Stable Diffusion

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

from diffusers import DiffusionPipeline


# 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")

from diffusers import AutoPipelineForText2Image


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]

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

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

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]

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]

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]

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]

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]

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel


# 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
control_image = get_canny_image(input_image)

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

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()

# 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]

# 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()

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

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

# Requires xformers package
pipe.enable_xformers_memory_efficient_attention()

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

# 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
)

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
)

# 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

from diffusers import StableDiffusionXLPipeline, DPMSolverMultistepScheduler


# 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]

from diffusers import AutoPipelineForText2Image, LCMScheduler


# 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]

# 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)

# Check VAE configuration
# Use safety checker bypass if needed
pipe.safety_checker = None

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

# 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]