StrugglerXYH
commited on
Commit
•
d622c17
1
Parent(s):
1255bc4
Update README.md
Browse files
README.md
CHANGED
@@ -11,15 +11,17 @@ pipeline_tag: text-to-image
|
|
11 |
# MistoLine
|
12 |
|
13 |
## Control Every Line!
|
14 |
-
![Intro Image](assets/intro.png)
|
|
|
15 |
|
16 |
MistoLine: A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning.
|
17 |
|
18 |
MistoLine is an SDXL-ControlNet model that can adapt to any type of line art input, demonstrating high accuracy and excellent stability. It can generate high-quality images (with a short side greater than 1024px) based on user-provided line art of various types, including hand-drawn sketches, different ControlNet line preprocessors, and model-generated outlines. MistoLine eliminates the need to select different ControlNet models for different line preprocessors, as it exhibits strong generalization capabilities across diverse line art conditions.
|
19 |
-
We developed MistoLine by employing a novel line preprocessing algorithm (Anyline) and retraining the ControlNet model based on the Unet of stabilityai/ stable-diffusion-xl-base-1.0, along with innovations in large model training engineering. MistoLine showcases superior performance across different types of
|
20 |
-
line art inputs, surpassing existing ControlNet models in terms of detail restoration, prompt alignment, and stability, particularly in more complex scenarios.
|
21 |
|
22 |
-
MistoLine
|
|
|
|
|
|
|
23 |
![ControlNet architecture](assets/controlnet_1.png)
|
24 |
![ControlNet architecture](assets/controlnet_2.png)
|
25 |
*reference:https://github.com/lllyasviel/ControlNet*
|
@@ -40,9 +42,11 @@ We have open-sourced the corresponding model weight files for non-commercial use
|
|
40 |
## Application Examples
|
41 |
|
42 |
### Sketch Rendering
|
|
|
43 |
![Sketch Rendering](assets/sketch_rendering.png)
|
44 |
|
45 |
### Model Rendering
|
|
|
46 |
![Model Rendering](assets/model_rendering.png)
|
47 |
|
48 |
## ComfyUI Recommended Parameters
|
@@ -79,4 +83,3 @@ end_percent:0.9
|
|
79 |
primaryClass={cs.CV}
|
80 |
}
|
81 |
```
|
82 |
-
|
|
|
11 |
# MistoLine
|
12 |
|
13 |
## Control Every Line!
|
14 |
+
![Intro Image](assets/intro.png)
|
15 |
+
You can download this model here: [HuggingFace TheMistoAI](https://huggingface.co/TheMistoAI/MistoLine)
|
16 |
|
17 |
MistoLine: A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning.
|
18 |
|
19 |
MistoLine is an SDXL-ControlNet model that can adapt to any type of line art input, demonstrating high accuracy and excellent stability. It can generate high-quality images (with a short side greater than 1024px) based on user-provided line art of various types, including hand-drawn sketches, different ControlNet line preprocessors, and model-generated outlines. MistoLine eliminates the need to select different ControlNet models for different line preprocessors, as it exhibits strong generalization capabilities across diverse line art conditions.
|
|
|
|
|
20 |
|
21 |
+
We developed MistoLine by employing a novel line preprocessing algorithm (Anyline) and retraining the ControlNet model based on the Unet of stabilityai/ stable-diffusion-xl-base-1.0, along with innovations in large model training engineering. MistoLine showcases superior performance across
|
22 |
+
different types of line art inputs, surpassing existing ControlNet models in terms of detail restoration, prompt alignment, and stability, particularly in more complex scenarios.
|
23 |
+
|
24 |
+
MistoLine maintains consistency with the ControlNet architecture released by @lllyasviel, as illustrated in the following schematic diagram:
|
25 |
![ControlNet architecture](assets/controlnet_1.png)
|
26 |
![ControlNet architecture](assets/controlnet_2.png)
|
27 |
*reference:https://github.com/lllyasviel/ControlNet*
|
|
|
42 |
## Application Examples
|
43 |
|
44 |
### Sketch Rendering
|
45 |
+
*The following case only utilized MistoLine as the controlnet:*
|
46 |
![Sketch Rendering](assets/sketch_rendering.png)
|
47 |
|
48 |
### Model Rendering
|
49 |
+
*The following case only utilized Anyline as the preprocessor and MistoLine as the controlnet.*
|
50 |
![Model Rendering](assets/model_rendering.png)
|
51 |
|
52 |
## ComfyUI Recommended Parameters
|
|
|
83 |
primaryClass={cs.CV}
|
84 |
}
|
85 |
```
|
|