Image-to-Image
Diffusers
Safetensors
Sana
English
VIBESanaEditingPipeline
image-editing
text-guided-editing
diffusion
qwen-vl
multimodal
distilled
cfg-distillation
Instructions to use iitolstykh/VIBE-Image-Edit-DistilledCFG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use iitolstykh/VIBE-Image-Edit-DistilledCFG 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("iitolstykh/VIBE-Image-Edit-DistilledCFG", dtype=torch.bfloat16, device_map="cuda") 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] - Sana
How to use iitolstykh/VIBE-Image-Edit-DistilledCFG with Sana:
# Load the model and infer image from text import torch from app.sana_pipeline import SanaPipeline from torchvision.utils import save_image sana = SanaPipeline("configs/sana_config/1024ms/Sana_1600M_img1024.yaml") sana.from_pretrained("hf://iitolstykh/VIBE-Image-Edit-DistilledCFG") image = sana( prompt='a cyberpunk cat with a neon sign that says "Sana"', height=1024, width=1024, guidance_scale=5.0, pag_guidance_scale=2.0, num_inference_steps=18, ) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,7 +81,7 @@ pip install transformers==4.57.1 torchvision==0.21.0 torch==2.6.0 diffusers==0.3
|
|
| 81 |
|
| 82 |
# Quick start
|
| 83 |
|
| 84 |
-
**Note:** When using this distilled model,
|
| 85 |
|
| 86 |
```python
|
| 87 |
from PIL import Image
|
|
@@ -102,6 +102,8 @@ model_path = snapshot_download(
|
|
| 102 |
editor = ImageEditor(
|
| 103 |
checkpoint_path=model_path,
|
| 104 |
num_inference_steps=20,
|
|
|
|
|
|
|
| 105 |
device="cuda:0",
|
| 106 |
)
|
| 107 |
|
|
|
|
| 81 |
|
| 82 |
# Quick start
|
| 83 |
|
| 84 |
+
**Note:** When using this distilled model, please set `image_guidance_scale` and `guidance_scale` to 0.0 to disable CFG.
|
| 85 |
|
| 86 |
```python
|
| 87 |
from PIL import Image
|
|
|
|
| 102 |
editor = ImageEditor(
|
| 103 |
checkpoint_path=model_path,
|
| 104 |
num_inference_steps=20,
|
| 105 |
+
image_guidance_scale=0.0,
|
| 106 |
+
guidance_scale=0.0,
|
| 107 |
device="cuda:0",
|
| 108 |
)
|
| 109 |
|