Ming Image 0.1 Design for WanGP
These are single-file checkpoints prepared for WanGP from
inclusionAI/Ming-Image-0.1-Design
at revision 208087ada1486931692c1896f38d4cd16ff3df82.
The original checkpoint and inference code are MIT licensed. See LICENSE.
The repository contains a BF16 diffusion transformer and its INT8 ConvRot
version at the root, a project-specific BailingMM2 text encoder and its INT8
ConvRot version under BailingMM2-Ming-Image/, and the VAE and runtime
configuration under ming_image/. The tokenizer lives beside the text encoder.
The INT8 files use WanGP's MMGP ConvRot loader rather than stock Diffusers.
The BF16 files were merged from upstream shards with tensor verification.
The connector's upstream FP32 weights were converted to BF16 for the BF16
inference variant. The original model sources and conversion notes are in
WanGP's models/ming_image/ directory.
WanGP supports text-to-image and one-reference image editing with these files. The separate Design-Layer model is not included.