pip install einops torchvision

from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from PIL import Image
import requests

# load the processor
processor = AutoProcessor.from_pretrained(
    'allenai/Molmo-7B-D-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# load the model
model = AutoModelForCausalLM.from_pretrained(
    'allenai/Molmo-7B-D-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# process the image and text
inputs = processor.process(
    images=[Image.open(requests.get("https://picsum.photos/id/237/536/354", stream=True).raw)],
    text="Describe this image."
)

# move inputs to the correct device and make a batch of size 1
inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()}

# generate output; maximum 200 new tokens; stop generation when <|endoftext|> is generated
output = model.generate_from_batch(
    inputs,
    GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
    tokenizer=processor.tokenizer
)

# only get generated tokens; decode them to text
generated_tokens = output[0,inputs['input_ids'].size(1):]
generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)

# print the generated text
print(generated_text)

# >>>  This image features an adorable black Labrador puppy, captured from a top-down
#      perspective. The puppy is sitting on a wooden deck, which is composed ...

with torch.autocast(device_type="cuda", enabled=True, dtype=torch.bfloat16):
  output = model.generate_from_batch(
      inputs,
      GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
      tokenizer=processor.tokenizer
  )

model.to(dtype=torch.bfloat16)
inputs["images"] = inputs["images"].to(torch.bfloat16)
output = model.generate_from_batch(
    inputs,
    GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
    tokenizer=processor.tokenizer
)

from PIL import Image

image = Image.open(...)

if image.mode != "RGB":
    image = image.convert("RGB")

# Load the image
url = "..."
image = Image.open(requests.get(url, stream=True).raw)

# Convert the image to grayscale to calculate brightness
gray_image = image.convert('L')  # Convert to grayscale

# Calculate the average brightness
stat = ImageStat.Stat(gray_image)
average_brightness = stat.mean[0]  # Get the average value

# Define background color based on brightness (threshold can be adjusted)
bg_color = (0, 0, 0) if average_brightness > 127 else (255, 255, 255)

# Create a new image with the same size as the original, filled with the background color
new_image = Image.new('RGB', image.size, bg_color)

# Paste the original image on top of the background (use image as a mask if needed)
new_image.paste(image, (0, 0), image if image.mode == 'RGBA' else None)

# Now you can pass the new_image to Molmo
processor = AutoProcessor.from_pretrained(
    'allenai/Molmo-7B-D-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)