Archived training logs and LoRA checkpoints from RL fine-tuning (GRPO-family) of video diffusion models. 13 experiment trees + promptdemoskyreels: 24,864 files, 633 symlinks, 2,734 directories. Each run holds checkpoints/ (LoRA current/old/EMA + optimizer state), permanent/epochN/ snapshots, evaluationvbenchi2v/ videos and scores, and wandb/ logs. Runs: skyreelsdefault (4 variants: epg / pepg / grpo / epg-guidance5.0), skyreelsbump, skyreelsbumpepg, skyreelsbumpram, skyreelsbumpdiffusionnft, skyreelsbumpta05epg, skyreelsdiffusionnft, skyreelsram, skyreelsnoisesplitdd08, skyreelsflowgrpo, skyreelsi2vbaseeval, skyreelswanextendeda14b, promptdemoskyreels. The zip exceeds the Hugging Face 50 GB…
Independent publisher
Jaemoo Choi
toony42
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Reinforcement learning.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.