You can deploy this model and start earning money today!

iky1e/
moebius-ft-ffhq-mlx-mxfp8

Views

No views yet

Moebius ft_ffhq MLX mxfp8

This folder contains a converted MLX version of the ft_ffhq Moebius checkpoint in mxfp8 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-mxfp8`
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	`mxfp8`
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

MLX MXFP8-style 8-bit export. The manifest selects unet_quantized.safetensors; VAE encoder and decoder remain regular f16 safetensors. Runtime quantization metadata uses mode: mxfp8 with group size 32.

UNet precision mode: mxfp8.
MLX grouped quantization is used for supported linear layers; grouped quantized weights are loaded through the Moebius-MLX manifest/runtime.
Quantization config: 8 bits, group size 32, mxfp8 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`	432.23 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.

iky1e/moebius-ft-ffhq-mlx-mxfp8