Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ widget:
|
|
| 24 |
|
| 25 |
# wan-disney-DCM-distilled
|
| 26 |
|
| 27 |
-
This is a
|
| 28 |
|
| 29 |
The main validation prompt used during training was:
|
| 30 |
```
|
|
@@ -54,9 +54,9 @@ You may reuse the base model text encoder for inference.
|
|
| 54 |
|
| 55 |
## Training settings
|
| 56 |
|
| 57 |
-
- Training epochs:
|
| 58 |
-
- Training steps:
|
| 59 |
-
- Learning rate:
|
| 60 |
- Learning rate schedule: cosine
|
| 61 |
- Warmup steps: 400000
|
| 62 |
- Max grad value: 0.01
|
|
|
|
| 24 |
|
| 25 |
# wan-disney-DCM-distilled
|
| 26 |
|
| 27 |
+
This is a standard PEFT LoRA derived from [Wan-AI/Wan2.1-T2V-1.3B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers).
|
| 28 |
|
| 29 |
The main validation prompt used during training was:
|
| 30 |
```
|
|
|
|
| 54 |
|
| 55 |
## Training settings
|
| 56 |
|
| 57 |
+
- Training epochs: 0
|
| 58 |
+
- Training steps: 100
|
| 59 |
+
- Learning rate: 0.0001
|
| 60 |
- Learning rate schedule: cosine
|
| 61 |
- Warmup steps: 400000
|
| 62 |
- Max grad value: 0.01
|