diffusion-outputs is an open-weight model from Wangwenbin. Its published files total 6.7 GB.
Unconditional and conditional DDPM training artifacts for CIFAR-10, using custom UNet architectures with attention and EMA.
Model Card
Unconditional and conditional DDPM training artifacts for CIFAR-10, using custom UNet architectures with attention and EMA. Only the final unconditional and conditional checkpoints are published: - ddpmwithattentionema/checkpoints/ddpmfinal.pt - conditionalddpmwithattentionema/checkpoints/conditionalddpmfinal.pt Each file is about 3.11 GiB, about 6.2 GiB combined. Intermediate checkpoints, sample images, and training history CSV files are not published. The original full final checkpoints contain model, EMA model, optimizer, scheduler, epoch, and loss state. Use emamodelstatedict for EMA inference weights, with the matching custom architectures from the code repository. Download the…
Excerpt from the card by Wangwenbin.
Identity and Version
- Repository
- Wenbinwang/diffusion-outputs
- Publisher
- Wangwenbin
- Task
- Not stated by the source
- Modality
- Other
- Library
- pytorch
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 75d808148a55ef80d4dacfbc9ce702a8316a5f2f
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
4 files, 6.7 GB in total. The weights are 2 files totalling 6.7 GB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| conditional_ddpm_with_attention_ema/checkpoints/conditional_ddpm_final.pt | Weights | 3.3 GB | 33e79bc8563d |
| ddpm_with_attention_ema/checkpoints/ddpm_final.pt | Weights | 3.3 GB | 92ce0f1e3a4f |
| README.md | Documentation | 923 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 6.7 GB
Released by Wangwenbin through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.