Helios-Distilled — Video Generation AI Model
Helios Distilled turns a text prompt — optionally seeded with an image — into as much as 60 seconds of 24fps video. Runs 2-3× faster than Helios Base for a small quality trade. Fixed 640×384, one to five minutes.
What it does
Helios Distilled is the fast variant of the Helios family: a text prompt, optionally seeded with a starting image, becomes as much as 60 seconds of 24fps video.
It runs two to three times faster than Helios Base for a small quality trade, on a single GPU rather than a cluster. Output is fixed at 640x384, and a clip takes one to five minutes.
When to use it
- Longer clips, up to 60 seconds, rather than the usual five or ten
- Turnaround first, when Helios Base is more wait than the job needs
- Starting from a text description, or from a single seed image
- Clips that stay coherent to the end instead of drifting
- Running on one GPU instead of a multi-GPU cluster
Details
- CategoryVideo Generation
- Year2026
- LicenseApache-2.0
Compliance & Provenance
- ProviderOpen-source (BestWishYsh) · Specialized
- EU AI Act RiskLimited Risk
- Art. 50 TransparencyRequired — AI-generated outputs are marked
Inputs & Outputs
- TextInputstring
Text prompt for video generation
- ImageInputimageoptional
Optional input image for image-to-video generation
- VideoOutputvideo
Generated video
Parameters
- resolutionstringdefault 640x384 (5:3)
Resolution (fixed)
Output resolution. Distilled model is fixed at '640x384 (5:3)'. To use other resolutions, switch to Helios Base.
- num_framesintegerdefault 99 frames (~4s @ 24fps)options: 99 frames (~4s @ 24fps), 198 frames (~8s @ 24fps), +13 more
Frame count (chunk multiples)
Total frames to generate. Same chunk-multiple constraint as Helios Base. Presets from '99 frames (~4s)' up to '1452 frames (~60.5s)' at 24fps. Default ~4 seconds.
- fpsintegerdefault 24options: 16, 24
Output FPS (16/24)
Output frame rate. 16 = lower file size. 24 (default) = cinematic standard.
- seedintegerdefault -1range -1–2147483647advanced
Random seed (-1 = random)
Random seed for reproducibility. -1 (default) selects a fresh random seed every run. Set a fixed non-negative integer to reproduce a previous video (same seed + same prompt + same params → same output). Useful for iterative prompt refinement.
Tags
Alternatives in Video Generation
- Cosmos3 Nano
NVIDIA world model for text-, image- and video-to-video, with optional synced audio.
- Helios Base
On-device text-to-video, up to 60s @ 24fps. 3-10 min.
- LatentSync 1.6 (Lip Sync)
Re-sync a talking video's lips to a new voice.
- LTX-2.5
Lightricks LTX-2.5 distilled 22B: text, or text plus a first-frame image, to a video with a synchronized soundtrack generated alongside it.
- LTX-2.5 Audio-to-Video
Make a talking video from one picture and a voice.
- MiniMax-H3 Ref2VA
MiniMax-H3 Ref2VA (omni-reference) generates a 5-15s 24fps video with native stereo audio from a prompt plus a reference image and a reference clip, that clip's own soundtrack included. Video and its soundtrack come out of one denoising loop, so lip movement and sound land in sync. ~144GB bf16 weights — offloaded component-by-component, minutes-scale per clip.
- Wan2.2 TI2V 5B
Wan2.2 dense 5B unified text+image-to-video. Text only → 5s video from prompt; text + image → image as the first frame of the video.