolution and 64 x 64 latent resolution
- 9-channel UNet input: noisy latent, mask, and masked-image latent
- VAE scaling factor 0.13025
Attribution
Moebius was released by the original authors as hustvl/Moebius. This folder is a format conversion and/or quantized MLX packaging of the original PyTorch weights, not a newly trained model.