Image-to-Image
Diffusers
lora
template:diffusion-lora
text-to-video
image-to-video
video-to-video
lightx2v
Instructions to use rzgar/Bernini-R-LightX2V-4step-loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rzgar/Bernini-R-LightX2V-4step-loras with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/Bernini-R", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("rzgar/Bernini-R-LightX2V-4step-loras") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,13 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
-
- text-to-image
|
| 4 |
- lora
|
| 5 |
- diffusers
|
| 6 |
- template:diffusion-lora
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
base_model: ByteDance/Bernini-R
|
| 9 |
instance_prompt: null
|
| 10 |
license: apache-2.0
|
|
@@ -39,9 +42,12 @@ These LightX2V LoRAs behave like the Wan 2.2 4-step stack , clean motion, sharp
|
|
| 39 |
**Strength: 1.0** on both (same as the official Wan 2.2 4-step workflow).
|
| 40 |
|
| 41 |
**Steps: 4**
|
|
|
|
| 42 |
**Sampler**: dpmpp_2m_sde
|
|
|
|
| 43 |
**Scheduler**: sgm_uniform
|
| 44 |
|
|
|
|
| 45 |
## Credits
|
| 46 |
[**LightXtV**](https://huggingface.co/lightx2v)
|
| 47 |
|
|
@@ -49,4 +55,4 @@ These LightX2V LoRAs behave like the Wan 2.2 4-step stack , clean motion, sharp
|
|
| 49 |
## Download model
|
| 50 |
|
| 51 |
|
| 52 |
-
[Download](/rzgar/Bernini-R-LightX2V-4step-loras/tree/main) them in the Files & versions tab.
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
|
|
|
| 3 |
- lora
|
| 4 |
- diffusers
|
| 5 |
- template:diffusion-lora
|
| 6 |
+
- text-to-video
|
| 7 |
+
- image-to-video
|
| 8 |
+
- video-to-video
|
| 9 |
+
- image-to-image
|
| 10 |
+
- lightx2v
|
| 11 |
base_model: ByteDance/Bernini-R
|
| 12 |
instance_prompt: null
|
| 13 |
license: apache-2.0
|
|
|
|
| 42 |
**Strength: 1.0** on both (same as the official Wan 2.2 4-step workflow).
|
| 43 |
|
| 44 |
**Steps: 4**
|
| 45 |
+
|
| 46 |
**Sampler**: dpmpp_2m_sde
|
| 47 |
+
|
| 48 |
**Scheduler**: sgm_uniform
|
| 49 |
|
| 50 |
+
|
| 51 |
## Credits
|
| 52 |
[**LightXtV**](https://huggingface.co/lightx2v)
|
| 53 |
|
|
|
|
| 55 |
## Download model
|
| 56 |
|
| 57 |
|
| 58 |
+
[Download](/rzgar/Bernini-R-LightX2V-4step-loras/tree/main) them in the Files & versions tab.
|