skills.rest
memoirlabs
memoirlabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

huggingface-image-generation

Generate and edit images via Hugging Face inference with seed control.

6|Updated Mar 26, 2026
Search Tags:#image generation#image editing#text-to-image#image-to-image#huggingface#prompt tuning#inference providers
One-click install
npx skills add https://github.com/memoirlabs/mog --skill huggingface-image-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: huggingface-image-generation
Source: https://github.com/memoirlabs/mog/tree/main/apps/mog/src/brain/skills/huggingface-image-generation
Command: npx skills add https://github.com/memoirlabs/mog --skill huggingface-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you produce high-quality images (or edit existing images) without hand-building complex inference logic, so you can ship marketing-ready visuals faster and more reliably.

Core Features & Use Cases

  • Hosted text-to-image and image-to-image workflows: Use Hugging Face Inference Providers for generating new images from prompts or transforming an input image with a prompt.
  • Model and parameter tuning: Support practical controls like model selection, prompt/negative prompt, seeds for reproducibility, and common generation settings such as dimensions and step counts.
  • Safe handling of returned image bytes: Return image data as blobs/bytes or as saved files, instead of breaking callers with unsafe token or filesystem practices.
  • Use Case: You need a repeatable campaign loop where each variation uses a specific seed and dimensions, and you want to swap between text-to-image and image-to-image depending on whether you’re ideating or doing revisions.

Quick Start

Use the huggingface-image-generation skill to generate a marketing hero image from the prompt “Bold minimal gradient background with subtle lighting, modern SaaS style” using model “black-forest-labs/FLUX.1-schnell” and a fixed seed for consistency.

Frequently Asked Questions about huggingface-image-generation

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

FAQPage Schema
How do I generate marketing images from text prompts using Hugging Face inference providers?▼

Hugging Face text-to-image generation lets you produce marketing visuals by sending prompts to inference providers. You select a model, set dimensions and step counts, and the Skill returns image bytes safely as blobs or files.

Can I use a fixed seed for reproducible image generation across campaign variations?▼

Yes, seed-based reproducibility allows you to generate consistent image variations. By setting a fixed seed alongside your prompt and dimensions, you can reliably reproduce the same output across different campaign iterations and text-to-image runs.

Do I need an HF_TOKEN environment variable to run Hugging Face image generation workflows?▼

Yes, this Skill requires reading an HF_TOKEN from your environment variables to authenticate with Hugging Face inference providers. You must configure this token before executing text-to-image or image-to-image generation tasks.

What is the difference between text-to-image and image-to-image workflows for product visuals?▼

Text-to-image creates new visuals from a prompt for initial ideation, while image-to-image transforms an existing input image using a prompt for revisions. Both support negative prompt tuning and dynamic model capability checks.

How are generated image bytes safely returned from Hugging Face inference calls?▼

Generated image bytes are returned safely as blobs, array buffers, or file responses. This approach prevents breaking callers with unsafe token or filesystem practices during text-to-image and image-to-image processing.

Can I use negative prompts and dynamic model selection for Hugging Face image editing?▼

Yes, the Skill supports prompt and negative prompt tuning alongside dynamic model and provider capability checks. This allows you to refine image-to-image edits by specifying elements to exclude and switching models dynamically.

Related Skills

Explore More Design & Creative Skills→
MCERQUAMCERQUA
1

hugging-face

Generate images, text, and embeddings via Hugging Face models.

Community
Advanced
joyz0joyz0

media-processing-design

Fetch, validate, process, store, and serve media files from URLs, uploads, and base64 blobs.

Community
Advanced
manashmandalmanashmandal

imggen

Generate images from text prompts using OpenAI image APIs and extract OCR text from images.

Community
Basic
MuhammadUAMuhammadUA

replicate

Execute cloud-hosted AI/ML models via the Replicate API for media generation.

Community
Intermediate