2.6k
GitHub Stars
2
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill eachlabs-fashion-ai- _meta.json298 B
- SKILL.md5.7 KB
Overview
This skill generates high-quality fashion model imagery, virtual try-on results, runway videos, and campaign visuals using EachLabs AI models. It provides targeted model recommendations and workflows for image generation, image-to-image garment transfer, video catwalks, and brand style training. Use it to produce consistent, professional fashion content at scale.
How this skill works
The skill validates model availability, then creates predictions via EachLabs API with a model slug and input matching the model's request schema. It supports image generation, image-to-image virtual try-on, motion-driven video generation, and LoRA-style brand training. Polling the prediction endpoint returns the result URLs for downloaded images or video outputs.
When to use it
- Create editorial or e-commerce model photography from text prompts
- Produce virtual try-on mockups by combining garment and model images
- Generate short runway or catwalk videos for campaigns and lookbooks
- Train a brand-specific style model (LoRA) for consistent campaign visuals
- Animate a model using real motion reference for choreography or catwalks
Best practices
- Always call the model metadata endpoint first to get the exact request_schema and required parameters
- Supply clear prompts with pose, lighting, and style keywords (e.g., "full body shot", "editorial studio lighting")
- For virtual try-on, provide high-quality, front-facing garment and model images with consistent scale
- Use consistent style keywords and reference images across a campaign to preserve visual coherence
- Specify resolution, duration, and quality explicitly for video outputs to avoid rework
Example use cases
- Generate a series of lookbook images in a unified editorial style for seasonal campaigns
- Create virtual try-on previews by compositing product photos onto model images for e-commerce listings
- Produce a 5–10 second runway clip showing a model walking a branded catwalk for social promotion
- Train a brand style LoRA from a ZIP of campaign images to reproduce signature color grading and styling
- Animate a model using a runway reference video to create motion-rich advertising clips
FAQ
Use an API key in the X-API-Key header and set EACHLABS_API_KEY in your environment.
How do I ensure consistent character or model appearance across images?
Use the same model, repeat identical style prompts and reference images, and consider a consistency model such as Omni Zero or train a portrait LoRA for the brand.