from typing import List
import torch
import PIL.Image
from diffusers import AutoencoderKLWan, WanVACEPipeline, WanVACETransformer3DModel
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image, load_video
from diffusers import GGUFQuantizationConfig

model_id = "a-r-r-o-w/Wan-VACE-1.3B-diffusers"
transformer_path = f"https://huggingface.co/newgenai79/Wan-VACE-1.3B-diffusers-gguf/blob/main/Wan-VACE-1.3B-diffusers-Q8_0.gguf"
transformer_gguf = WanVACETransformer3DModel.from_single_file(
    transformer_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    torch_dtype=torch.bfloat16,
    config=model_id,
    subfolder="transformer",
)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanVACEPipeline.from_pretrained(
    model_id,
    transformer=transformer_gguf,
    vae=vae, 
    torch_dtype=torch.bfloat16
)
flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()


prompt = "A sleek, humanoid robot stands in a vast warehouse filled with neatly stacked cardboard boxes on industrial shelves. The robot's metallic body gleams under the bright, even lighting, highlighting its futuristic design and intricate joints. A glowing blue light emanates from its chest, adding a touch of advanced technology. The background is dominated by rows of boxes, suggesting a highly organized storage system. The floor is lined with wooden pallets, enhancing the industrial setting. The camera remains static, capturing the robot's poised stance amidst the orderly environment, with a shallow depth of field that keeps the focus on the robot while subtly blurring the background for a cinematic effect."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"

output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=832,
    height=480,
    num_frames=81,
    num_inference_steps=30,
    guidance_scale=5.0,
    conditioning_scale=0.0,
    generator=torch.Generator().manual_seed(0),
).frames[0]
export_to_video(output, "output.mp4", fps=16)

def _should_convert_state_dict_to_diffusers(model_state_dict, checkpoint_state_dict):
    return not set(model_state_dict.keys()).issubset(set(checkpoint_state_dict.keys())