Instructions to use cerspense/zeroscope_v1-1_320s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cerspense/zeroscope_v1-1_320s with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v1-1_320s", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,5 +4,4 @@ tags:
|
|
| 4 |
---
|
| 5 |
Modelscope without the watermark, trained in 320x320, with no skipped frames for less flicker.
|
| 6 |
This updated version fixes stretching issues present in v1
|
| 7 |
-
See comparison here: https://www.youtube.com/watch?v=r4tOc30Zu0w
|
| 8 |
Model was trained on a subset of the vimeo90k dataset + a selection of music videos
|
|
|
|
| 4 |
---
|
| 5 |
Modelscope without the watermark, trained in 320x320, with no skipped frames for less flicker.
|
| 6 |
This updated version fixes stretching issues present in v1
|
|
|
|
| 7 |
Model was trained on a subset of the vimeo90k dataset + a selection of music videos
|