iky1e/moebius-ft-ffhq-mlx-q4

Moebius ft_ffhq MLX q4

This folder contains a converted MLX version of the ft_ffhq Moebius checkpoint in q4 form. ft_ffhq means the Moebius checkpoint fine-tuned on FFHQ, for face and portrait inpainting.

Original upstream model: hustvl/Moebius
Original source repository: hustvl/Moebius

Moebius checkpoint fine-tuned on FFHQ. This is another face and portrait-oriented fine-tune.

Identity

Field	Value
Variant name	ft_ffhq-q4
Checkpoint meaning	Fine-tuned on FFHQ for face and portrait inpainting.
Original Moebius checkpoint family	ft_ffhq
Original checkpoint type	FFHQ fine-tune
Source PyTorch checkpoint	Moebius-Models/ft_ffhq/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.safetensors
• unet_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.