import os
import sys

import torch
from diffusers import FlowMatchEulerDiscreteScheduler

current_file_path = os.path.abspath(__file__)
project_roots = [os.path.dirname(current_file_path), os.path.dirname(os.path.dirname(current_file_path)), os.path.dirname(os.path.dirname(os.path.dirname(current_file_path)))]
for project_root in project_roots:
    sys.path.insert(0, project_root) if project_root not in sys.path else None

from videox_fun.dist import set_multi_gpus_devices, shard_model
from videox_fun.models import (AutoencoderKLFlux2, AutoTokenizer,
                               LensGptOssEncoder, LensTransformer2DModel)
from videox_fun.pipeline import LensPipeline
from videox_fun.utils import (register_auto_device_hook,
                              safe_enable_group_offload)
from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler
from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler
from videox_fun.utils.fp8_optimization import (convert_model_weight_to_float8,
                                               convert_weight_dtype_wrapper)
from videox_fun.utils.lora_utils import merge_lora, unmerge_lora

# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload].
# model_full_load means that the entire model will be moved to the GPU.
# 
# model_full_load_and_qfloat8 means that the entire model will be moved to the GPU,
# and the transformer model has been quantized to float8, which can save more GPU memory. 
# 
# model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory.
# 
# model_cpu_offload_and_qfloat8 indicates that the entire model will be moved to the CPU after use, 
# and the transformer model has been quantized to float8, which can save more GPU memory. 
# 
# model_group_offload transfers internal layer groups between CPU/CUDA, 
# balancing memory efficiency and speed between full-module and leaf-level offloading methods.
# 
# sequential_cpu_offload means that each layer of the model will be moved to the CPU after use, 
# resulting in slower speeds but saving a large amount of GPU memory.
GPU_memory_mode     = "model_cpu_offload"
# Multi GPUs config
# Please ensure that the product of ulysses_degree and ring_degree equals the number of GPUs used. 
# For example, if you are using 8 GPUs, you can set ulysses_degree = 2 and ring_degree = 4.
# If you are using 1 GPU, you can set ulysses_degree = 1 and ring_degree = 1.
ulysses_degree      = 1
ring_degree         = 1
# Use FSDP to save more GPU memory in multi gpus.
fsdp_dit            = False
fsdp_text_encoder   = False
# Compile will give a speedup in fixed resolution and need a little GPU memory. 
# The compile_dit is not compatible with the fsdp_dit and sequential_cpu_offload.
compile_dit         = False

# model path
model_name          = "models/Diffusion_Transformer/Lens"

# Choose the sampler in "Flow", "Flow_Unipc", "Flow_DPM++"
sampler_name        = "Flow"

# Load pretrained model if need
transformer_path    = None
vae_path            = None
lora_path           = None

# Other params
sample_size         = [1728, 992]

# Use torch.float16 if GPU does not support torch.bfloat16
# ome graphics cards, such as v100, 2080ti, do not support torch.bfloat16
weight_dtype        = torch.bfloat16
# Set to True on A100/V100 to dequantize MXFP4 GPT-OSS weights.
dequantize_mxfp4    = False
prompt              = "1girl, black_hair, brown_eyes, earrings, freckles, grey_background, jewelry, lips, long_hair, looking_at_viewer, nose, piercing, realistic, red_lips, solo, upper_body"
negative_prompt     = " "
guidance_scale      = 4.5
seed                = 43
num_inference_steps = 40
lora_weight         = 0.55
save_path           = "samples/lens-t2i"

device = set_multi_gpus_devices(ulysses_degree, ring_degree)

# Get transformer
transformer = LensTransformer2DModel.from_pretrained(
    model_name,
    subfolder="transformer",
    low_cpu_mem_usage=True,
    torch_dtype=weight_dtype,
).to(weight_dtype)

if transformer_path is not None:
    print(f"From checkpoint: {transformer_path}")
    if transformer_path.endswith("safetensors"):
        from safetensors.torch import load_file, safe_open
        state_dict = load_file(transformer_path)
    else:
        state_dict = torch.load(transformer_path, map_location="cpu")
    state_dict = state_dict["state_dict"] if "state_dict" in state_dict else state_dict

    m, u = transformer.load_state_dict(state_dict, strict=False)
    print(f"missing keys: {len(m)}, unexpected keys: {len(u)}")

# Get Vae
vae = AutoencoderKLFlux2.from_pretrained(
    model_name,
    subfolder="vae",
).to(weight_dtype)

if vae_path is not None:
    print(f"From checkpoint: {vae_path}")
    if vae_path.endswith("safetensors"):
        from safetensors.torch import load_file, safe_open
        state_dict = load_file(vae_path)
    else:
        state_dict = torch.load(vae_path, map_location="cpu")
    state_dict = state_dict["state_dict"] if "state_dict" in state_dict else state_dict

    m, u = vae.load_state_dict(state_dict, strict=False)
    print(f"missing keys: {len(m)}, unexpected keys: {len(u)}")

# Get tokenizer and text_encoder
tokenizer = AutoTokenizer.from_pretrained(
    model_name, subfolder="tokenizer"
)
text_encoder_kwargs = {"subfolder": "text_encoder", "torch_dtype": weight_dtype}
try:
    from transformers import Mxfp4Config
    text_encoder_kwargs["quantization_config"] = Mxfp4Config(
        dequantize=dequantize_mxfp4
    )
except ImportError:
    pass  # Older transformers without Mxfp4Config

text_encoder = LensGptOssEncoder.from_pretrained(
    model_name, **text_encoder_kwargs
)

# Get Scheduler
Chosen_Scheduler = scheduler_dict = {
    "Flow": FlowMatchEulerDiscreteScheduler,
    "Flow_Unipc": FlowUniPCMultistepScheduler,
    "Flow_DPM++": FlowDPMSolverMultistepScheduler,
}[sampler_name]
scheduler = Chosen_Scheduler.from_pretrained(
    model_name, 
    subfolder="scheduler"
)

pipeline = LensPipeline(
    vae=vae,
    tokenizer=tokenizer,
    text_encoder=text_encoder,
    transformer=transformer,
    scheduler=scheduler,
)

if ulysses_degree > 1 or ring_degree > 1:
    from functools import partial
    transformer.enable_multi_gpus_inference()
    if fsdp_dit:
        shard_fn = partial(shard_model, device_id=device, param_dtype=weight_dtype, module_to_wrapper=list(transformer.transformer_blocks))
        pipeline.transformer = shard_fn(pipeline.transformer)
        print("Add FSDP DIT")
    if fsdp_text_encoder:
        shard_fn = partial(shard_model, device_id=device, param_dtype=weight_dtype, module_to_wrapper=list(text_encoder.model.layers))
        pipeline.text_encoder = shard_fn(pipeline.text_encoder)
        print("Add FSDP TEXT ENCODER")

if compile_dit:
    for i in range(len(pipeline.transformer.transformer_blocks)):
        pipeline.transformer.transformer_blocks[i] = torch.compile(pipeline.transformer.transformer_blocks[i])
    print("Add Compile")

if GPU_memory_mode == "sequential_cpu_offload":
    pipeline.enable_sequential_cpu_offload(device=device)
elif GPU_memory_mode == "model_group_offload":
    register_auto_device_hook(pipeline.transformer)
    safe_enable_group_offload(pipeline, onload_device=device, offload_device="cpu", offload_type="leaf_level", use_stream=True)
elif GPU_memory_mode == "model_cpu_offload_and_qfloat8":
    convert_model_weight_to_float8(transformer, exclude_module_name=["img_in", "txt_in", "timestep"], device=device)
    convert_weight_dtype_wrapper(transformer, weight_dtype)
    pipeline.enable_model_cpu_offload(device=device)
elif GPU_memory_mode == "model_cpu_offload":
    pipeline.enable_model_cpu_offload(device=device)
elif GPU_memory_mode == "model_full_load_and_qfloat8":
    convert_model_weight_to_float8(transformer, exclude_module_name=["img_in", "txt_in", "timestep"], device=device)
    convert_weight_dtype_wrapper(transformer, weight_dtype)
    pipeline.to(device=device)
else:
    pipeline.to(device=device)

generator = torch.Generator(device=device).manual_seed(seed)

if lora_path is not None:
    pipeline = merge_lora(pipeline, lora_path, lora_weight, device=device, dtype=weight_dtype)

with torch.no_grad():
    sample = pipeline(
        prompt, 
        negative_prompt = negative_prompt,
        height      = sample_size[0],
        width       = sample_size[1],
        generator   = generator,
        guidance_scale = guidance_scale,
        num_inference_steps = num_inference_steps,
    ).images

if lora_path is not None:
    pipeline = unmerge_lora(pipeline, lora_path, lora_weight, device=device, dtype=weight_dtype)

def save_results():
    if not os.path.exists(save_path):
        os.makedirs(save_path, exist_ok=True)

    index = len([path for path in os.listdir(save_path)]) + 1
    prefix = str(index).zfill(8)
    video_path = os.path.join(save_path, prefix + ".png")
    image = sample[0]
    image.save(video_path)

if ulysses_degree * ring_degree > 1:
    import torch.distributed as dist
    if dist.get_rank() == 0:
        save_results()
else:
    save_results()