Instructions to use mobled37/vae-model-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mobled37/vae-model-finetuned with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mobled37/vae-model-finetuned", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
End of training
Browse files
README.md
CHANGED
|
@@ -22,11 +22,11 @@ This pipeline was finetuned from **None** on the **vipseg** dataset. Below are s
|
|
| 22 |
These are the key hyperparameters used during training:
|
| 23 |
|
| 24 |
* Epochs: 100
|
| 25 |
-
* Learning rate:
|
| 26 |
-
* Batch size:
|
| 27 |
* Gradient accumulation steps: 2
|
| 28 |
* Image resolution: 30
|
| 29 |
* Mixed-precision: fp16
|
| 30 |
|
| 31 |
|
| 32 |
-
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/wearesameasyou/vae-fine-tune/runs/
|
|
|
|
| 22 |
These are the key hyperparameters used during training:
|
| 23 |
|
| 24 |
* Epochs: 100
|
| 25 |
+
* Learning rate: 1.92e-05
|
| 26 |
+
* Batch size: 64
|
| 27 |
* Gradient accumulation steps: 2
|
| 28 |
* Image resolution: 30
|
| 29 |
* Mixed-precision: fp16
|
| 30 |
|
| 31 |
|
| 32 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/wearesameasyou/vae-fine-tune/runs/667jmxdx).
|