Fifteen few-step checkpoints for the MiniMax-H3 video+audio model, each run on the same 48 English prompts × 2 seeds (0 and 1) × 3 step counts (4, 8, 32) = 288 videos per checkpoint, 4,320 videos in total. Conditioning is text only (no input image, no camera trajectory). Every video is 1344×768, 5 seconds (120 frames at 24 fps), with synthesized audio unless noted. All checkpoints are adapters or distilled variants of MiniMaxAI/MiniMax-H3, except the SolarWM row. The set is intended for side-by-side comparison; it is not a quality ranking. stepNofficial marks the step count the checkpoint was published for; plain stepN folders are extrapolations to step counts the checkpoint was not trained…
Independent publisher
Phd
hffordata
Models in Library0
Datasets in Library1
Models on Hugging Face—
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: Text to video.
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.