| --- |
| pipeline_tag: text-to-video |
| tags: |
| - omnimem |
| - wan |
| - video-generation |
| - long-video |
| --- |
| |
| # long_rolling_plain_from_ode_init |
| |
| OmniMem long rolling video generation with a fixed prompt, using an ODE-derived self-forcing initialization. |
| |
| This release contains the **EMA generator checkpoint at training step 1500**. |
| The plain rolling-training run initialized from step-800 self-forcing EMA weights in the ODE lineage. |
| |
| ## Contents |
| |
| - `config.json` |
| - Two `safetensors` weight shards and their index |
| - `SHA256SUMS` for payload integrity checking |
| |
| The weights retain their original FP32 storage. The model configuration uses NSA top-12 block selection. |
| |
| ## Usage |
| |
| Use compatible OmniMem code with `CausalWanNSAModel` and `CausalWanT2VPipeline`. |
| The Wan2.1 VAE, UMT5 text encoder, and tokenizer are separate required components. |
| |
| ```python |
| from omnimem.models.transformers.causal_wan_nsa_model import CausalWanNSAModel |
|
|
| model = CausalWanNSAModel.from_pretrained( |
| "omnimem/long_rolling_plain_from_ode_init" |
| ) |
| ``` |
| |
| The original checkpoint configuration is preserved unchanged. Its saved class name |
| records the training wrapper, and `_name_or_path` records the initialization source. |
| The released weights are the **step-1500 EMA** weights. |
| |
| ## Training evaluation settings |
| |
| | Setting | Value | |
| | --- | --- | |
| | Prompt mode | Fixed prompt throughout each video | |
| | Resolution | 832 × 480 | |
| | Video duration | 60 seconds | |
| | Frame rate | 16 FPS | |
| | Exported frames | 960 (969 generated, tail cropped) | |
| | Sampling steps | 4 | |
| | Guidance scale | 1 | |
| | Timestep shift | 5 | |
| | Seed | 42 | |
| | Frame block size | 3 | |
| | KV history window | 3 | |
| | KV cache LRU maximum | 7 | |
| | VAE decode chunk size | 3 | |
| |
| Training evaluation uses five full-length static prompts. |
| |
