add examples in readme
Browse files
README.md
CHANGED
@@ -53,7 +53,6 @@ pipe.to("cuda")
|
|
53 |
pipe.load_lora_weights(adapter_id)
|
54 |
pipe.fuse_lora()
|
55 |
|
56 |
-
|
57 |
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
|
58 |
|
59 |
# disable guidance_scale by passing 0
|
@@ -62,21 +61,206 @@ image = pipe(prompt=prompt, num_inference_steps=4, guidance_scale=0).images[0]
|
|
62 |
|
63 |
![](./image.png)
|
64 |
|
65 |
-
###
|
66 |
|
67 |
-
|
68 |
|
69 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
### ControlNet
|
74 |
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
### T2I Adapter
|
78 |
|
79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
## Speed Benchmark
|
82 |
|
|
|
53 |
pipe.load_lora_weights(adapter_id)
|
54 |
pipe.fuse_lora()
|
55 |
|
|
|
56 |
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
|
57 |
|
58 |
# disable guidance_scale by passing 0
|
|
|
61 |
|
62 |
![](./image.png)
|
63 |
|
64 |
+
### Inpainting
|
65 |
|
66 |
+
LCM-LoRA can be used for inpainting as well.
|
67 |
|
68 |
+
```python
|
69 |
+
import torch
|
70 |
+
from diffusers import AutoPipelineForInpainting, LCMScheduler
|
71 |
+
from diffusers.utils import load_image, make_image_grid
|
72 |
+
|
73 |
+
pipe = AutoPipelineForInpainting.from_pretrained(
|
74 |
+
"diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
|
75 |
+
torch_dtype=torch.float16,
|
76 |
+
variant="fp16",
|
77 |
+
).to("cuda")
|
78 |
+
|
79 |
+
# set scheduler
|
80 |
+
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
|
81 |
+
|
82 |
+
# load LCM-LoRA
|
83 |
+
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
|
84 |
+
pipe.fuse_lora()
|
85 |
+
|
86 |
+
# load base and mask image
|
87 |
+
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png").resize((1024, 1024))
|
88 |
+
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png").resize((1024, 1024))
|
89 |
+
|
90 |
+
prompt = "a castle on top of a mountain, highly detailed, 8k"
|
91 |
+
generator = torch.manual_seed(42)
|
92 |
+
image = pipe(
|
93 |
+
prompt=prompt,
|
94 |
+
image=init_image,
|
95 |
+
mask_image=mask_image,
|
96 |
+
generator=generator,
|
97 |
+
num_inference_steps=5,
|
98 |
+
guidance_scale=4,
|
99 |
+
).images[0]
|
100 |
+
make_image_grid([init_image, mask_image, image], rows=1, cols=3)
|
101 |
+
```
|
102 |
+
|
103 |
+
![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_inpainting.png)
|
104 |
+
|
105 |
+
|
106 |
+
## Combine with styled LoRAs
|
107 |
|
108 |
+
LCM-LoRA can be combined with other LoRAs to generate styled-images in very few steps (4-8). In the following example, we'll use the LCM-LoRA with the [papercut LoRA](TheLastBen/Papercut_SDXL).
|
109 |
+
To learn more about how to combine LoRAs, refer to [this guide](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#combine-multiple-adapters).
|
110 |
+
|
111 |
+
```python
|
112 |
+
import torch
|
113 |
+
from diffusers import DiffusionPipeline, LCMScheduler
|
114 |
+
|
115 |
+
pipe = DiffusionPipeline.from_pretrained(
|
116 |
+
"stabilityai/stable-diffusion-xl-base-1.0",
|
117 |
+
variant="fp16",
|
118 |
+
torch_dtype=torch.float16
|
119 |
+
).to("cuda")
|
120 |
+
|
121 |
+
# set scheduler
|
122 |
+
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
|
123 |
+
|
124 |
+
# load LoRAs
|
125 |
+
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl", adapter_name="lcm")
|
126 |
+
pipe.load_lora_weights("TheLastBen/Papercut_SDXL", weight_name="papercut.safetensors", adapter_name="papercut")
|
127 |
+
|
128 |
+
# Combine LoRAs
|
129 |
+
pipe.set_adapters(["lcm", "papercut"], adapter_weights=[1.0, 0.8])
|
130 |
+
|
131 |
+
prompt = "papercut, a cute fox"
|
132 |
+
generator = torch.manual_seed(0)
|
133 |
+
image = pipe(prompt, num_inference_steps=4, guidance_scale=1, generator=generator).images[0]
|
134 |
+
image
|
135 |
+
```
|
136 |
+
|
137 |
+
![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdx_lora_mix.png)
|
138 |
|
139 |
### ControlNet
|
140 |
|
141 |
+
```python
|
142 |
+
import torch
|
143 |
+
import cv2
|
144 |
+
import numpy as np
|
145 |
+
from PIL import Image
|
146 |
+
|
147 |
+
from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel, LCMScheduler
|
148 |
+
from diffusers.utils import load_image
|
149 |
+
|
150 |
+
image = load_image(
|
151 |
+
"https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
|
152 |
+
).resize((1024, 1024))
|
153 |
+
|
154 |
+
image = np.array(image)
|
155 |
+
|
156 |
+
low_threshold = 100
|
157 |
+
high_threshold = 200
|
158 |
+
|
159 |
+
image = cv2.Canny(image, low_threshold, high_threshold)
|
160 |
+
image = image[:, :, None]
|
161 |
+
image = np.concatenate([image, image, image], axis=2)
|
162 |
+
canny_image = Image.fromarray(image)
|
163 |
+
|
164 |
+
controlnet = ControlNetModel.from_pretrained("diffusers/controlnet-canny-sdxl-1.0-small", torch_dtype=torch.float16, variant="fp16")
|
165 |
+
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
|
166 |
+
"stabilityai/stable-diffusion-xl-base-1.0",
|
167 |
+
controlnet=controlnet,
|
168 |
+
torch_dtype=torch.float16,
|
169 |
+
safety_checker=None,
|
170 |
+
variant="fp16"
|
171 |
+
).to("cuda")
|
172 |
+
|
173 |
+
# set scheduler
|
174 |
+
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
|
175 |
+
|
176 |
+
# load LCM-LoRA
|
177 |
+
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
|
178 |
+
pipe.fuse_lora()
|
179 |
+
|
180 |
+
generator = torch.manual_seed(0)
|
181 |
+
image = pipe(
|
182 |
+
"picture of the mona lisa",
|
183 |
+
image=canny_image,
|
184 |
+
num_inference_steps=5,
|
185 |
+
guidance_scale=1.5,
|
186 |
+
controlnet_conditioning_scale=0.5,
|
187 |
+
cross_attention_kwargs={"scale": 1},
|
188 |
+
generator=generator,
|
189 |
+
).images[0]
|
190 |
+
make_image_grid([canny_image, image], rows=1, cols=2)
|
191 |
+
```
|
192 |
+
|
193 |
+
![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_controlnet.png)
|
194 |
+
|
195 |
+
|
196 |
+
<Tip>
|
197 |
+
The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one.
|
198 |
+
</Tip>
|
199 |
|
200 |
### T2I Adapter
|
201 |
|
202 |
+
This example shows how to use the LCM-LoRA with the [Canny T2I-Adapter](TencentARC/t2i-adapter-canny-sdxl-1.0) and SDXL.
|
203 |
+
|
204 |
+
```python
|
205 |
+
import torch
|
206 |
+
import cv2
|
207 |
+
import numpy as np
|
208 |
+
from PIL import Image
|
209 |
+
|
210 |
+
from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, LCMScheduler
|
211 |
+
from diffusers.utils import load_image, make_image_grid
|
212 |
+
|
213 |
+
# Prepare image
|
214 |
+
# Detect the canny map in low resolution to avoid high-frequency details
|
215 |
+
image = load_image(
|
216 |
+
"https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_canny.jpg"
|
217 |
+
).resize((384, 384))
|
218 |
+
|
219 |
+
image = np.array(image)
|
220 |
+
|
221 |
+
low_threshold = 100
|
222 |
+
high_threshold = 200
|
223 |
+
|
224 |
+
image = cv2.Canny(image, low_threshold, high_threshold)
|
225 |
+
image = image[:, :, None]
|
226 |
+
image = np.concatenate([image, image, image], axis=2)
|
227 |
+
canny_image = Image.fromarray(image).resize((1024, 1024))
|
228 |
+
|
229 |
+
# load adapter
|
230 |
+
adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16, varient="fp16").to("cuda")
|
231 |
+
|
232 |
+
pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
|
233 |
+
"stabilityai/stable-diffusion-xl-base-1.0",
|
234 |
+
adapter=adapter,
|
235 |
+
torch_dtype=torch.float16,
|
236 |
+
variant="fp16",
|
237 |
+
).to("cuda")
|
238 |
+
|
239 |
+
# set scheduler
|
240 |
+
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
|
241 |
+
|
242 |
+
# load LCM-LoRA
|
243 |
+
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
|
244 |
+
|
245 |
+
prompt = "Mystical fairy in real, magic, 4k picture, high quality"
|
246 |
+
negative_prompt = "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured"
|
247 |
+
|
248 |
+
generator = torch.manual_seed(0)
|
249 |
+
image = pipe(
|
250 |
+
prompt=prompt,
|
251 |
+
negative_prompt=negative_prompt,
|
252 |
+
image=canny_image,
|
253 |
+
num_inference_steps=4,
|
254 |
+
guidance_scale=1.5,
|
255 |
+
adapter_conditioning_scale=0.8,
|
256 |
+
adapter_conditioning_factor=1,
|
257 |
+
generator=generator,
|
258 |
+
).images[0]
|
259 |
+
make_image_grid([canny_image, image], rows=1, cols=2)
|
260 |
+
```
|
261 |
+
|
262 |
+
![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_t2iadapter.png)
|
263 |
+
|
264 |
|
265 |
## Speed Benchmark
|
266 |
|