from PIL import Image
from transformers import AutoTokenizer, AutoModel, AutoImageProcessor, AutoModelForCausalLM
from transformers.generation.configuration_utils import GenerationConfig
from transformers.generation import LogitsProcessorList, PrefixConstrainedLogitsProcessor, UnbatchedClassifierFreeGuidanceLogitsProcessor
import torch

from modelscope import snapshot_download
 
# model path
EMU_HUB = snapshot_download("BAAI/Emu3-Stage1")
VQ_HUB = snapshot_download("BAAI/Emu3-VisionTokenizer")

import sys
sys.path.append(EMU_HUB)
from processing_emu3 import Emu3Processor

# prepare model and processor
model = AutoModelForCausalLM.from_pretrained(
    EMU_HUB,
    device_map="cuda:0",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(EMU_HUB, trust_remote_code=True, padding_side="left")
image_processor = AutoImageProcessor.from_pretrained(VQ_HUB, trust_remote_code=True)
image_tokenizer = AutoModel.from_pretrained(VQ_HUB, device_map="cuda:0", trust_remote_code=True).eval()
processor = Emu3Processor(image_processor, image_tokenizer, tokenizer, chat_template="{image_prompt}{text_prompt}")

# Image Generation
# prepare input
POSITIVE_PROMPT = " masterpiece, film grained, best quality."
NEGATIVE_PROMPT = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry."

classifier_free_guidance = 3.0
prompt = "a portrait of young girl."
prompt += POSITIVE_PROMPT

kwargs = dict(
    mode='G',
    ratio="1:1",
    image_area=model.config.image_area,
    return_tensors="pt",
    padding="longest",
)

pos_inputs = processor(text=prompt, **kwargs)
neg_inputs = processor(text=NEGATIVE_PROMPT, **kwargs)

# prepare hyper parameters
GENERATION_CONFIG = GenerationConfig(
    use_cache=True,
    eos_token_id=model.config.eos_token_id,
    pad_token_id=model.config.pad_token_id,
    max_new_tokens=40960,
    do_sample=True,
    top_k=2048,
)

h = pos_inputs.image_size[:, 0]
w = pos_inputs.image_size[:, 1]
constrained_fn = processor.build_prefix_constrained_fn(h, w)
logits_processor = LogitsProcessorList([
    UnbatchedClassifierFreeGuidanceLogitsProcessor(
        classifier_free_guidance,
        model,
        unconditional_ids=neg_inputs.input_ids.to("cuda:0"),
    ),
    PrefixConstrainedLogitsProcessor(
        constrained_fn ,
        num_beams=1,
    ),
])

# generate
outputs = model.generate(
    pos_inputs.input_ids.to("cuda:0"),
    GENERATION_CONFIG,
    logits_processor=logits_processor,
    attention_mask=pos_inputs.attention_mask.to("cuda:0"),
)

mm_list = processor.decode(outputs[0])
for idx, im in enumerate(mm_list):
    if not isinstance(im, Image.Image):
        continue
    im.save(f"result_{idx}.png")

# Multimodal Understanding
text = "The image depicts "
image = Image.open("assets/demo.png")
inputs = processor(
    text=text,
    image=image,
    mode='U',
    padding="longest",
    return_tensors="pt",
)

GENERATION_CONFIG = GenerationConfig(
    pad_token_id=tokenizer.pad_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=1024,
)

 outputs = model.generate(
     inputs.input_ids.to("cuda:0"),
     GENERATION_CONFIG,
     attention_mask=inputs.attention_mask.to("cuda:0"),
 )

 outputs = outputs[:, inputs.input_ids.shape[-1]:]
 answers = processor.batch_decode(outputs, skip_special_tokens=True)
 for ans in answers:
     print(ans)

git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .[llm]

# 默认：微调 LLM, 冻结 image tokenizer
CUDA_VISIBLE_DEVICES=0 swift sft \
  --model_type emu3-chat \
  --model_id_or_path BAAI/Emu3-Chat\
  --sft_type lora \
  --dataset coco-en-mini#500

# Deepspeed ZeRO2
NPROC_PER_NODE=4 \
CUDA_VISIBLE_DEVICES=0,1,2,3 swift sft \
  --model_type emu3-chat \
  --model_id_or_path BAAI/Emu3-Chat \
  --sft_type lora \
  --dataset coco-en-mini#500 \
  --deepspeed default-zero2

# val_dataset可选，如果不指定，则会从dataset中切出一部分数据集作为验证集
    --dataset train.jsonl \
    --val_dataset val.jsonl \
{"query": "<image>55555", "response": "66666", "images": ["image_path"]}
{"query": "<image><image>eeeee", "response": "fffff", "history": [], "images": ["image_path1", "image_path2"]}
{"query": "EEEEE", "response": "FFFFF", "history": [["query1", "response1"], ["query2", "response2"]]}

CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/emu3-chat/vx-xxx/checkpoint-xxx \
    --load_dataset_config true

# or merge-lora & infer
CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/emu3-chat/vx-xxx/checkpoint-xxx \
    --load_dataset_config true --merge_lora true