Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ControlNet Standard Lineart for SDXL
|
| 2 |
SDXL has perfect content generation functions and amazing LoRa performance, but its ControlNet is always its drawback, filtering out most of the users. Based on the computational power constraints of personal GPU, one cannot easily train and tune a perfect ControlNet model.
|
| 3 |
|
|
@@ -72,5 +82,4 @@ image = pipe(
|
|
| 72 |
--train_data_dir="/path/to/your/dataset_example"
|
| 73 |
```
|
| 74 |
|
| 75 |
-
2. Based on the experiment, sometimes this ControlNet cannot understand colorization very well on the xl-base-1.0. However, it can capture the line perfectly. So I suspect the miss colorization happened on the base model I chose. More experiments are needed.
|
| 76 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- 'art '
|
| 6 |
+
- stable-diffusion-xl-diffusers
|
| 7 |
+
- stable-diffusion-xl
|
| 8 |
+
- controlnet
|
| 9 |
+
- lineart
|
| 10 |
+
---
|
| 11 |
# ControlNet Standard Lineart for SDXL
|
| 12 |
SDXL has perfect content generation functions and amazing LoRa performance, but its ControlNet is always its drawback, filtering out most of the users. Based on the computational power constraints of personal GPU, one cannot easily train and tune a perfect ControlNet model.
|
| 13 |
|
|
|
|
| 82 |
--train_data_dir="/path/to/your/dataset_example"
|
| 83 |
```
|
| 84 |
|
| 85 |
+
2. Based on the experiment, sometimes this ControlNet cannot understand colorization very well on the xl-base-1.0. However, it can capture the line perfectly. So I suspect the miss colorization happened on the base model I chose. More experiments are needed.
|
|
|