# 快速入门

Diffusers 是一个面向开发者和研究人员的库，提供了用于生成图像、视频和音频的便捷推理 API，以及用于实现新工作流的构建模块。

Diffusers 提供了许多开箱即用的优化功能，使得在内存有限的设备上加载和运行大型模型成为可能，或加速推理过程。

本快速入门将带你概览 Diffusers，并让你快速上手生成内容。

> [!TIP]
> 在开始之前，请确保您拥有一个 Hugging Face [账户](https://huggingface.co/join)，以便使用 [Flux](https://huggingface.co/black-forest-labs/FLUX.1-dev) 等受控模型。如果您打算构建自定义流水线，请参阅 [Modular Diffusers 快速入门](./modular_diffusers/quickstart) 和 [概述](./modular_diffusers/overview)。

如果尚未安装 Diffusers，请按照[安装](./installation)指南进行安装。

## Agent 提示

将此内容粘贴到您的编码代理中，以完成 Diffusers 的推理环境配置。

```text
Help me get set up with Hugging Face Diffusers for inference.

1. Install Diffusers for my environment with `uv pip install "diffusers[torch]"`.
2. If I need gated Hub models, help me authenticate to the Hugging Face Hub.
3. Install Diffusers coding agent skills with `diffusers-cli skills add diffusers-cli`. Pass `--cursor`, `--claude`, or `--codex` if auto-detect fails. Optionally pass `--all` to install every skill in the registry.
4. Run a first text-to-image with DiffusionPipeline or `diffusers-cli run`, using a small or current Quickstart model and the right `device_map` for my machine.
5. Ask what I want next and point me at the matching docs.
```

## DiffusionPipeline

[DiffusionPipeline](/docs/diffusers/v0.43.0/zh/api/pipelines/overview#diffusers.DiffusionPipeline) packages the pieces of a diffusion model (text encoder, scheduler, UNet or DiT, and VAE) into one class for inference. Load with [from_pretrained()](/docs/diffusers/v0.43.0/zh/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained), then call the pipeline.

`__call__()` 中的参数（例如 `num_inference_steps`）会影响生成质量和速度。有关加载详情以及组件的混合搭配，请参阅 [加载流水线](./using-diffusers/loading)。如需更换调度器，请参阅 [调度器](./using-diffusers/schedulers)。

以下示例使用默认参数值。

使用 `.images[0]` 访问生成的图像输出。

```py
import torch
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
  "Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda"  # or "mps", "xpu", "cpu"
)

prompt = """
cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
"""
pipeline(prompt).images[0]
```

使用 `.frames[0]` 访问生成的视频输出，并使用 [export_to_video()](/docs/diffusers/v0.43.0/zh/api/utilities#diffusers.utils.export_to_video) 保存视频。

```py
import torch
from diffusers import AutoencoderKLWan, DiffusionPipeline
from diffusers.utils import export_to_video

vae = AutoencoderKLWan.from_pretrained(
  "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
  subfolder="vae",
  dtype=torch.float32
)
pipeline = DiffusionPipeline.from_pretrained(
  "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
  vae=vae,
  dtype=torch.bfloat16,
  device_map="cuda"  # or "mps", "xpu", "cpu"
)

prompt = """
Cinematic video of a sleek cat lounging on a colorful inflatable in a crystal-clear turquoise pool in Palm Springs, 
sipping a salt-rimmed margarita through a straw. Golden-hour sunlight glows over mid-century modern homes and swaying palms. 
Shot in rich Sony a7S III: with moody, glamorous color grading, subtle lens flares, and soft vintage film grain. 
Ripples shimmer as a warm desert breeze stirs the water, blending luxury and playful charm in an epic, gorgeously composed frame.
"""
video = pipeline(prompt=prompt, num_frames=81, num_inference_steps=40).frames[0]
export_to_video(video, "output.mp4", fps=16)
```

## LoRA

[LoRA](./tutorials/using_peft_for_inference) 适配器会在基础流水线之上添加一个小型的风格或主题检查点。使用 [load_lora_weights()](/docs/diffusers/v0.43.0/zh/api/loaders/lora#diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights) 加载其中一个。某些 LoRA 需要触发短语。请查看该 LoRA 的模型卡。

```py
import torch
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
  "Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda"  # or "mps", "xpu", "cpu"
)
pipeline.load_lora_weights(
  "threecrowco/VolkClipartQwen",
  weight_name="pytorch_lora_weights.safetensors",
)

prompt = """
Volk clipart style drawing of a cat sipping a margarita in a pool in Palm Springs, California, flat colors, bold outlines, simple shapes
"""
pipeline(prompt).images[0]
```

## 量化与优化

大型模型通常需要更少的内存或更高的速度。使用 [量化](./quantization/overview) 来缩小内存中的权重，并使用 [compile_repeated_blocks()](/docs/diffusers/v0.43.0/zh/api/models/overview#diffusers.ModelMixin.compile_repeated_blocks) 来加速后续的生成过程。有关 [模型卸载](./optimization/memory#model-offloading) 及其他选项，请参阅 [优化与扩展](./stable_diffusion)。

要减少内存占用，请使用 bitsandbytes 以 4 位精度加载。

```py
import torch
from diffusers import DiffusionPipeline
from diffusers.quantizers import PipelineQuantizationConfig

quant_config = PipelineQuantizationConfig(
  quant_backend="bitsandbytes_4bit",
  quant_kwargs={"load_in_4bit": True, "bnb_4bit_quant_type": "nf4", "bnb_4bit_compute_dtype": torch.bfloat16},
  components_to_quantize=["transformer", "text_encoder"],
)
pipeline = DiffusionPipeline.from_pretrained(
  "Qwen/Qwen-Image",
  dtype=torch.bfloat16,
  quantization_config=quant_config,
  device_map="cuda"  # or "mps", "xpu", "cpu"
)

prompt = """
cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
"""
pipeline(prompt).images[0]
```

为了加快后续运行速度，请对 transformer 中重复出现的块进行编译。编译后的首次 generate 属于冷启动，速度较慢。之后的 generate 会更快。

```py
import torch
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
  "Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda"  # or "mps", "xpu", "cpu"
)
pipeline.transformer.compile_repeated_blocks(fullgraph=True)

prompt = """
cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
"""
pipeline(prompt).images[0]
```

## 后续步骤

- [推理](./using-diffusers/loading) — 流水线、提示词和适配器
- [优化与扩展](./stable_diffusion) — 内存、速度、量化和推理服务
- [模块化 Diffusers](./modular_diffusers/overview) — 可组合的模块和自定义流水线
- [训练与微调](./training/overview) — 训练脚本和适配器
- [CLI](./using-diffusers/cli) — 从命令行生成