import torch
from diffusers import ModularPipeline, ComponentsManager

# Use ComponentsManager to enable auto CPU offloading for memory efficiency
manager = ComponentsManager()
manager.enable_auto_cpu_offload(device="cuda:0")

pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image", components_manager=manager)
pipe.load_components(dtype=torch.bfloat16)

image = pipe(
    prompt="cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney",
).images[0]
image

print(pipe)

QwenImageModularPipeline {
  "_blocks_class_name": "QwenImageAutoBlocks",
  "_class_name": "QwenImageModularPipeline",
  "_diffusers_version": "0.37.0.dev0",
  "transformer": [
    "diffusers",
    "QwenImageTransformer2DModel",
    {
      "pretrained_model_name_or_path": "Qwen/Qwen-Image",
      "revision": null,
      "subfolder": "transformer",
      "type_hint": [
        "diffusers",
        "QwenImageTransformer2DModel"
      ],
      "variant": null
    }
  ],
  ...
}

print(pipe.blocks)

QwenImageAutoBlocks(
  Class: SequentialPipelineBlocks

  Description: Auto Modular pipeline for text-to-image, image-to-image, inpainting, and controlnet tasks using QwenImage.
      
      Supported workflows:
        - `text2image`: requires `prompt`
        - `image2image`: requires `prompt`, `image`
        - `inpainting`: requires `prompt`, `mask_image`, `image`
        - `controlnet_text2image`: requires `prompt`, `control_image`
        ...

  Components:
      text_encoder (`Qwen2_5_VLForConditionalGeneration`)
      vae (`AutoencoderKLQwenImage`)
      transformer (`QwenImageTransformer2DModel`)
      ...

  Sub-Blocks:
    [0] text_encoder (QwenImageAutoTextEncoderStep)
    [1] vae_encoder (QwenImageAutoVaeEncoderStep)
    [2] controlnet_vae_encoder (QwenImageOptionalControlNetVaeEncoderStep)
    [3] denoise (QwenImageAutoCoreDenoiseStep)
    [4] decode (QwenImageAutoDecodeStep)
)

from diffusers.utils import load_image

input_image = load_image("https://github.com/Trgtuan10/Image_storage/blob/main/cute_cat.png?raw=true")

image = pipe(
    prompt="cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney",
    image=input_image,
).images[0]

img2img_blocks = pipe.blocks.get_workflow("image2image")

vae_encoder_block = pipe.blocks.sub_blocks["vae_encoder"]
print(vae_encoder_block.doc)

vae_encoder_pipe = vae_encoder_block.init_pipeline()

# Reuse the VAE we already loaded, we can reuse it with update_components() method
vae_encoder_pipe.update_components(vae=pipe.vae)

# Run just this block
image_latents = vae_encoder_pipe(image=input_image).image_latents
print(image_latents.shape)

from diffusers.modular_pipelines import ModularPipelineBlocks

# Load a canny block from the Hub
canny_block = ModularPipelineBlocks.from_pretrained(
    "diffusers-internal-dev/canny-filtering",
    trust_remote_code=True,
)

print(canny_block.doc)

class CannyBlock

  Inputs:
      image (`Union[Image, ndarray]`):
          Image to compute canny filter on
      low_threshold (`int`, *optional*, defaults to 50):
          Low threshold for the canny filter.
      high_threshold (`int`, *optional*, defaults to 200):
          High threshold for the canny filter.
      ...

  Outputs:
      control_image (`PIL.Image`):
          Canny map for input image

# Get the controlnet workflow that we want to work with
blocks = pipe.blocks.get_workflow("controlnet_text2image")
print(blocks.doc)

class SequentialPipelineBlocks

  Inputs:
      prompt (`str`):
          The prompt or prompts to guide image generation.
      control_image (`Image`):
          Control image for ControlNet conditioning.
      ...

# Insert canny at the beginning
blocks.sub_blocks.insert("canny", canny_block, 0)

# Check the updated structure: CannyBlock is now listed as first sub-block
print(blocks)
# Check the updated doc
print(blocks.doc)

class SequentialPipelineBlocks

  Inputs:
      image (`Union[Image, ndarray]`):
          Image to compute canny filter on
      low_threshold (`int`, *optional*, defaults to 50):
          Low threshold for the canny filter.
      high_threshold (`int`, *optional*, defaults to 200):
          High threshold for the canny filter.
      prompt (`str`):
          The prompt or prompts to guide image generation.
      ...

pipeline = blocks.init_pipeline("Qwen/Qwen-Image", components_manager=manager)

pipeline.load_components(dtype=torch.bfloat16)

# Load the ControlNet model
controlnet_spec = pipeline.get_component_spec("controlnet")
controlnet_spec.pretrained_model_name_or_path = "InstantX/Qwen-Image-ControlNet-Union"
controlnet = controlnet_spec.load(dtype=torch.bfloat16)
pipeline.update_components(controlnet=controlnet)

from diffusers.utils import load_image

prompt = "cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney"
image = load_image("https://github.com/Trgtuan10/Image_storage/blob/main/cute_cat.png?raw=true")

output = pipeline(
    prompt=prompt,
    image=image,
).images[0]
output