| --- |
| language: en |
| library_name: pytorch |
| tags: |
| - image-generation |
| - imagenet |
| - priming-models |
| --- |
| # Priming Models |
|
|
| ImageNet-256 class-conditional B/L checkpoints after 80/160 epochs of |
| reconstruction pretraining, before and after 25,000 distributional |
| post-training updates. |
|
|
| Files under `checkpoints/pretraining/` contain original full pretraining |
| checkpoints with online and EMA 0.9999 weights. Files directly under |
| `checkpoints/` contain full post-training checkpoints; evaluation uses their |
| EMA 0.999 weights. Post-training initializes from the pretraining online weights. |
| These are original PyTorch training checkpoints, including optimizer state, |
| not standalone Diffusers pipelines or safetensors exports. |
|
|
| The two JSON manifests identify all eight files with sizes and SHA256 hashes. |
| See [the code and setup guide](https://github.com/JaeyeonKim01/priming) |
| for model definitions, evaluation, training recipes, and reproduction records. |
|
|
| ## Evaluation reference assets |
|
|
| `assets/fid_stats/` contains the frozen FDr5 reference statistics and the extra |
| ConvNeXt statistic used during training diagnostics. The precomputed Inception |
| precision/recall reference features are under `data/prc/`. The code's |
| `scripts/download_assets.py` downloads the required subset, pins upstream |
| evaluation encoders, and fetches the separate official JiT FID reference. |
| Users evaluating Priming do not need to recompute real-image statistics. |
|
|
| The processed ImageNet training release is in the separate |
| [dataset repository](https://huggingface.co/datasets/jaykim1102/priming), with |
| ImageNet access terms and matching class indices/OT calibration. Neither |
| sampling nor final FID/FDr5 evaluation requires that training dataset. |
|
|
