Stable Diffusion Image Generation

# Stable Diffusion Advanced Usage Guide

## Custom Pipelines

### Building from components

```python
from diffusers import (
    UNet2DConditionModel,
    AutoencoderKL,
    DDPMScheduler,
    StableDiffusionPipeline
)
from transformers import CLIPTextModel, CLIPTokenizer
import torch

# Load components individually
unet = UNet2DConditionModel.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    subfolder="unet"
)
vae = AutoencoderKL.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    subfolder="vae"
)
text_encoder = CLIPTextModel.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    subfolder="text_encoder"
)
tokenizer = CLIPTokenizer.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    subfolder="tokenizer"
)
scheduler = DDPMScheduler.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    subfolder="scheduler"
)

# Assemble pipeline
pipe = StableDiffusionPipeline(
    unet=unet,
    vae=vae,
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    scheduler=scheduler,
    safety_checker=None,
    feature_extractor=None,
    requires_safety_checker=False
)
```

### Custom denoising loop

```python
from diffusers import DDIMScheduler, AutoencoderKL, UNet2DConditionModel
from transformers import CLIPTextModel, CLIPTokenizer
import torch

def custom_generate(
    prompt: str,
    num_steps: int = 50,
    guidance_scale: float = 7.5,
    height: int = 512,
    width: int = 512
):
    # Load components
    tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
    text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")
    unet = UNet2DConditionModel.from_pretrained("sd-model", subfolder="unet")
    vae = AutoencoderKL.from_pretrained("sd-model", subfolder="vae")
    scheduler = DDIMScheduler.from_pretrained("sd-model", subfolder="scheduler")

    device = "cuda"
    text_encoder.to(device)
    unet.to(device)
    vae.to(device)

    # Encode prompt
    text_input = tokenizer(
        prompt,
        padding="max_length",
        max_length=77,
        truncation=True,
        return_tensors="pt"
    )
    text_embeddings = text_encoder(text_input.input_ids.to(device))[0]

    # Unconditional embeddings for classifier-free guidance
    uncond_input = tokenizer(
        "",
        padding="max_length",
        max_length=77,
        return_tensors="pt"
    )
    uncond_embeddings = text_encoder(uncond_input.input_ids.to(device))[0]

    # Concatenate for batch processing
    text_embeddings = torch.cat([uncond_embeddings, text_embeddings])

    # Initialize latents
    latents = torch.randn(
        (1, 4, height // 8, width // 8),
        device=device
    )
    latents = latents * scheduler.init_noise_sigma

    # Denoising loop
    scheduler.set_timesteps(num_steps)
    for t in scheduler.timesteps:
        latent_model_input = torch.cat([latents] * 2)
        latent_model_input = scheduler.scale_model_input(latent_model_input, t)

        # Predict noise
        with torch.no_grad():
            noise_pred = unet(
                latent_model_input,
                t,
                encoder_hidden_states=text_embeddings
            ).sample

        # Classifier-free guidance
        noise_pred_uncond, noise_pred_cond = noise_pred.chunk(2)
        noise_pred = noise_pred_uncond + guidance_scale * (
            noise_pred_cond - noise_pred_uncond
        )

        # Update latents
        latents = scheduler.step(noise_pred, t, latents).prev_sample

    # Decode latents
    latents = latents / vae.config.scaling_factor
    with torch.no_grad():
        image = vae.decode(latents).sample

    # Convert to PIL
    image = (image / 2 + 0.5).clamp(0, 1)
    image = image.cpu().permute(0, 2, 3, 1).numpy()
    image = (image * 255).round().astype("uint8")[0]

    return Image.fromarray(image)
```

## IP-Adapter

Use image prompts alongside text:

```python
from diffusers import StableDiffusionPi