fyxfelixfu/consistentDMD

Consistent Distribution Matching for Data-Free Diffusion Distillation

This is the official PyTorch checkpoint repository for Consistent Distribution Matching for Data-Free Diffusion Distillation.

Project page: https://consistentdmd.github.io/

Code: https://github.com/felix-yuxiang/CDMD

This release contains one LightningDiT-teacher CDMD student for class-conditional ImageNet 256×256 generation. The same student produces the project page's 2.04 / 1.62 / 1.37 FID results with 1 / 2 / 4 Euler steps. Each step is one network evaluation; inference uses no classifier-free guidance pair or teacher model.

Checkpoint and statistics

File	Size	Description
consistentdmd-ldit-best.pt	2.73 GB	Reporting PostHocEMA index 1, sigma_rel=0.2. Compact FP32 student weights and portable metadata, compatible with the public code.
latents_stats.pt	1.8 KB	Matching VA-VAE latent mean and standard deviation, required for image generation.
fid-50k-256.npz	33.6 MB	ImageNet reference statistics for FID evaluation with the pinned metric implementation.

The statistics for this model are .pt and .npz files; no statistics .pkl is required. The compact checkpoint contains no optimizer, teacher, or training history and cannot resume training. Its implementation configuration is LightningDiT-XL/1, dmf_depth=10, with 32-channel 16×16 VA-VAE latents and 1,000 classes.

The required VA-VAE decoder is downloaded separately by the code's asset script. The two statistics files are unmodified copies from Peterande/FACM at revision b7b5fee6d3f43347883d0fe6f9f357e3068375b8. assets.json records their upstream revision, sizes, and SHA-256 hashes, together with the decoder and training-only teacher identities.

Download and sample

Set up the environment from the code repository. Run the following commands from its root:

hf download fyxfelixfu/consistentDMD \
  consistentdmd-ldit-best.pt latents_stats.pt fid-50k-256.npz \
  --local-dir cache

# Downloads the VA-VAE and verifies the matching inference assets.
python scripts/download_assets.py

# Generate 64 images with one network evaluation per image.
bash scripts/test.sh --sampling-steps 1 --num-samples 64 --skip-metrics \
  --output-dir samples/preview

Use --sampling-steps 2 or --sampling-steps 4 for the other project-page settings. The public sampler also supports 8, 16, 32, and 64 Euler steps. Inference requires a BF16-capable NVIDIA GPU. The decoder runs in FP32 and the student runs in BF16, while checkpoint tensors remain FP32.

Reproduce FID

Use the public repository's pinned requirements, including the LTH14 torch-fidelity fork. The recorded setup uses two A100 80GB GPUs, seed 0, 50,000 images, and batch size 32 per GPU:

torchrun --standalone --nproc_per_node=2 test.py \
  --ckpt-path cache/consistentdmd-ldit-best.pt \
  --sampling-steps 1 --num-samples 50000 \
  --batch-size 32 --decode-batch-size 32 \
  --output-dir samples/euler-1

Repeat with --sampling-steps 2 and 4, using a fresh output directory for each run.

Euler steps / NFE	Recorded FID-50K ↓
1	2.0358
2	1.6185
4	1.3711
8	1.2764

results.json contains the evaluation protocol and results.

Integrity and provenance

The release was checked against the frozen reporting EMA: all 419 state tensors are exactly equal, with no precision conversion. The checkpoint SHA-256 is:

0eddca248af6cfaa21e5b9b32d0c02329923e5066d1bb2b140fa6827c061c1d4

See consistentdmd-ldit-best.pt.json for model and EMA metadata, consistentdmd-ldit-best.pt.sha256 for its checksum, and SHA256SUMS for all release files. This is an exact copy of the validated export under the filename expected by the public code.

License and acknowledgements

The CDMD checkpoint follows the project's CC BY-NC-SA 4.0 license. The architecture and decoder build on Lightning-DiT and DiT. Upstream assets retain their respective terms; see THIRD_PARTY_NOTICES.md.

Citation

@article{fu2026cdmd,
  title   = {Consistent Distribution Matching for Data-Free Diffusion Distillation},
  author  = {Fu, Yuxiang and Yan, Qi and Wu, Zike and Zhang, Yongxing and
             Abolmaesumi, Purang and Wang, Lele and Liao, Renjie},
  journal = {arXiv preprint arXiv:2610.09221},
  year    = {2026},
  url     = {https://arxiv.org/abs/2610.09221}
}