From a6d2fc2c1d307b2c7efb83417f49597800a79ff1 Mon Sep 17 00:00:00 2001
From: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Date: Wed, 13 Aug 2025 11:14:21 -0700
Subject: [PATCH] [docs] Refresh effective and efficient doc (#12134)
* refresh
* init
* feedback
---
docs/source/en/_toctree.yml | 2 +-
docs/source/en/stable_diffusion.md | 295 ++++++++---------------------
2 files changed, 81 insertions(+), 216 deletions(-)
diff --git a/docs/source/en/_toctree.yml b/docs/source/en/_toctree.yml
index 4013efe2dc..ff7d050619 100644
--- a/docs/source/en/_toctree.yml
+++ b/docs/source/en/_toctree.yml
@@ -7,7 +7,7 @@
- local: quicktour
title: Quicktour
- local: stable_diffusion
- title: Effective and efficient diffusion
+ title: Basic performance
- title: DiffusionPipeline
isExpanded: false
diff --git a/docs/source/en/stable_diffusion.md b/docs/source/en/stable_diffusion.md
index e43bcf3eaa..bc3dcbdc1c 100644
--- a/docs/source/en/stable_diffusion.md
+++ b/docs/source/en/stable_diffusion.md
@@ -10,252 +10,117 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
specific language governing permissions and limitations under the License.
-->
-# Effective and efficient diffusion
-
[[open-in-colab]]
-Getting the [`DiffusionPipeline`] to generate images in a certain style or include what you want can be tricky. Often times, you have to run the [`DiffusionPipeline`] several times before you end up with an image you're happy with. But generating something out of nothing is a computationally intensive process, especially if you're running inference over and over again.
+# Basic performance
-This is why it's important to get the most *computational* (speed) and *memory* (GPU vRAM) efficiency from the pipeline to reduce the time between inference cycles so you can iterate faster.
+Diffusion is a random process that is computationally demanding. You may need to run the [`DiffusionPipeline`] several times before getting a desired output. That's why it's important to carefully balance generation speed and memory usage in order to iterate faster,
-This tutorial walks you through how to generate faster and better with the [`DiffusionPipeline`].
+This guide recommends some basic performance tips for using the [`DiffusionPipeline`]. Refer to the Inference Optimization section docs such as [Accelerate inference](./optimization/fp16) or [Reduce memory usage](./optimization/memory) for more detailed performance guides.
-Begin by loading the [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) model:
+## Memory usage
-```python
+Reducing the amount of memory used indirectly speeds up generation and can help a model fit on device.
+
+```py
+import torch
from diffusers import DiffusionPipeline
-model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
-pipeline = DiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
+pipeline = DiffusionPipeline.from_pretrained(
+ "stabilityai/stable-diffusion-xl-base-1.0",
+ torch_dtype=torch.bfloat16
+).to("cuda")
+pipeline.enable_model_cpu_offload()
+
+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]
+print(f"Max memory reserved: {torch.cuda.max_memory_allocated() / 1024**3:.2f} GB")
```
-The example prompt you'll use is a portrait of an old warrior chief, but feel free to use your own prompt:
+## Inference speed
-```python
-prompt = "portrait photo of a old warrior chief"
-```
+Denoising is the most computationally demanding process during diffusion. Methods that optimizes this process accelerates inference speed. Try the following methods for a speed up.
-## Speed
+- Add `.to("cuda")` to place the pipeline on a GPU. Placing a model on an accelerator, like a GPU, increases speed because it performs computations in parallel.
+- Set `torch_dtype=torch.bfloat16` to execute the pipeline in half-precision. Reducing the data type precision increases speed because it takes less time to perform computations in a lower precision.
-
-
-💡 If you don't have access to a GPU, you can use one for free from a GPU provider like [Colab](https://colab.research.google.com/)!
-
-
-
-One of the simplest ways to speed up inference is to place the pipeline on a GPU the same way you would with any PyTorch module:
-
-```python
-pipeline = pipeline.to("cuda")
-```
-
-To make sure you can use the same image and improve on it, use a [`Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) and set a seed for [reproducibility](./using-diffusers/reusing_seeds):
-
-```python
+```py
import torch
+import time
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
-generator = torch.Generator("cuda").manual_seed(0)
+pipeline = DiffusionPipeline.from_pretrained(
+ "stabilityai/stable-diffusion-xl-base-1.0",
+ torch_dtype=torch.bfloat16
+).to("cuda")
```
-Now you can generate an image:
-
-```python
-image = pipeline(prompt, generator=generator).images[0]
-image
-```
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-