mirror of https://github.com/Comfy-Org/ComfyUI_frontend.git synced 2026-04-20 14:30:41 +00:00

Files

dante01yoon bbd0a6b201 feat: migrate workflow template site as apps/hub

Migrate workflow_templates/site into the frontend monorepo as apps/hub
so the hub can use @comfyorg/design-system and shared packages.

Changes to existing files:
- pnpm-workspace.yaml: add @astrojs/sitemap, @astrojs/vercel, lucide-vue-next
- eslint.config.ts: add hub ignores and i18n/import rule overrides
- .oxlintrc.json: add hub scripts to ignore patterns
- knip.config.ts: add hub workspace config

apps/hub adaptations from source:
- Replace local cn() with @comfyorg/tailwind-utils (19 files)
- Integrate @comfyorg/design-system/css/base.css in global.css
- Make TEMPLATES_DIR configurable via HUB_TEMPLATES_DIR env var
- Add HUB_SKIP_SYNC flag for builds without template data
- Remove Vite 8-incompatible rollupOptions.output.manualChunks
- Fix stylelint violations (modern color notation, number precision)
- Gitignore generated content (thumbnails, synced templates, AI cache)

2026-04-06 20:53:13 +09:00

2.2 KiB

Raw Blame History

Vidu

Vidu is a video generation API developed by ShengShu Technology. It supports text-to-video, image-to-video, reference-to-video with multi-entity consistency, and start-end frame interpolation. Vidu is known for fast generation speeds (as low as 10 seconds) and strong anime-style output.

Model Variants

Vidu 2.0

Extended 8-second video generation at up to 1080p
Text-to-video and image-to-video modes
First and last frame control for transitions
Available via the Vidu API and third-party platforms

Vidu Q1

Reference-to-video with multi-entity consistency
Supports up to 7 reference images with semantic understanding
Infers missing elements from text prompts and reference context
Generates coherent scenes combining multiple characters, objects, and environments

Vidu Q2

Optimized for quality and speed balance
Supports 6-8 second generation at up to 1080p
1080p image generation included in higher tiers

Vidu Q3

Latest generation model with improved output quality
Available through the Vidu platform and API

Key Features

Ultra-fast inference (videos generated in as few as 10 seconds)
Multi-entity consistency across characters, objects, and scenes
First and last frame control for precise transitions
Superior anime and 2D animation quality
Up to 1080p resolution output with multiple aspect ratios
Optimized scene templates for interactive effects and e-commerce

Hardware Requirements

Cloud API only; no local hardware required
Accessed via platform.vidu.com or third-party API providers
Credit-based pricing with free tier available

Common Use Cases

Anime and 2D animation series production
E-commerce product video creation
Social media content (TikTok, Reels, Shorts)
Reference-based multi-character storytelling
Marketing and advertising videos
Start-end frame transitions and morphing effects

Key Parameters

prompt: Text description of desired video content
image_url: Source image for image-to-video generation
duration: Video length (4-8 seconds depending on model)
resolution: Output resolution (720p or 1080p)
style: Visual style selection (realistic or animated)
movement_amplitude: Controls intensity of motion in output

2.2 KiB Raw Blame History