Skip to main content

​
Get Started with Scope

Daydream Scope is an open-source tool for running and customizing real-time interactive generative AI pipelines and models. Follow these steps to install Scope and create your first generation.

​
Supported Pipelines

Scope supports five autoregressive video diffusion models:

StreamDiffusion V2

Real-time video generation with streaming capabilities for immediate visual feedback

LongLive

Extended generation capabilities for longer video sequences with consistent quality

Krea Realtime

14B model for higher quality generation (requires ≥32GB VRAM)

RewardForcing

Trained with Rewarded Distribution Matching for improved output quality

MemFlow

Memory bank architecture for better long-context consistency

​
Prerequisites

For Desktop App or Local Installation:
  • NVIDIA GPU with ≥24GB VRAM (RTX 4090/5090 or similar)
  • CUDA 12.8+ drivers
  • Windows or Linux
For Cloud (RunPod):
  • RunPod account with credits
  • Similar GPU requirements apply to your instance selection

Full System Requirements

View detailed hardware specs, pipeline-specific VRAM needs, and software dependencies
Krea Realtime requires ≥32GB VRAM (≥40GB recommended for higher resolutions).

​
Step 1: Install Scope

Choose your installation method:
Best for: Windows users who want the easiest installation experience
The Daydream Scope desktop app is an Electron-based application that provides the simplest way to get Scope running on your Windows machine.
1

Download the installer

Visit the Daydream Scope releases page on GitHub.Select the latest release (or the version you want to install).
2

Find the Windows installer

Expand the Assets section at the bottom of the release.Download the file ending in .exe.
3

Install the application

Run the downloaded .exe file and follow the standard Windows installation prompts.
4

Launch Scope

Once installed, launch Daydream Scope from your Start menu or desktop shortcut.

​
Step 2: Your First Generation

Once Scope is running, open the interface at localhost:8000 (or your RunPod URL).

​
What You’ll See

  • Default mode: Video mode with a looping cat test video
  • Default prompt: “a dog walking in grass”
  • Expected speed: ~8 FPS (varies by hardware)

​
Try Updating the Prompt

Change the prompt in real-time and watch the video transform:
  • “a cow walking in grass”
  • “a dragon flying through clouds”
  • “a robot walking on mars”
The video transforms based on your prompt while maintaining the structure and motion of the original.

​
Try Community Examples

Want to see what’s possible? Import timeline files from these community projects:

Factory Fire to Rain

A dramatic real-time transition from industrial calm to explosion to storm — showcasing narrative arcs with LongLive

Urban Battlefield

AAA game-style cinematic of a soldier in a war zone — powered by Krea Realtime 14B

Origami Christmas Vibes

A cozy paper-craft holiday scene with gentle evolution — demonstrating atmosphere and stability with LongLive
Each project page includes downloadable timeline files you can import into Scope to replay and remix.
Success! You just generated your first real-time AI video.

​
Step 3: Connect, Share & Contribute

Community Hub

Browse creations, download timelines, and share your work

Join Discord

Get help, share creations, and connect in our #scope channel

Contribute on GitHub

Report issues, suggest features, or contribute code

​
Troubleshooting

Run nvidia-smi and verify CUDA version is ≥ 12.8. Update your NVIDIA drivers if needed.
  • Ensure UV, Node.js, and npm are properly installed
  • Try clearing the cache: uv cache clean && uv run build
Install the Python development package:
# Debian/Ubuntu
sudo apt-get install python3-dev
  • Check your internet connection
  • Verify disk space in ~/.daydream-scope/models
  • Model downloads can be large — be patient on first run
  • Verify the instance is fully deployed in RunPod dashboard
  • Ensure you’re accessing port 8000
  • Check that HF_TOKEN is correctly set
  • Verify your HF_TOKEN is valid with read permissions
  • Try redeploying the instance with the correct token