Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,9 @@ https://modelscope.cn/organization/DiffSynth-Studio
|
|
| 12 |
----------------
|
| 13 |
|
| 14 |
Wan2.1-1.3b-lora-aesthetics-v1:
|
|
|
|
| 15 |
Model Overview
|
|
|
|
| 16 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework. It has been finely tuned on an aesthetics-focused dataset, enhancing the visual appeal of generated videos. Additionally, the classifier-free guidance can be disabled to speed up the process.
|
| 17 |
|
| 18 |
Recommended Settings
|
|
@@ -26,6 +28,7 @@ Using this model may reduce the diversity of generated videos. It is recommended
|
|
| 26 |
----------------
|
| 27 |
|
| 28 |
Wan2.1-1.3b-lora-speedcontrol-v1:
|
|
|
|
| 29 |
Model Overview
|
| 30 |
|
| 31 |
This LoRA model is trained from the Wan2.1-1.3B model using the DiffSynth-Studio framework. It has been fine-tuned on an aesthetics-focused dataset, enhancing the visual appearance of generated videos. Additionally, the classifier-free guidance can be disabled to speed up the process.
|
|
@@ -66,7 +69,9 @@ LoRA alpha = -0.5 → Faster speed, reduced visual quality.
|
|
| 66 |
----------------
|
| 67 |
|
| 68 |
Wan2.1-1.3b-lora-highresfix-v1:
|
|
|
|
| 69 |
Model Overview
|
|
|
|
| 70 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework. Since the base model was originally trained at 480p resolution, it has certain limitations in sharpness. To address this, additional training was conducted to enhance the quality of high-resolution videos, preventing image collapse or a dull appearance.
|
| 71 |
|
| 72 |
Recommended Usage
|
|
@@ -98,7 +103,9 @@ Negative Prompt: Overly bright colors, overexposure, static, blurry details, sub
|
|
| 98 |
----------------
|
| 99 |
|
| 100 |
Wan2.1-1.3b-lora-exvideo-v1:
|
|
|
|
| 101 |
Model Overview
|
|
|
|
| 102 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework.
|
| 103 |
It enables video duration extension: once activated, this LoRA allows the generation of videos twice as long as usual.
|
| 104 |
|
|
|
|
| 12 |
----------------
|
| 13 |
|
| 14 |
Wan2.1-1.3b-lora-aesthetics-v1:
|
| 15 |
+
|
| 16 |
Model Overview
|
| 17 |
+
|
| 18 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework. It has been finely tuned on an aesthetics-focused dataset, enhancing the visual appeal of generated videos. Additionally, the classifier-free guidance can be disabled to speed up the process.
|
| 19 |
|
| 20 |
Recommended Settings
|
|
|
|
| 28 |
----------------
|
| 29 |
|
| 30 |
Wan2.1-1.3b-lora-speedcontrol-v1:
|
| 31 |
+
|
| 32 |
Model Overview
|
| 33 |
|
| 34 |
This LoRA model is trained from the Wan2.1-1.3B model using the DiffSynth-Studio framework. It has been fine-tuned on an aesthetics-focused dataset, enhancing the visual appearance of generated videos. Additionally, the classifier-free guidance can be disabled to speed up the process.
|
|
|
|
| 69 |
----------------
|
| 70 |
|
| 71 |
Wan2.1-1.3b-lora-highresfix-v1:
|
| 72 |
+
|
| 73 |
Model Overview
|
| 74 |
+
|
| 75 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework. Since the base model was originally trained at 480p resolution, it has certain limitations in sharpness. To address this, additional training was conducted to enhance the quality of high-resolution videos, preventing image collapse or a dull appearance.
|
| 76 |
|
| 77 |
Recommended Usage
|
|
|
|
| 103 |
----------------
|
| 104 |
|
| 105 |
Wan2.1-1.3b-lora-exvideo-v1:
|
| 106 |
+
|
| 107 |
Model Overview
|
| 108 |
+
|
| 109 |
This LoRA model is trained based on the Wan2.1-1.3B model using the DiffSynth-Studio framework.
|
| 110 |
It enables video duration extension: once activated, this LoRA allows the generation of videos twice as long as usual.
|
| 111 |
|