Skip to content

Commit b27b69c

Browse files
stevhliustevhliu
authored
[docs] Improve navigation (#14537)
* docs * rearrange * cross links * titles
1 parent a71e62e commit b27b69c

5 files changed

Lines changed: 142 additions & 118 deletions

File tree

‎docs/source/en/_toctree.yml‎

Lines changed: 134 additions & 118 deletions
Original file line numberDiff line numberDiff line change
@@ -5,73 +5,71 @@
55
title: Installation
66
- local: quicktour
77
title: Quickstart
8-
- local: stable_diffusion
9-
title: Basic performance
8+
- local: using-diffusers/cli
9+
title: Command line interface
1010
title: Get started
11-
- isExpanded: false
12-
sections:
13-
- local: using-diffusers/loading
14-
title: DiffusionPipeline
15-
- local: tutorials/autopipeline
16-
title: AutoPipeline
17-
- local: using-diffusers/custom_pipeline_overview
18-
title: Community pipelines and components
19-
- local: using-diffusers/callback
20-
title: Pipeline callbacks
21-
- local: using-diffusers/reusing_seeds
22-
title: Reproducibility
23-
- local: using-diffusers/schedulers
24-
title: Schedulers
25-
- local: using-diffusers/guiders
26-
title: Guiders
27-
- local: using-diffusers/automodel
28-
title: AutoModel
29-
- local: using-diffusers/other-formats
30-
title: Model formats
31-
- local: using-diffusers/push_to_hub
32-
title: Sharing pipelines and models
33-
title: Pipelines
34-
- isExpanded: false
35-
sections:
36-
- local: tutorials/using_peft_for_inference
37-
title: LoRA
38-
- local: using-diffusers/ip_adapter
39-
title: IP-Adapter
40-
- local: using-diffusers/controlnet
41-
title: ControlNet
42-
- local: using-diffusers/t2i_adapter
43-
title: T2I-Adapter
44-
- local: using-diffusers/dreambooth
45-
title: DreamBooth
46-
- local: using-diffusers/textual_inversion_inference
47-
title: Textual inversion
48-
title: Adapters
49-
- isExpanded: false
11+
- isExpanded: true
5012
sections:
51-
- local: using-diffusers/weighted_prompts
52-
title: Prompting
53-
- local: using-diffusers/create_a_server
54-
title: Create a server
55-
- local: using-diffusers/batched_inference
56-
title: Batch inference
57-
- local: training/distributed_inference
58-
title: Distributed inference
59-
- local: hybrid_inference/overview
60-
title: Remote inference
13+
- isExpanded: false
14+
sections:
15+
- local: using-diffusers/weighted_prompts
16+
title: Prompting
17+
- local: using-diffusers/loading
18+
title: DiffusionPipeline
19+
- local: tutorials/autopipeline
20+
title: AutoPipeline
21+
- local: using-diffusers/custom_pipeline_overview
22+
title: Community pipelines and components
23+
- local: using-diffusers/callback
24+
title: Pipeline callbacks
25+
- local: using-diffusers/reusing_seeds
26+
title: Reproducibility
27+
- local: using-diffusers/schedulers
28+
title: Schedulers
29+
- local: using-diffusers/guiders
30+
title: Guiders
31+
- local: using-diffusers/automodel
32+
title: AutoModel
33+
- local: using-diffusers/other-formats
34+
title: Model formats
35+
- local: using-diffusers/push_to_hub
36+
title: Sharing pipelines and models
37+
title: Using diffusion pipelines
38+
- isExpanded: false
39+
sections:
40+
- local: tutorials/using_peft_for_inference
41+
title: LoRA
42+
- local: using-diffusers/ip_adapter
43+
title: IP-Adapter
44+
- local: using-diffusers/controlnet
45+
title: ControlNet
46+
- local: using-diffusers/t2i_adapter
47+
title: T2I-Adapter
48+
- local: using-diffusers/dreambooth
49+
title: DreamBooth
50+
- local: using-diffusers/textual_inversion_inference
51+
title: Textual inversion
52+
title: Adapters and personalization
6153
title: Inference
62-
- isExpanded: false
54+
- isExpanded: true
6355
sections:
64-
- local: optimization/fp16
65-
title: Accelerate inference
66-
- local: optimization/cache
67-
title: Caching
68-
- local: optimization/attention_backends
69-
title: Attention backends
70-
- local: optimization/memory
71-
title: Reduce memory usage
72-
- local: optimization/speed-memory-optims
73-
title: Compiling and offloading quantized models
74-
- sections:
56+
- local: stable_diffusion
57+
title: Basic performance
58+
- isExpanded: false
59+
sections:
60+
- local: optimization/fp16
61+
title: Accelerate inference
62+
- local: optimization/cache
63+
title: Caching
64+
- local: optimization/attention_backends
65+
title: Attention backends
66+
- local: optimization/memory
67+
title: Reduce memory usage
68+
- local: optimization/speed-memory-optims
69+
title: Compiling and offloading quantized models
70+
title: Inference
71+
- isExpanded: false
72+
sections:
7573
- local: optimization/pruna
7674
title: Pruna
7775
- local: optimization/xformers
@@ -90,8 +88,55 @@
9088
title: ParaAttention
9189
- local: using-diffusers/image_quality
9290
title: FreeU
93-
title: Community optimizations
94-
title: Inference optimization
91+
title: Community methods
92+
- isExpanded: false
93+
sections:
94+
- local: quantization/overview
95+
title: Getting started
96+
- local: quantization/bitsandbytes
97+
title: bitsandbytes
98+
- local: quantization/gguf
99+
title: gguf
100+
- local: quantization/nunchaku
101+
title: Nunchaku Lite
102+
- local: quantization/torchao
103+
title: torchao
104+
- local: quantization/quanto
105+
title: quanto
106+
- local: quantization/modelopt
107+
title: NVIDIA ModelOpt
108+
- local: quantization/autoround
109+
title: AutoRound
110+
- local: quantization/sdnq
111+
title: SDNQ
112+
title: Quantization
113+
- isExpanded: false
114+
sections:
115+
- local: optimization/onnx
116+
title: ONNX
117+
- local: optimization/open_vino
118+
title: OpenVINO
119+
- local: optimization/coreml
120+
title: Core ML
121+
- local: optimization/mps
122+
title: Metal Performance Shaders (MPS)
123+
- local: optimization/habana
124+
title: Intel Gaudi
125+
- local: optimization/neuron
126+
title: AWS Neuron
127+
title: Hardware-specific acceleration
128+
- isExpanded: false
129+
sections:
130+
- local: using-diffusers/create_a_server
131+
title: Create a server
132+
- local: using-diffusers/batched_inference
133+
title: Batch inference
134+
- local: training/distributed_inference
135+
title: Distributed inference
136+
- local: hybrid_inference/overview
137+
title: Remote inference
138+
title: Serving and scaling
139+
title: Optimize and scale
95140
- isExpanded: false
96141
sections:
97142
- local: modular_diffusers/overview
@@ -129,7 +174,8 @@
129174
title: Adapt a model to a new task
130175
- local: tutorials/basic_training
131176
title: Train a diffusion model
132-
- sections:
177+
- isExpanded: false
178+
sections:
133179
- local: training/unconditional_training
134180
title: Unconditional image generation
135181
- local: training/text2image
@@ -146,8 +192,9 @@
146192
title: InstructPix2Pix
147193
- local: training/cogvideox
148194
title: CogVideoX
149-
title: Models
150-
- sections:
195+
title: Model recipes
196+
- isExpanded: false
197+
sections:
151198
- local: training/text_inversion
152199
title: Textual Inversion
153200
- local: training/dreambooth
@@ -160,49 +207,14 @@
160207
title: Latent Consistency Distillation
161208
- local: training/ddpo
162209
title: Reinforcement learning training with DDPO
163-
title: Methods
210+
title: Training methods
164211
- local: training/nemo_automodel
165212
title: NeMo Automodel
166-
title: Training
167-
- isExpanded: false
168-
sections:
169-
- local: quantization/overview
170-
title: Getting started
171-
- local: quantization/bitsandbytes
172-
title: bitsandbytes
173-
- local: quantization/gguf
174-
title: gguf
175-
- local: quantization/nunchaku
176-
title: Nunchaku Lite
177-
- local: quantization/torchao
178-
title: torchao
179-
- local: quantization/quanto
180-
title: quanto
181-
- local: quantization/modelopt
182-
title: NVIDIA ModelOpt
183-
- local: quantization/autoround
184-
title: AutoRound
185-
- local: quantization/sdnq
186-
title: SDNQ
187-
title: Quantization
213+
title: Train and fine-tune
188214
- isExpanded: false
189215
sections:
190-
- local: optimization/onnx
191-
title: ONNX
192-
- local: optimization/open_vino
193-
title: OpenVINO
194-
- local: optimization/coreml
195-
title: Core ML
196-
- local: optimization/mps
197-
title: Metal Performance Shaders (MPS)
198-
- local: optimization/habana
199-
title: Intel Gaudi
200-
- local: optimization/neuron
201-
title: AWS Neuron
202-
title: Model accelerators and hardware
203-
- isExpanded: false
204-
sections:
205-
- sections:
216+
- isExpanded: false
217+
sections:
206218
- local: using-diffusers/unconditional_image_generation
207219
title: Unconditional image generation
208220
- local: using-diffusers/conditional_image_generation
@@ -217,22 +229,26 @@
217229
title: Video generation
218230
- local: using-diffusers/depth2img
219231
title: Depth-to-image
220-
title: Task recipes
221-
- local: using-diffusers/write_own_pipeline
222-
title: Understanding pipelines, models and schedulers
223-
- local: using-diffusers/cli
224-
title: Command line interface
232+
title: Recipes
233+
- isExpanded: false
234+
sections:
235+
- local: conceptual/philosophy
236+
title: Diffusers philosophy
237+
- local: using-diffusers/write_own_pipeline
238+
title: Understanding pipelines, models and schedulers
239+
- local: using-diffusers/controlling_generation
240+
title: Controlled generation
241+
title: Concepts and background
225242
- local: community_projects
226243
title: Projects built with Diffusers
227-
- local: conceptual/philosophy
228-
title: Philosophy
229-
- local: using-diffusers/controlling_generation
230-
title: Controlled generation
244+
title: Resources
245+
- isExpanded: false
246+
sections:
231247
- local: conceptual/contribution
232-
title: How to contribute?
248+
title: How to contribute
233249
- local: conceptual/ethical_guidelines
234250
title: Diffusers' Ethical Guidelines
235-
title: Resources
251+
title: Contribute
236252
- isExpanded: false
237253
sections:
238254
- sections:

‎docs/source/en/training/dreambooth.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,6 +14,8 @@ specific language governing permissions and limitations under the License.
1414

1515
[DreamBooth](https://huggingface.co/papers/2208.12242) is a training technique that updates the entire diffusion model by training on just a few images of a subject or style. It works by associating a special word in the prompt with the example images.
1616

17+
To load a trained checkpoint for inference, see [Load a DreamBooth adapter for inference](../using-diffusers/dreambooth).
18+
1719
If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing` and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers).
1820

1921
This guide will explore the [train_dreambooth.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py) script to help you become more familiar with it, and how you can adapt it for your own use-case.

‎docs/source/en/training/text_inversion.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,6 +14,8 @@ specific language governing permissions and limitations under the License.
1414

1515
[Textual Inversion](https://hf.co/papers/2208.01618) is a training technique for personalizing image generation models with just a few example images of what you want it to learn. This technique works by learning and updating the text embeddings (the new embeddings are tied to a special word you must use in the prompt) to match the example images you provide.
1616

17+
For inference with trained embeddings, see [Textual inversion inference](../using-diffusers/textual_inversion_inference).
18+
1719
If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing` and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers).
1820

1921
This guide will explore the [textual_inversion.py](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py) script to help you become more familiar with it, and how you can adapt it for your own use-case.

‎docs/source/en/using-diffusers/dreambooth.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,8 @@ specific language governing permissions and limitations under the License.
1616

1717
DreamBooth checkpoints are typically a few GBs in size because it contains the full model weights.
1818

19+
To train one, see [Train DreamBooth](../training/dreambooth).
20+
1921
Load the DreamBooth checkpoint with [`~DiffusionPipeline.from_pretrained`] and include the unique identifier in the prompt to activate its generation.
2022

2123
```py

‎docs/source/en/using-diffusers/textual_inversion_inference.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,8 @@ specific language governing permissions and limitations under the License.
1616

1717
Textual Inversion weights are very lightweight and typically only a few KBs because they're only word embeddings. However, this also means the word embeddings need to be loaded after loading a model with [`~DiffusionPipeline.from_pretrained`].
1818

19+
To train embeddings, see [Train textual inversion](../training/text_inversion).
20+
1921
```py
2022
import torch
2123
from diffusers import AutoPipelineForText2Image

0 commit comments

Comments
 (0)