Skip to content
Back to skills

Web Demo

ASecurity

Routes DreamOmni2 Gradio demo launchers for editing and generation.

  • 247 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 8, 2026
tools

Works with

  • cli

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill web-demo --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Web Demo?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Web Demo
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-web-demo/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-web-demo)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: web-demo
description: "Routes DreamOmni2 Gradio demo launchers for editing and generation."
disable-model-invocation: true
metadata:
  disco-role: operating
license: Apache 2.0
---

# DreamOmni2 web demo

Use this sub-skill when the user wants to launch the DreamOmni2 browser UI instead of the one-shot CLI scripts.

## Typical triggers
- "launch the DreamOmni2 demo"
- "start the Gradio app"
- "run the editing web UI"
- "run the generation web UI"
- "what port does the demo use?"

## What belongs here
- The editing Gradio launcher
- The generation Gradio launcher
- Port, host, and browser-access troubleshooting
- UI-specific input-order guidance and demo startup checks

## What does not belong here
- One-shot command-line inference; use `sub-skills/inference/`
- Training or fine-tuning helpers
- Generic Gradio applications that are not DreamOmni2-specific

## Read these files first
- `references/workflows.md` for the launch commands and UI behavior
- `references/troubleshooting.md` for port, browser, model-load, and upload failures
- `../../references/model-setup.md` for the expected model directories
- `../../scripts/dreamomni2_common.py` for the shared model and prompt helpers used by the launchers

## Bundled scripts
- `scripts/web_edit.py` for the editing UI
- `scripts/web_generate.py` for the generation UI

## Workflow outline
1. Confirm which UI mode is needed: editing or generation.
2. Confirm the model paths and that the CUDA environment is ready.
3. Launch the chosen script with the desired host and port.
4. Open the browser, upload two images, and enter the instruction.
5. If the result is wrong, check the image order and the model-path configuration before touching the UI code.

## Decision points
- **Port selection**: the bundled launchers default to 7860 for editing and 7861 for generation, but both accept overrides.
- **Input order**: the editing UI still expects the source image first.
- **Examples**: the bundled launchers are intentionally not tied to the source checkout's sample images, so users should upload their own images or add local examples of their own.

## If you need more detail
Read the linked reference files when you need exact launch options, browser recovery steps, or a model-path check before starting the app.

Files in this skill

  • SKILL.md2.2 KB
  • references/troubleshooting.md1.8 KB
  • references/workflows.md1.8 KB
  • scripts/web_edit.py3.6 KB
  • scripts/web_generate.py3.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.