Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Improved routing: added negative examples and pipeline info
What This Skill Does
Takes a single source image and generates 10 PNG variations with different camera angles, perspectives, and compositions via ComfyDeploy's MULTISHOT-UGC workflow. Designed to feed into lip-sync video tools like VEED for multi-shot UGC-style ads.
Eliminates the need to manually stage or photograph multiple angles by deriving all shot variations from a single source image.
When to use it
- Creating varied camera angles from one product photo
- Building multi-scene UGC ads without reshooting
- Getting close-up and wide-shot versions of a hero image
- Generating shot options to pick the best 4 for a video edit
- Producing 9:16 vertical variations for social media content
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate 10 angle variations of ./hero-product.png for a UGC video
- 1Calls generate.py with --image ./hero-product.png and --output-dir ./shots
- 2Submits job to ComfyDeploy deployment 9ccbb29a via queue API
- 3Polls for completion (takes ~2-3 minutes)
- 4Downloads 10 PNG files named 1_00001_.png through 10_00001_.png to ./shots
10 perspective variations saved to ./shots/, ready for VEED lip-sync selection
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.