lucid-dl/ddpm-church

DDPM (LSUN-Church 256×256)

https://arxiv.org/abs/2006.11239

Lucid port of diffusers/google/ddpm-church-256, converted to Lucid-native safetensors.

Available weights

Tag	Params	GFLOPs	Size	Source
LSUN_CHURCH (default)	113.7M	—	433.67 MB	diffusers

Usage

import lucid.models as models
from lucid.models.weights import DdpmLsunWeights

# default tag
model = models.ddpm_lsun(pretrained=True)

# explicit tag (enum or string)
model = models.ddpm_lsun(weights=DdpmLsunWeights.LSUN_CHURCH)
model = models.ddpm_lsun(pretrained="LSUN_CHURCH")

# preprocessing travels with the weights
weights = DdpmLsunWeights.LSUN_CHURCH
preprocess = weights.transforms()
out = model(preprocess(image)[None])
logits = out.logits  # (B, num_classes)

Conversion

Converted from diffusers/google/ddpm-church-256 via python -m tools.convert_weights ddpm_lsun --tag LSUN_CHURCH. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

Ho, Jonathan, Ajay Jain, and Pieter Abbeel. "Denoising Diffusion Probabilistic Models." Advances in Neural Information Processing Systems, 2020, pp. 6840–6851.