import torch
from diffusers import DiffusionPipeline
from diffusers.quantizers import PipelineQuantizationConfig

torch._dynamo.config.cache_size_limit = 1000
torch._dynamo.config.capture_dynamic_output_shape_ops = True

# quantize
pipeline_quant_config = PipelineQuantizationConfig(
    quant_backend="bitsandbytes_4bit",
    quant_kwargs={"load_in_4bit": True, "bnb_4bit_quant_type": "nf4", "bnb_4bit_compute_dtype": torch.bfloat16},
    components_to_quantize=["transformer", "text_encoder_2"],
)
pipeline = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    quantization_config=pipeline_quant_config,
    dtype=torch.bfloat16,
).to("cuda")  # or "mps", "xpu", "cpu"

# model CPU offloading
pipeline.enable_model_cpu_offload()

# compile
pipeline.transformer.compile()
pipeline(
    "cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"
).images[0]

# pip install ftfy
import torch
from diffusers import AutoModel, DiffusionPipeline
from diffusers.hooks import apply_group_offloading
from diffusers.utils import export_to_video
from diffusers.quantizers import PipelineQuantizationConfig
from transformers import UMT5EncoderModel

torch._dynamo.config.cache_size_limit = 1000
torch._dynamo.config.capture_dynamic_output_shape_ops = True

# quantize
pipeline_quant_config = PipelineQuantizationConfig(
    quant_backend="bitsandbytes_4bit",
    quant_kwargs={"load_in_4bit": True, "bnb_4bit_quant_type": "nf4", "bnb_4bit_compute_dtype": torch.bfloat16},
    components_to_quantize=["transformer", "text_encoder"],
)

text_encoder = UMT5EncoderModel.from_pretrained(
    "Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", dtype=torch.bfloat16
)
pipeline = DiffusionPipeline.from_pretrained(
    "Wan-AI/Wan2.1-T2V-14B-Diffusers",
    quantization_config=pipeline_quant_config,
    dtype=torch.bfloat16,
).to("cuda")  # or "mps", "xpu", "cpu"

# group offloading
onload_device = torch.device("cuda")
offload_device = torch.device("cpu")

pipeline.transformer.enable_group_offload(
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="leaf_level",
    use_stream=True,
    non_blocking=True
)
pipeline.vae.enable_group_offload(
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="leaf_level",
    use_stream=True,
    non_blocking=True
)
apply_group_offloading(
    pipeline.text_encoder,
    onload_device=onload_device,
    offload_type="leaf_level",
    use_stream=True,
    non_blocking=True
)

# compile
pipeline.transformer.compile()

prompt = """
The camera rushes from far to near in a low-angle shot, 
revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
"""
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 = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)