StrugglerXYH commited on
Commit
d622c17
1 Parent(s): 1255bc4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -5
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 maintains consistency with the ControlNet architecture released by lllyasviel, as illustrated in the following schematic diagram:
 
 
 
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
  ```