Helios vs LTX-2.5: inputs, controls and API cost
Compare Helios and LTX-2.5 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product.
Helios and LTX-2.5 are both realtime video generation options in Windflow's public catalog. Choose by the inputs and interaction you need, then evaluate quality and responsiveness with your actual application. This page compares the published serving profiles; it does not present a head-to-head performance experiment.
Quick decision
- Evaluate Helios for: Continuous generative video that never has to restart: ambient scenes, live backdrops, long takes.
- Evaluate LTX-2.5 for: Audio-visual scenes where sound is generated with the picture rather than dubbed after.
Specifications side by side
| Published specification | Helios | LTX-2.5 |
|---|---|---|
| Architecture | 14B Diffusion Transformer, autoregressive chunked diffusion | 22B joint audio+video DiT, two-stage, generated one window at a time |
| Resolution | Negotiated per session | 832 × 448 measured; the canvas is configurable in multiples of 64 |
| Playout | Negotiated per session | 24 |
| Chunk | 33 native frames in the production profile | 241 frames per window (10.04 s) |
| Control latency | First chunk after roughly one chunk of generation | A whole window: the pipeline does not yield progressively, so time-to-first-frame equals one window's generation time. The reference still is published while it runs. |
| Inputs | Text prompt (required before start) and an optional reference image for image-to-video | A text prompt and an optional reference still |
| Outputs | One continuous, steerable clip on the main_video track | Video on main_video and the audio generated with it on main_audio, aligned per window |
| Delivery | WebSocket (H.264) · WebRTC | WebRTC |
| Session protocol | sdk.realtime.v2 | sdk.realtime.v2 |
| Price | $0.0017 per ready second | $0.0040 per ready second |
| Implementation status | production | production |
Implementation status describes runtime maturity. Live GPU readiness is reported separately; Windflow is in private beta and brings capacity up on demand.
Input and control fit
Both models accept text prompts in the published Windflow profile. Both models accept reference or seed images in the published Windflow profile. Both models do not accept uploaded source clips in the published Windflow profile. Both models do not accept live webcam input in the published Windflow profile. Both models do not accept movement and look controls in the published Windflow profile.
A shared session API does not make commands interchangeable. Use each model's supported inputs and control timing. In particular, prompt changes may land at a chunk or generation-window boundary; movement input can represent persistent state until replaced.
What Helios is designed for
Helios is a 14-billion-parameter, open-source video diffusion model from the PKU-YuanGroup research lab, built to generate long video continuously rather than as a fixed-length clip. On Windflow it runs as a realtime session: you set the opening prompt, start the stream, and keep steering the same continuous clip while frames arrive live.
- Continuous generative video that never has to restart: ambient scenes, live backdrops, long takes.
- Prompt-steered storytelling where each prompt change continues the scene instead of cutting away.
- Image-to-video runs that start from a reference image and keep going.
- Prototyping interactive video products before committing to a heavier world model.
What LTX-2.5 is designed for
LTX-2.5 is Lightricks' 22-billion-parameter joint audio-and-video diffusion model. On Windflow it generates a stream window by window from a text prompt and an optional reference still, delivering video on main_video and the audio generated with it on main_audio, aligned per window.
- Audio-visual scenes where sound is generated with the picture rather than dubbed after.
- Continuous AI television or channel formats built from successive windows.
- Reference-still-anchored characters and settings across windows.
- Comparing a joint audio-video model with video-only alternatives on one protocol.
Compare a realistic session budget
- Helios: $0.0017 per ready second, or $1.02 for ten ready minutes.
- LTX-2.5: $0.0040 per ready second, or $2.40 for ten ready minutes.
Queueing and worker startup are free. A ready owner session can remain billable while delivery is paused or unwatched; release it when done. Independent sessions carry independent meters. Use the cost calculator to estimate your duration and daily sessions.
Evaluate before choosing
Use one repeatable input sequence, the same client and network, and equivalent output expectations. Record first visible frame, control-to-visible delay, frame gaps, scene continuity and rejected controls. Run several starts and a sustained session. If serving profiles differ, label the differences instead of treating displayed FPS as directly comparable native generation speed.
See the latency measurement guide and the model selector for a reproducible decision process.
Sources
- PKU-YuanGroup/Helios on GitHub — Apache-2.0
- Lightricks/LTX-2 on GitHub — LTX-2 Community License
- Lightricks/LTX-2.5 on Hugging Face
FAQ
Is Helios better than LTX-2.5?
The answer depends on the inputs, control behavior, quality and output your product requires. The published specifications identify capability differences; an application-level evaluation establishes performance for your scenario.
Can I switch between these models through the same API?
Windflow keeps the session lifecycle common. Your application must adapt to each model's supported inputs, commands, output tracks and generation timing.
Do the published prices guarantee available GPU capacity?
No. Rates and implementation status are catalog facts. Live readiness is a separate operational signal, and private-beta access is required to run sessions.