Stable Diffusion image maker

What it does

Images made from a text description, edits to your own photos, or code for your own image pipeline. The skill uses the Hugging Face Diffusers library with Stable Diffusion models, including SDXL and Flux. It covers text-to-image, image-to-image for changing style or quality, inpainting to refill a masked area, and outpainting to extend a picture. It adds ControlNet for guiding by edges, pose or depth, and LoRA for style tuning. It writes the Python and install steps. You need a computer with a capable graphics card and some Python knowledge. If you want no GPU, it points to hosted options.

What goes in and out

You give it

• A text description or a source image
• A mask for the area to change (optional)
• A computer with a GPU and Python. Know your GPU model and Python version before you start.
• A style or model preference (optional)

You get

• Python code that generates images
• Install steps
• Image-to-image and inpainting setups
• ControlNet and style tuning options

Full instructions

• Check that you have a computer with a graphics card and Python. If not, pick a hosted tool instead.
• Open Claude, ChatGPT or Gemini and paste this skill. Then describe the picture you want, or attach your photo.
• Install the packages your AI lists, starting with the pip install line for diffusers, transformers, accelerate and torch.
• Run the text-to-image code your AI gives you. The image is saved as output.png in the folder where you run it.
• If you see an out-of-memory error, ask your AI for the memory settings in this skill and run again.
• Before you use an image for business, check the licence of the model you chose. Then try image-to-image, inpainting or ControlNet to refine it. Check output.png first, and make small changes to the prompt and run it again until it looks right.

Full instruction file

Stable Diffusion Image Generation

Comprehensive guide to generating images with Stable Diffusion using the HuggingFace Diffusers library.

Before you start

Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait.

What you need (use your own material or the linked skill):

• Your question (yours): the decision or problem, and what a good outcome looks like.

How to start:

1. Look first. Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name.
2. Check what's missing. Look for your question. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps.
3. Do the job. Follow the skill below with the facts and tools you have. Mark each gap with MISSING: where it belongs and never invent a fact to fill it.

When to use Stable Diffusion

Use Stable Diffusion when:

• Generating images from text descriptions
• Performing image-to-image translation (style transfer, enhancement)
• Inpainting (filling in masked regions)
• Outpainting (extending images beyond boundaries)
• Creating variations of existing images
• Building custom image generation workflows

Key features:

• Text-to-Image: Generate images from natural language prompts
• Image-to-Image: Transform existing images with text guidance
• Inpainting: Fill masked regions with context-aware content
• ControlNet: Add spatial conditioning (edges, poses, depth)
• LoRA Support: Efficient fine-tuning and style adaptation
• Multiple Models: SD 1.5, SDXL, SD 3.0, Flux support

Use alternatives instead:

• DALL-E 3: For API-based generation without GPU
• Midjourney: For artistic, stylized outputs
• Imagen: For Google Cloud integration
• Leonardo.ai: For web-based creative workflows

Quick start

Installation

pip install diffusers transformers accelerate torch
pip install xformers  # Optional: memory-efficient attention

Basic text-to-image

from diffusers import DiffusionPipeline
import torch

# Load pipeline (auto-detects model type)
pipe = DiffusionPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    torch_dtype=torch.float16
)
pipe.to("cuda")

# Generate image
image = pipe(
    "A serene mountain landscape at sunset, highly detailed",
    num_inference_steps=50,
    guidance_scale=7.5
).images[0]

image.save("output.png")

Using SDXL (higher quality)

from diffusers import AutoPipelineForText2Image
import torch

pipe = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16"
)
pipe.to("cuda")

# Enable memory optimization
pipe.enable_model_cpu_offload()

image = pipe(
    prompt="A futuristic city with flying cars, cinematic lighting",
    height=1024,
    width=1024,
    num_inference_steps=30
).images[0]

Architecture overview

Three-pillar design

Diffusers is built around three core components:

Pipeline (orchestration)
├── Model (neural networks)
│   ├── UNet / Transformer (noise prediction)
│   ├── VAE (latent encoding/decoding)
│   └── Text Encoder (CLIP/T5)
└── Scheduler (denoising algorithm)

Pipeline inference flow

Text Prompt → Text Encoder → Text Embeddings
                                    ↓
Random Noise → [Denoising Loop] ← Scheduler
                      ↓
               Predicted Noise
                      ↓
              VAE Decoder → Final Image

Core concepts

Pipelines

Pipelines orchestrate complete workflows:

Schedulers

Schedulers control the denoising process:

Swapping schedulers

from diffusers import DPMSolverMultistepScheduler

# Swap for faster generation
pipe.scheduler = DPMSolverMultistepScheduler.from_config(
    pipe.scheduler.config
)

# Now generate with fewer steps
image = pipe(prompt, num_inference_steps=20).images[0]

Generation parameters

Key parameters

Reproducible generation

import torch

generator = torch.Generator(device="cuda").manual_seed(42)

image = pipe(
    prompt="A cat wearing a top hat",
    generator=generator,
    num_inference_steps=50
).images[0]

Negative prompts

image = pipe(
    prompt="Professional photo of a dog in a garden",
    negative_prompt="blurry, low quality, distorted, ugly, bad anatomy",
    guidance_scale=7.5
).images[0]

Image-to-image

Transform existing images with text guidance:

from diffusers import AutoPipelineForImage2Image
from PIL import Image

pipe = AutoPipelineForImage2Image.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    torch_dtype=torch.float16
).to("cuda")

init_image = Image.open("input.jpg").resize((512, 512))

image = pipe(
    prompt="A watercolor painting of the scene",
    image=init_image,
    strength=0.75,  # How much to transform (0-1)
    num_inference_steps=50
).images[0]

Inpainting

Fill masked regions:

from diffusers import AutoPipelineForInpainting
from PIL import Image

pipe = AutoPipelineForInpainting.from_pretrained(
    "runwayml/stable-diffusion-inpainting",
    torch_dtype=torch.float16
).to("cuda")

image = Image.open("photo.jpg")
mask = Image.open("mask.png")  # White = inpaint region

result = pipe(
    prompt="A red car parked on the street",
    image=image,
    mask_image=mask,
    num_inference_steps=50
).images[0]

ControlNet

Add spatial conditioning for precise control:

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
import torch

# Load ControlNet for edge conditioning
controlnet = ControlNetModel.from_pretrained(
    "lllyasviel/control_v11p_sd15_canny",
    torch_dtype=torch.float16
)

pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    controlnet=controlnet,
    torch_dtype=torch.float16
).to("cuda")

# Use Canny edge image as control.
# get_canny_image is not a library function: you supply the edge-map step. A simple version:
import cv2, numpy as np
from PIL import Image
def get_canny_image(img):
    edges = cv2.Canny(np.array(img.convert("RGB")), 100, 200)
    return Image.fromarray(np.stack([edges] * 3, axis=-1))

control_image = get_canny_image(input_image)  # input_image is your PIL photo

image = pipe(
    prompt="A beautiful house in the style of Van Gogh",
    image=control_image,
    num_inference_steps=30
).images[0]

Available ControlNets

LoRA adapters

Load fine-tuned style adapters:

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    torch_dtype=torch.float16
).to("cuda")

# Load LoRA weights
pipe.load_lora_weights("path/to/lora", weight_name="style.safetensors")

# Generate with LoRA style
image = pipe("A portrait in the trained style").images[0]

# Adjust LoRA strength
pipe.fuse_lora(lora_scale=0.8)

# Unload LoRA
pipe.unload_lora_weights()

Multiple LoRAs

# Load multiple LoRAs
pipe.load_lora_weights("lora1", adapter_name="style")
pipe.load_lora_weights("lora2", adapter_name="character")

# Set weights for each
pipe.set_adapters(["style", "character"], adapter_weights=[0.7, 0.5])

image = pipe("A portrait").images[0]

Memory optimization

Enable CPU offloading

# Model CPU offload - moves models to CPU when not in use
pipe.enable_model_cpu_offload()

# Sequential CPU offload - more aggressive, slower
pipe.enable_sequential_cpu_offload()

Attention slicing

# Reduce memory by computing attention in chunks
pipe.enable_attention_slicing()

# Or specific chunk size
pipe.enable_attention_slicing("max")

xFormers memory-efficient attention

# Requires xformers package
pipe.enable_xformers_memory_efficient_attention()

VAE slicing for large images

# Decode latents in tiles for large images
pipe.enable_vae_slicing()
pipe.enable_vae_tiling()

Model variants

Loading different precisions

# FP16 (recommended for GPU)
pipe = DiffusionPipeline.from_pretrained(
    "model-id",
    torch_dtype=torch.float16,
    variant="fp16"
)

# BF16 (better precision, requires Ampere+ GPU)
pipe = DiffusionPipeline.from_pretrained(
    "model-id",
    torch_dtype=torch.bfloat16
)

Loading specific components

from diffusers import UNet2DConditionModel, AutoencoderKL

# Load custom VAE
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")

# Use with pipeline
pipe = DiffusionPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    vae=vae,
    torch_dtype=torch.float16
)

Batch generation

Generate multiple images efficiently:

# Multiple prompts
prompts = [
    "A cat playing piano",
    "A dog reading a book",
    "A bird painting a picture"
]

images = pipe(prompts, num_inference_steps=30).images

# Multiple images per prompt
images = pipe(
    "A beautiful sunset",
    num_images_per_prompt=4,
    num_inference_steps=30
).images

Common workflows

Workflow 1: High-quality generation

from diffusers import StableDiffusionXLPipeline, DPMSolverMultistepScheduler
import torch

# 1. Load SDXL with optimizations
pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16"
)
pipe.to("cuda")
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

# 2. Generate with quality settings
image = pipe(
    prompt="A majestic lion in the savanna, golden hour lighting, 8k, detailed fur",
    negative_prompt="blurry, low quality, cartoon, anime, sketch",
    num_inference_steps=30,
    guidance_scale=7.5,
    height=1024,
    width=1024
).images[0]

Workflow 2: Fast prototyping

from diffusers import AutoPipelineForText2Image, LCMScheduler
import torch

# Use LCM for 4-8 step generation
pipe = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16
).to("cuda")

# Load LCM LoRA for fast generation
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.fuse_lora()

# Generate in ~1 second
image = pipe(
    "A beautiful landscape",
    num_inference_steps=4,
    guidance_scale=1.0
).images[0]

Common issues

CUDA out of memory:

# Enable memory optimizations
pipe.enable_model_cpu_offload()
pipe.enable_attention_slicing()
pipe.enable_vae_slicing()

# Or use lower precision
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)

Black/noise images:

# If the pipeline exposes a safety flag, inspect it without disabling the check.
result = pipe(prompt)
flags = getattr(result, "nsfw_content_detected", None)
print("Safety flag:", flags[0] if flags else "not exposed by this pipeline")

# A flag means review the prompt and follow the model or service policy.
# If there is no flag, check the VAE configuration and model compatibility.

# Ensure proper dtype consistency
pipe = pipe.to(dtype=torch.float16)

Slow generation:

# Use faster scheduler
from diffusers import DPMSolverMultistepScheduler
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)

# Reduce steps
image = pipe(prompt, num_inference_steps=20).images[0]

References

• Advanced Usage - Custom pipelines, fine-tuning, deployment
• Troubleshooting - Common issues and solutions

Resources

• Documentation: https://huggingface.co/docs/diffusers
• Repository: https://github.com/huggingface/diffusers
• Model Hub: https://huggingface.co/models?library=diffusers
• Discord: https://discord.gg/diffusers

After this

When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own:

• The Image maker and editor. It takes the image. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.