skills.rest
JamesFincher
JamesFincherCOMMUNITY
Explore all skills by this author →
GitHub

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers.

Updated May 4, 2026
Search Tags:#text-to-image#image-to-image#lora#inpainting#diffusers#stable diffusion#controlnet
One-click install
npx skills add https://github.com/JamesFincher/gengar --skill stable-diffusion-image-generation-jamesfincher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stable-diffusion-image-generation
Source: https://github.com/JamesFincher/gengar/tree/main/optional-skills/mlops/stable-diffusion
Command: npx skills add https://github.com/JamesFincher/gengar --skill stable-diffusion-image-generation-jamesfincher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you reliably turn text prompts (and optional reference images) into high-quality images using Stable Diffusion through HuggingFace Diffusers, removing the need to manually wire up complex diffusion pipelines.

Core Features & Use Cases

  • Text-to-Image generation: Create images directly from natural-language prompts with controllable quality via steps and guidance scale.
  • Image-to-Image translation: Transform an existing image using a prompt and a strength parameter to control how much to change.
  • Inpainting: Fill masked regions with prompt-guided content for edits like removing objects or correcting parts of an image.
  • Structured conditioning (ControlNet): Add spatial control (e.g., edges, pose, depth) to keep composition aligned with a reference.
  • Performance and quality controls: Switch schedulers, enable memory optimizations (CPU offload, slicing, xFormers), and select model variants (SD 1.x/SDXL/SD 3.0/Flux).
  • Quality and iteration workflows: Use SDXL refiner-style multi-stage generation patterns and reproducible seeds.

Quick Start

Use the stable-diffusion-image-generation skill to generate an image from the attached prompt by running text-to-image generation with Stable Diffusion via Diffusers.

Frequently Asked Questions about stable-diffusion-image-generation

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

FAQPage Schema
How do I generate images from text prompts using Stable Diffusion?▼

You generate images from text prompts using Stable Diffusion by configuring HuggingFace Diffusers pipelines with adjustable schedulers, inference steps, and guidance scale to produce photorealistic or stylized outputs.

Can I use ControlNet for spatially controlled image generation?▼

Yes, you can use ControlNet for spatially controlled generation, allowing you to maintain structural alignment with reference edges, poses, or depth maps while executing text-to-image or image-to-image tasks.

How does inpainting work with Stable Diffusion to edit specific image regions?▼

Inpainting with Stable Diffusion fills masked regions with prompt-guided content, enabling targeted edits like object removal or part correction while preserving the unmasked areas of the original image.

What's the best way to optimize Stable Diffusion memory usage on limited hardware?▼

To optimize Stable Diffusion memory usage, enable CPU offload, memory slicing, or xFormers alongside selecting fp16 or bf16 precision options within the HuggingFace Diffusers pipeline configuration.

Does HuggingFace Diffusers support image-to-image translation with existing photos?▼

Yes, HuggingFace Diffusers supports image-to-image translation, allowing you to transform an existing photo using a prompt and a strength parameter that controls the intensity of the visual modifications.

Do I need to manually configure diffusion pipelines to use different SD models?▼

No, you do not need to manually wire complex diffusion pipelines; this Skill allows you to seamlessly select and switch between model variants like SD 1.x, SDXL, SD 3.0, and Flux for your generation workflows.

Related Skills

Explore More Design & Creative Skills→
manashmandalmanashmandal

imggen

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

Community
Basic
shuyu-labsshuyu-labs
288

pptx

Generate and edit PowerPoint presentations with slides, layouts, and speaker notes.

Official
Advanced
JKhyroJKhyro

stable-diffusion-image-generation

Generate images from text prompts and source images using Stable Diffusion pipelines.

Community
Advanced
MesferAliMesferAli

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers.

Community
Advanced