Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -15,12 +15,7 @@ tags:
|
|
| 15 |
- standard
|
| 16 |
pipeline_tag: text-to-image
|
| 17 |
inference: true
|
| 18 |
-
|
| 19 |
-
- text: 'A photo-realistic image of a cat'
|
| 20 |
-
parameters:
|
| 21 |
-
negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
|
| 22 |
-
output:
|
| 23 |
-
url: ./assets/image_0_0.png
|
| 24 |
---
|
| 25 |
|
| 26 |
# pixart-controlnet-lora-test
|
|
@@ -44,7 +39,7 @@ A photo-realistic image of a cat
|
|
| 44 |
|
| 45 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
|
| 50 |
<Gallery />
|
|
@@ -55,8 +50,8 @@ You may reuse the base model text encoder for inference.
|
|
| 55 |
|
| 56 |
## Training settings
|
| 57 |
|
| 58 |
-
- Training epochs:
|
| 59 |
-
- Training steps:
|
| 60 |
- Learning rate: 0.0001
|
| 61 |
- Learning rate schedule: constant
|
| 62 |
- Warmup steps: 500
|
|
|
|
| 15 |
- standard
|
| 16 |
pipeline_tag: text-to-image
|
| 17 |
inference: true
|
| 18 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# pixart-controlnet-lora-test
|
|
|
|
| 39 |
|
| 40 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
| 41 |
|
| 42 |
+
|
| 43 |
|
| 44 |
|
| 45 |
<Gallery />
|
|
|
|
| 50 |
|
| 51 |
## Training settings
|
| 52 |
|
| 53 |
+
- Training epochs: 4
|
| 54 |
+
- Training steps: 10
|
| 55 |
- Learning rate: 0.0001
|
| 56 |
- Learning rate schedule: constant
|
| 57 |
- Warmup steps: 500
|