Git-RSCLIP-ViT-L-16

This model is a mirror/redistribution of the original lcybuaa/Git-RSCLIP model.

Original Repository and Links

• Original Hugging Face Model: lcybuaa/Git-RSCLIP
• Official GitHub Repository: Chen-Yang-Liu/Text2Earth
• Paper: Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

Description

Git-RSCLIP is pre-trained on the Git-10M dataset, a global-scale remote sensing image-text pair dataset consisting of 10 million pairs. It uses a structure similar to SigLIP and is designed for tasks like image-text retrieval and zero-shot classification in the remote sensing domain.

How to use

With transformers

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

# Load model and processor
model = CLIPModel.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")
processor = CLIPProcessor.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")

# Load and process image
image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=["a photo of a building", "a photo of vegetation", "a photo of water"],
    images=image,
    return_tensors="pt",
    padding=True
)

# Get image-text similarity scores
with torch.inference_mode():
    outputs = model(**inputs)
    logits_per_image = outputs.logits_per_image
    probs = logits_per_image.softmax(dim=1)

print(f"Similarity scores: {probs}")

Zero-shot image classification:

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")
processor = CLIPProcessor.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")

# Define candidate labels
candidate_labels = [
    "a satellite image of urban area",
    "a satellite image of forest",
    "a satellite image of agricultural land",
    "a satellite image of water body"
]

image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=candidate_labels,
    images=image,
    return_tensors="pt",
    padding=True
)

with torch.inference_mode():
    outputs = model(**inputs)
    probs = outputs.logits_per_image.softmax(dim=1)

# Get the predicted label
predicted_idx = probs.argmax().item()
print(f"Predicted label: {candidate_labels[predicted_idx]}")
print(f"Confidence: {probs[0][predicted_idx]:.4f}")

Extracting individual features:

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")
processor = CLIPProcessor.from_pretrained("BiliSakura/Git-RSCLIP-ViT-L-16")

# Get image features only
image = Image.open("path/to/your/image.jpg")
image_inputs = processor(images=image, return_tensors="pt")

with torch.inference_mode():
    image_features = model.get_image_features(**image_inputs)

# Get text features only
text_inputs = processor(
    text=["a satellite image of urban area"],
    return_tensors="pt",
    padding=True,
    truncation=True
)

with torch.inference_mode():
    text_features = model.get_text_features(**text_inputs)

print(f"Image features shape: {image_features.shape}")
print(f"Text features shape: {text_features.shape}")

With diffusers

This model's text encoder can be used with Stable Diffusion and other diffusion models:

from diffusers import StableDiffusionPipeline
from transformers import CLIPTextModel, CLIPTokenizer
import torch

# Load the text encoder and tokenizer
text_encoder = CLIPTextModel.from_pretrained(
    "BiliSakura/Git-RSCLIP-ViT-L-16/diffusers",
    subfolder="text_encoder",
    torch_dtype=torch.float16
)
tokenizer = CLIPTokenizer.from_pretrained(
    "BiliSakura/Git-RSCLIP-ViT-L-16"
)

# Encode text prompt
prompt = "a satellite image of a city with buildings and roads"
text_inputs = tokenizer(
    prompt,
    padding="max_length",
    max_length=77,
    truncation=True,
    return_tensors="pt"
)

with torch.inference_mode():
    text_outputs = text_encoder(text_inputs.input_ids)
    text_embeddings = text_outputs.last_hidden_state

print(f"Text embeddings shape: {text_embeddings.shape}")

Using with Stable Diffusion:

from diffusers import StableDiffusionPipeline
import torch

# Load pipeline with custom text encoder
pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

# Generate image
prompt = "a high-resolution satellite image of urban area"
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
image.save("generated_image.png")

Citation

If you use this model in your research, please cite the original work:

@misc{liu2025text2earthunlockingtextdrivenremote,
      title={Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model}, 
      author={Chenyang Liu and Keyan Chen and Rui Zhao and Zhengxia Zou and Zhenwei Shi},
      year={2025},
      eprint={2501.00895},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2501.00895}, 
}