Give the video model a character, a scene and a sound to work from.
MiniMax H3 Reference-to-Video + Singularity are now on NanoGPT: guide clips with image/video/audio references, or animate a starting image.
3-15 seconds, with native stereo audio.
Reference-to-Video:
https://nano-gpt.com/media?mode=video&model=minimax-h3%2Freference-to-video
Singularity:
https://nano-gpt.com/media?mode=video&model=minimax-h3-singularity%2Fimage-to-video
nanogpt / NanoGPT
npub1v2…e3fn9
2026-09-19 23:12:21 UTC
Author Public Key
npub1v2fdmse57a5jddq7aenmlcuj97n6867fm55kktp6uq5lt6m409fsle3fn9Published at
2026-09-19 23:12:21 UTCEvent JSON
{
"id": "073a071b464b9a5101cb6eb5bb30d4d5705062a404f962d07a90d1885ae95dbe",
"pubkey": "6292ddc334f76926b41eee67bfe3922fa7a3ebc9dd296b2c3ae029f5eb757953",
"created_at": 1789859541,
"kind": 1,
"tags": [
[
"t",
"minimax"
],
[
"t",
"h3"
],
[
"t",
"singularity"
],
[
"t",
"ai"
],
[
"t",
"nanogpt"
],
[
"t",
"videogeneration"
],
[
"r",
"https://nano-gpt.com/media?mode=video\u0026model=minimax-h3%2Freference-to-video"
],
[
"r",
"https://nano-gpt.com/media?mode=video\u0026model=minimax-h3-singularity%2Fimage-to-video"
]
],
"content": "Give the video model a character, a scene and a sound to work from.\n\nMiniMax H3 Reference-to-Video + Singularity are now on NanoGPT: guide clips with image/video/audio references, or animate a starting image.\n\n3-15 seconds, with native stereo audio.\n\nReference-to-Video:\nhttps://nano-gpt.com/media?mode=video\u0026model=minimax-h3%2Freference-to-video\n\nSingularity:\nhttps://nano-gpt.com/media?mode=video\u0026model=minimax-h3-singularity%2Fimage-to-video",
"sig": "920889b9cc6692cb0b5848adcea1bf36afbb47f45871aaa49b06867c6cd06e6b9560981780eb8d3bb59298b5db7bce81d8773aaf13b0a4456669d8f7c2f31dd2"
}