Personal avatar set from one photo
Create multiple avatar styles from one portrait
Place a product into a realistic scene without changing shape
Use this skill when you need a repeatable image workflow, not a one-off prompt guess. It defines the input, output, tool path, and quality gate before generation starts.
Strong ecommerce use case
Create product scene from packshot image, using a task-first workflow instead of a loose prompt dump.
background-replacement, reference-consistency
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: Product scene from packshot
Scene: Business / Product hero images
Input: packshot image
Output: product scene
Tools: ComfyUI inpainting, IP-Adapter, GPT Image 2
Quality check: the result must match the promised output and preserve the user intent.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
Create product scene for this task: Place a product into a realistic scene without changing shape
Input available: packshot image
Preferred tool path: ComfyUI inpainting, IP-Adapter, GPT Image 2
Keep the result faithful to the input and optimize for the product hero images scene.
Create multiple avatar styles from one portrait
Create movie-poster style portraits from one face
Generate consistent section-divider images for a deck