skills.rest
aimentor606
aimentor606COMMUNITY
Explore all skills by this author →
GitHub

replicate

Run and compare AI/ML models via the Replicate API for media generation.

Updated Apr 8, 2026
Search Tags:#api#models#image-generation#replicate#audio-generation#video-generation#predictions
One-click install
npx skills add https://github.com/aimentor606/aether --skill replicate-aimentor606
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: replicate
Source: https://github.com/aimentor606/aether/tree/main/core/kortix-master/opencode/skills/GENERAL-KNOWLEDGE-WORKER/replicate
Command: npx skills add https://github.com/aimentor606/aether --skill replicate-aimentor606

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of discovering models, validating schemas, creating predictions, and retrieving ephemeral outputs from the Replicate API so you can reliably generate and transform AI-created media.

Core Features & Use Cases

  • Model discovery & validation: fetch model metadata and latest input schemas to validate parameters before running predictions.
  • Prediction orchestration: create predictions with randomized seeds, poll status, use synchronous wait or webhooks, and cancel or list predictions.
  • Media workflows: supports text-to-image, inpainting, upscaling, video and audio generation, embeddings and classification; for example, generate multiple image variations concurrently and save backups before output URLs expire.

Quick Start

Use the replicate skill to generate an image with model black-forest-labs/flux-1.1-pro from the prompt A serene mountain lake at sunrise and save the result locally.

Frequently Asked Questions about replicate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run text-to-image generation models using an API?▼

Replicate API text-to-image generation works by fetching model schemas, creating predictions, and polling status until outputs are ready for download. It supports concurrent variations and external model execution.

Why do my generated media URLs expire and how do I save outputs?▼

Generated media URLs expire because Replicate outputs are ephemeral. You must download or save outputs locally before URL expiry, immediately after polling confirms the prediction status is complete.

Do I need an API token to create predictions for video and audio generation?▼

Yes, you need a REPLICATE_API_TOKEN to authenticate and create predictions for video and audio generation. The token allows fetching model metadata, running inference jobs, and managing prediction orchestration.

Can I use webhooks instead of polling to check prediction status?▼

Yes, you can use webhooks instead of synchronous polling to check prediction status. The prediction orchestration supports both synchronous wait polling and webhooks to handle asynchronous inference jobs efficiently.

What's the best way to validate input parameters before running an inference job?▼

The best way to validate input parameters is to fetch model metadata and the latest input schemas before running the inference job. This ensures parameter accuracy before creating predictions via the API.

Does this approach support inpainting and upscaling workflows?▼

Yes, this approach supports inpainting and upscaling workflows alongside text-to-speech and classification tasks. It handles media workflows by orchestrating predictions across various AI/ML models for transformation and generation.

Related Skills

Explore More Design & Creative Skills→
benjaminshafiibenjaminshafii
10

bitwarden

Configure Bitwarden CLI with API key authentication to retrieve vault credentials.

Community
Intermediate
sellersessionssellersessions

dashboard-auto-generation-client

Generate standalone HTML dashboards from CSV, Excel, JSON, or TSV files.

Community
Advanced
fcamacholfcamachol

seguimiento

Monitor registration process statuses and trigger change notifications.

Community
Basic
GroundMountCompanyGroundMountCompany

ai-image-generation

Automate AI image generation via Replicate API with model selection and iterative refinement.

Community
Intermediate