import torch
from modelscope import AutoModelForCausalLM, AutoTokenizer
from encoder.image_tokenizer import ImageTokenizer
from decoder.utils import generate_crop_size_list, var_center_crop
from decoder import decode_vq_tokens
from PIL import Image

model_path = "inclusionAI/LLaDA2.0-Uni"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path, device_map="auto", torch_dtype="bfloat16", trust_remote_code=True
).eval()
model.tokenizer = tokenizer

# Encode source image
image_tokenizer = ImageTokenizer(model_path=model_path, device="cuda")
crop_size_list = generate_crop_size_list((512 // 32) ** 2, 32)
pil_image = var_center_crop(Image.open("./assets/edit_example.png").convert("RGB"), crop_size_list=crop_size_list)
info = image_tokenizer.encode_with_info(pil_image)
image_tokens = [x + model.config.image_token_offset for x in info["token_ids"]]
_, h, w = info["grid_thw"]

# Edit the image
result = model.edit_image(
    image_tokens, h, w,
    instruction="Change the background to a beach.",
    steps=8, cfg_text_scale=4.0,
)

# Decode to PIL image
edited_image = decode_vq_tokens(result["token_ids"], result["h"], result["w"], model_path, "cuda", num_steps=8, decode_mode="decoder-turbo",)
edited_image.save("edited.png")