Text-to-Video
Diffusers
Safetensors
English
SkyReelsV2DiffusionForcingPipeline
video
video generation
Instructions to use Skywork/SkyReels-V2-DF-1.3B-540P-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Skywork/SkyReels-V2-DF-1.3B-540P-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Skywork/SkyReels-V2-DF-1.3B-540P-Diffusers", 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
#3
by tolgacangoz - opened
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: skywork-license
|
| 4 |
license_link: LICENSE
|
| 5 |
-
pipeline_tag: text-to-
|
| 6 |
library_name: diffusers
|
| 7 |
tags:
|
| 8 |
- video
|
|
@@ -63,10 +63,9 @@ The demos above showcase 30-second videos generated using our SkyReels-V2 Diffus
|
|
| 63 |
|
| 64 |
## 🚀 Quickstart
|
| 65 |
|
| 66 |
-
|
| 67 |
|
| 68 |
```py
|
| 69 |
-
# pip install ftfy
|
| 70 |
import torch
|
| 71 |
from diffusers import AutoModel, SkyReelsV2DiffusionForcingPipeline, UniPCMultistepScheduler
|
| 72 |
from diffusers.utils import export_to_video
|
|
@@ -97,7 +96,7 @@ output = pipeline(
|
|
| 97 |
overlap_history=None, # Number of frames to overlap for smooth transitions in long videos; 17 for long video generations
|
| 98 |
addnoise_condition=20, # Improves consistency in long video generation
|
| 99 |
).frames[0]
|
| 100 |
-
export_to_video(output, "
|
| 101 |
```
|
| 102 |
|
| 103 |
#### Installation
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: skywork-license
|
| 4 |
license_link: LICENSE
|
| 5 |
+
pipeline_tag: text-to-image
|
| 6 |
library_name: diffusers
|
| 7 |
tags:
|
| 8 |
- video
|
|
|
|
| 63 |
|
| 64 |
## 🚀 Quickstart
|
| 65 |
|
| 66 |
+
[SkyReels-V2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/skyreels_v2) can be run directly using 🤗 Diffusers!
|
| 67 |
|
| 68 |
```py
|
|
|
|
| 69 |
import torch
|
| 70 |
from diffusers import AutoModel, SkyReelsV2DiffusionForcingPipeline, UniPCMultistepScheduler
|
| 71 |
from diffusers.utils import export_to_video
|
|
|
|
| 96 |
overlap_history=None, # Number of frames to overlap for smooth transitions in long videos; 17 for long video generations
|
| 97 |
addnoise_condition=20, # Improves consistency in long video generation
|
| 98 |
).frames[0]
|
| 99 |
+
export_to_video(output, "video.mp4", fps=24, quality=8)
|
| 100 |
```
|
| 101 |
|
| 102 |
#### Installation
|