Add support for Helios-14B, a real-time long video generation model

🚀 Today, we are thrilled to release Helios: a 14B real-time long-video generation model! Could you help to support in DiffSynth-Studio, thank you so much! @Artiprocher @mi804 @mi804

💻 Code: https://github.com/PKU-YuanGroup/Helios
🏠 Page: https://pku-yuangroup.github.io/Helios-Page
📄 Paper: https://huggingface.co/papers/2603.04379

It’s completely wild—faster than 1.3B models and achieves this without using self-forcing. Welcome to the new era of video generation! 😎👇

🔹 True Single-GPU Extreme Speed ⚡️
No need to rely on traditional workarounds like KV-cache, quantization, sparse/linear attention, or TinyVAE. Helios hits an end-to-end 19.5 FPS on a single H100!

Training is also highly accessible: an 80GB VRAM can fit four 14B models.

🔹 Solving Long-Video "Drift" from the Core 🎥
Tired of visual drift and repetitive loops? We ditched traditional hacks (like error banks, self-forcing, or keyframe sampling).

Instead, our innovative training strategy simulates & eliminates drift directly, keeping minute-long videos incredibly coherent with stunning quality. ✨

🔹 3 Model Variants for Full Coverage 🛠️
With a unified architecture natively supporting T2V, I2V, and V2V, we are open-sourcing 3 flavors:

1️⃣ Base: Single-stage denoising for extreme high-fidelity.
2️⃣ Mid: Pyramid denoising + CFG-Zero for the perfect balance of quality & throughput.
3️⃣ Distilled: Adversarial Distillation (DMD) for ultra-fast, few-step generation.

🔹 Day-0 Ecosystem Ready 🌍
We wanted deployment to be a breeze from the second we launched. Helios drops with comprehensive Day-0 hardware and framework support:

✅ Huawei Ascend-NPU
✅ HuggingFace Diffusers
✅ vLLM-Omni
✅ SGLang-Diffusion

https://github.com/user-attachments/assets/44f3b95b-46f4-4670-bdb7-6913a2df9c89

Start by reading the linked Helios code, page, and paper, then inspect DiffSynth-Studio's existing model integrations. The issue names no DiffSynth-Studio files, tests, or entry points; completion would require defining and validating support for Helios's T2V, I2V, and V2V variants.