--- license: creativeml-openrail-m base_model: - stable-diffusion-v1-5/stable-diffusion-v1-5 - guoyww/animatediff tags: - video-motion-graphs - video-interpolation - pose-guided-video --- # Video Motion Graphs Original weighted-pose diffusion interpolation checkpoint and example inputs for [Video Motion Graphs](https://github.com/haiyangliu0/Video-Motion-Graphs). `finetune_weighted/checkpoint-8000/pytorch_model.bin` is the original full model checkpoint, including reference UNet, denoising UNet, pose guider and 4-channel seed guider. It requires the matching architecture and base components documented in the code repository; it is not a standalone Diffusers pipeline. The checkpoint uses 14 frames: three context frames at each end and eight generated middle frames. The supplied inference configuration uses 20 denoising steps and guidance scale 3.5. Verified on one NVIDIA H100 80GB: real video interpolation, music-driven dance rearrangement, and three real training updates across checkpoint save and new-process resume. These short runs do not establish training convergence or reproduce the full paper benchmark. Weights retain the CreativeML OpenRAIL-M terms of their Stable Diffusion base. Project source code and third-party notices are distributed separately in the code repository. Example media is provided to reproduce the demonstration and is not covered by the source-code license. Checkpoint SHA256: `9cc0f0354c5ec4b33085196ba5786f845e0901fd1dc7159e57be14d972c371af`. ## Reproduced example Starting with only the raw 3,051-frame example video and music, the release code rebuilt pose and segmentation, constructed a 762-node / 1,059-edge graph, and generated three new diffusion transitions. The resulting video is 18 seconds, 768×768, 30 fps with audio. This run completed in 12 minutes 2 seconds on one H100 80GB. ## Historical interpolation variants The following dated archival variants are separate from the original weighted-pose checkpoint above. Their source files and independent fresh Hub downloads passed full SHA256 checks; strict CPU key/shape checks also passed. **GPU inference and rendered-video evaluation: Not performed; this is a historical weight archive, not an inference-quality or paper-final validation.** The CPU checks did not perform a forward pass. | Material Date | Historical Run | Step | Details | | --- | --- | ---: | --- | | 2024-09 | `v7_dup_14_continue_2` | 655000 | [2409 historical variant](2409_variants/v7_dup_14_continue_2_step655000/README.md) | | 2024-11 | `v7_dup_14_s2_8frames_512` | 9000 | [2411 8-frame variant](2411_variants/v7_dup_14_s2_8frames_512_step9000/README.md) | | 2024-11 | `v7_dup_14_s2_12frames_512` | 30000 | [2411 12-frame variant](2411_variants/v7_dup_14_s2_12frames_512_step30000/README.md) | The [standalone runtime](2610_variant_runtime/README.md) contains the matching five-channel standard-VAE entrypoint, three configurations, pinned requirements, source licenses and a base-asset downloader. Its source snapshot is recorded in the [runtime hash manifest](2610_runtime_asset_manifest.json); model and configuration hashes are in the [variant asset manifest](2610_variant_asset_manifest.json). Date prefixes describe the earliest confirmed source-material month. The relationship of step 655000 to the final TANGO or ACInterp model is unconfirmed; none of these checkpoints is labeled best or paper-final. Only model weights are retained, without optimizer or exact-resume state. The existing `finetune_weighted/checkpoint-8000` model and its previously verified example remain unchanged. The archival SHA256 checks are recorded at [model revision `272e50d04196a4946902dafe602c7679e09e5b9f`](https://huggingface.co/haiyangliu0/Video-Motion-Graphs/tree/272e50d04196a4946902dafe602c7679e09e5b9f) in the [archival verification receipt](2610_archival_verification.json). These checks establish file integrity and CPU structure compatibility, not GPU inference quality.