README.md

metadata

title: Krea Realtime Video • T2V ZeroGPU
emoji: 🎬
colorFrom: blue
colorTo: purple
sdk: gradio
app_file: app.py
pinned: false
hardware: zerogpu
python_version: 3.10.13

Krea Realtime Video

A Hugging Face Space for generating short videos with krea/krea-realtime-video, using Diffusers ModularPipeline and ZeroGPU.

This demo runs local text-to-video inference inside the Space and includes optional LoRA support for the Origami style.

Features

• Text-to-video generation with Krea Realtime Video 14B
• Diffusers ModularPipeline integration
• ZeroGPU-compatible runtime
• Manual style loading before generation
• Optional Origami LoRA support
• Automatic [origami] trigger insertion when the Origami style is active
• Adjustable video length and quality controls
• Progress feedback during generation

How to use

1. Enter a prompt describing the video you want to generate.
2. Optionally select a style.
3. If you select Origami, click Load style before generating.
4. Adjust:
   • Length: number of video blocks
   • Quality: inference steps per block
   • Seed: reproducibility seed
5. Click Generate video.

The generated video will appear on the right side of the interface.

Styles

Base model

Uses the original Krea Realtime Video model without any additional LoRA.

Origami

Uses the Origami LoRA adapter:

shauray/Origami_WanLora

When this style is active, the app automatically prefixes the prompt with:

[origami]

For example, this prompt:

a cat sitting on a boat

is internally sent as:

[origami] a cat sitting on a boat

Recommended settings

For a balanced result:

Length: 9
Quality: 6
Seed: any fixed integer

Lower values generate faster. Higher values may improve temporal consistency and visual quality, but can take longer.

Example prompts

Astronaut in a jungle, cold color palette, muted colors, detailed, cinematic, 8k

A tiny wooden boat drifting through a misty lake at sunrise, a curious cat sitting at the front, soft cinematic lighting, calm water reflections

A futuristic city at sunset, flying vehicles between glass towers, neon reflections, cinematic camera movement, atmospheric haze

A car racing down a snowy mountain road, dramatic chase shot, powder snow flying behind the wheels, cold blue lighting, high speed motion

A surreal underwater library, glowing jellyfish floating between bookshelves, slow cinematic dolly shot, dreamlike atmosphere

Origami examples:

a cat sitting on a boat

a dragon flying over a mountain village at sunrise, paper-folded geometry, delicate handmade texture, soft shadows

a small fox walking through a paper forest, handcrafted origami style, warm lantern light, cinematic close-up

Implementation notes

This Space uses a ZeroGPU compatibility path.

The original optimized inference path for Krea Realtime Video relies on features such as torch.compile and optimized attention kernels. In this Space, torch.compile is intentionally disabled to keep the runtime compatible with ZeroGPU.

The model is loaded when the Space starts. LoRA styles are loaded manually through the UI before generation, so the generation step can focus on inference.

Limitations

• The demo is intended for short video generation.
• Very long generations may be slower or less stable.
• The Origami style must be loaded once before it can be used.
• LoRA strength control is not exposed in the UI because the current adapter API used by this runtime does not reliably support per-adapter weights.
• ZeroGPU compatibility may be slower than a fully optimized dedicated GPU deployment.

Model

Base model:

krea/krea-realtime-video

Optional LoRA:

shauray/Origami_WanLora

Acknowledgements

This Space is built on top of the Hugging Face ecosystem, including Diffusers, Gradio, PEFT, and the Hugging Face Hub.