mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-20 15:48:20 +00:00
update docs
This commit is contained in:
Artiprocher
133
docs/source/creating/AdaptersForImageSynthesis.md
Normal file
133
docs/source/creating/AdaptersForImageSynthesis.md
Normal file
@@ -0,0 +1,133 @@
|
||||
# ControlNet、LoRA、IP-Adapter
|
||||
|
||||
在文生图模型的基础上，还可以使用各种 Adapter 架构的模型对生成过程进行控制。
|
||||
|
||||
接下来的例子会用到很多模型，我们先把它们下载好。
|
||||
|
||||
* 一个广受好评的 Stable Diffusion XL 架构动漫风格模型
|
||||
* 一个支持多种控制模式的 ControlNet 模型
|
||||
* 一个 Stable Diffusion XL 模型的 LoRA 模型
|
||||
* 一个 IP-Adapter 模型及其对应的图像编码器
|
||||
|
||||
```python
|
||||
from diffsynth import download_models
|
||||
|
||||
download_models([
|
||||
"BluePencilXL_v200",
|
||||
"ControlNet_union_sdxl_promax",
|
||||
"SDXL_lora_zyd232_ChineseInkStyle_SDXL_v1_0",
|
||||
"IP-Adapter-SDXL"
|
||||
])
|
||||
```
|
||||
|
||||
用基础文生图功能生成一张图
|
||||
|
||||
```python
|
||||
from diffsynth import ModelManager, SDXLImagePipeline
|
||||
import torch
|
||||
|
||||
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
|
||||
model_manager.load_models(["models/stable_diffusion_xl/bluePencilXL_v200.safetensors"])
|
||||
pipe = SDXLImagePipeline.from_model_manager(model_manager)
|
||||
torch.manual_seed(1)
|
||||
image = pipe(
|
||||
prompt="masterpiece, best quality, solo, long hair, wavy hair, silver hair, blue eyes, blue dress, medium breasts, dress, underwater, air bubble, floating hair, refraction, portrait,",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,",
|
||||
cfg_scale=6, num_inference_steps=60,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
```
|
||||
|
||||
|
||||
|
||||
接下来，我们让这位水下翩翩起舞的少女变成火系魔法师！启用 ControlNet 保持画面结构的同时，修改提示词。
|
||||
|
||||
```python
|
||||
from diffsynth import ModelManager, SDXLImagePipeline, ControlNetConfigUnit
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
|
||||
model_manager.load_models([
|
||||
"models/stable_diffusion_xl/bluePencilXL_v200.safetensors",
|
||||
"models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors"
|
||||
])
|
||||
pipe = SDXLImagePipeline.from_model_manager(model_manager, controlnet_config_units=[
|
||||
ControlNetConfigUnit("depth", "models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors", scale=1)
|
||||
])
|
||||
torch.manual_seed(2)
|
||||
image = pipe(
|
||||
prompt="masterpiece, best quality, solo, long hair, wavy hair, pink hair, red eyes, red dress, medium breasts, dress, fire ball, fire background, floating hair, refraction, portrait,",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw, white background",
|
||||
cfg_scale=6, num_inference_steps=60,
|
||||
controlnet_image=Image.open("image.jpg")
|
||||
)
|
||||
image.save("image_controlnet.jpg")
|
||||
```
|
||||
|
||||
|
||||
|
||||
很酷对不对？还有更酷的，加个 LoRA，让画面更贴近手绘漫画的扁平风格。这个 LoRA 需要一定的触发词才能生效，这在原作者的模型页面有提到，记得在提示词的开头加上触发词哦。
|
||||
|
||||
```python
|
||||
from diffsynth import ModelManager, SDXLImagePipeline, ControlNetConfigUnit
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
|
||||
model_manager.load_models([
|
||||
"models/stable_diffusion_xl/bluePencilXL_v200.safetensors",
|
||||
"models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors"
|
||||
])
|
||||
model_manager.load_lora("models/lora/zyd232_ChineseInkStyle_SDXL_v1_0.safetensors", lora_alpha=1.0)
|
||||
pipe = SDXLImagePipeline.from_model_manager(model_manager, controlnet_config_units=[
|
||||
ControlNetConfigUnit("depth", "models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors", scale=1.0)
|
||||
])
|
||||
torch.manual_seed(3)
|
||||
image = pipe(
|
||||
prompt="zydink, ink sketch, flat anime, masterpiece, best quality, solo, long hair, wavy hair, pink hair, red eyes, red dress, medium breasts, dress, fire ball, fire background, floating hair, refraction, portrait,",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw, white background",
|
||||
cfg_scale=6, num_inference_steps=60,
|
||||
controlnet_image=Image.open("image.jpg")
|
||||
)
|
||||
image.save("image_lora.jpg")
|
||||
```
|
||||
|
||||
|
||||
|
||||
还没结束呢！找一张水墨风的中国画作为风格引导，启动 IP-Adapter，让古典艺术和现代美学碰撞！
|
||||
|
||||
|就用这张图作为风格引导吧||
|
||||
|-|-|
|
||||
|
||||
```python
|
||||
from diffsynth import ModelManager, SDXLImagePipeline, ControlNetConfigUnit
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
|
||||
model_manager.load_models([
|
||||
"models/stable_diffusion_xl/bluePencilXL_v200.safetensors",
|
||||
"models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors",
|
||||
"models/IpAdapter/stable_diffusion_xl/ip-adapter_sdxl.bin",
|
||||
"models/IpAdapter/stable_diffusion_xl/image_encoder/model.safetensors",
|
||||
])
|
||||
model_manager.load_lora("models/lora/zyd232_ChineseInkStyle_SDXL_v1_0.safetensors", lora_alpha=1.0)
|
||||
pipe = SDXLImagePipeline.from_model_manager(model_manager, controlnet_config_units=[
|
||||
ControlNetConfigUnit("depth", "models/ControlNet/controlnet_union/diffusion_pytorch_model_promax.safetensors", scale=1.0)
|
||||
])
|
||||
torch.manual_seed(2)
|
||||
image = pipe(
|
||||
prompt="zydink, ink sketch, flat anime, masterpiece, best quality, solo, long hair, wavy hair, pink hair, red eyes, red dress, medium breasts, dress, fire ball, fire background, floating hair, refraction, portrait,",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw, white background",
|
||||
cfg_scale=6, num_inference_steps=60,
|
||||
controlnet_image=Image.open("image.jpg"),
|
||||
ipadapter_images=[Image.open("ink_style.jpg")],
|
||||
ipadapter_use_instant_style=True, ipadapter_scale=0.5
|
||||
)
|
||||
image.save("image_ipadapter.jpg")
|
||||
```
|
||||
|
||||
|
||||
|
||||
用 Diffusion 生成图像的乐趣在于，各种生态模型的组合，可以实现各种奇思妙想。
|
||||
65
docs/source/creating/BasicImageSynthesis.md
Normal file
65
docs/source/creating/BasicImageSynthesis.md
Normal file
@@ -0,0 +1,65 @@
|
||||
# 文生图、图生图、高分辨率修复
|
||||
|
||||
加载文生图模型，这里我们使用一个 Civiai 上一个动漫风格的模型作为例子。
|
||||
|
||||
```python
|
||||
import torch
|
||||
from diffsynth import ModelManager, SDImagePipeline, download_models
|
||||
|
||||
download_models(["AingDiffusion_v12"])
|
||||
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
|
||||
model_manager.load_models(["models/stable_diffusion/aingdiffusion_v12.safetensors"])
|
||||
pipe = SDImagePipeline.from_model_manager(model_manager)
|
||||
```
|
||||
|
||||
生成一张图小试身手。
|
||||
|
||||
```python
|
||||
torch.manual_seed(0)
|
||||
image = pipe(
|
||||
prompt="masterpiece, best quality, a girl with long silver hair",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,",
|
||||
height=512, width=512, num_inference_steps=80,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
```
|
||||
|
||||
嗯，一个可爱的小姐姐。
|
||||
|
||||
|
||||
|
||||
用图生图功能把她的头发变成红色，只需要添加 `input_image` 和 `denoising_strength` 两个参数。其中 `denoising_strength` 用于控制加噪声的强度，为 0 时生成的图与输入的图完全一致，为 1 时完全随机生成图。
|
||||
|
||||
```python
|
||||
torch.manual_seed(1)
|
||||
image_edited = pipe(
|
||||
prompt="masterpiece, best quality, a girl with long red hair",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,",
|
||||
height=512, width=512, num_inference_steps=80,
|
||||
input_image=image, denoising_strength=0.6,
|
||||
)
|
||||
image_edited.save("image_edited.jpg")
|
||||
```
|
||||
|
||||
嗯，一个红色头发的可爱小姐姐。
|
||||
|
||||
|
||||
|
||||
由于模型本身是在 512*512 分辨率下训练的，所以图片看起来有点模糊，不过我们可以利用模型自身的能力润色这张图，为其填充细节。具体来说，就是提高分辨率后进行图生图。
|
||||
|
||||
```python
|
||||
torch.manual_seed(2)
|
||||
image_highres = pipe(
|
||||
prompt="masterpiece, best quality, a girl with long red hair",
|
||||
negative_prompt="worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,",
|
||||
height=1024, width=1024, num_inference_steps=80,
|
||||
input_image=image_edited.resize((1024, 1024)), denoising_strength=0.6,
|
||||
)
|
||||
image_highres.save("image_highres.jpg")
|
||||
```
|
||||
|
||||
嗯，一个清晰的红色头发可爱小姐姐。
|
||||
|
||||
|
||||
|
||||
值得注意的是，图生图和高分辨率修复功能是全局支持的，目前我们所有的图像生成流水线都可以这样使用。
|
||||
@@ -21,6 +21,13 @@ DiffSynth-Studio 文档
|
||||
tutorial/Extensions.md
|
||||
tutorial/Schedulers.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: 开启创作之旅
|
||||
|
||||
creating/BasicImageSynthesis.md
|
||||
creating/AdaptersForImageSynthesis.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: 微调
|
||||
|
||||
Reference in New Issue
Block a user