import torch
from diffusers import DPMSolverMultistepScheduler, StableDiffusionXLPipeline
from diffusers.callbacks import SDXLCFGCutoffCallback

callback = SDXLCFGCutoffCallback(cutoff_step_ratio=0.4)
# if using cutoff_step_index
# callback = SDXLCFGCutoffCallback(cutoff_step_ratio=None, cutoff_step_index=10)

pipeline = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    dtype=torch.float16,
    device_map="cuda"  # or "mps", "xpu", "cpu"
)
pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, use_karras_sigmas=True)

prompt = "a sports car on the road, best quality, high quality, high detail, 8k resolution"
output = pipeline(
    prompt=prompt,
    negative_prompt="",
    guidance_scale=6.5,
    num_inference_steps=25,
    callback_on_step_end=callback,
)

import torch
from diffusers import DiffusionPipeline

def interrupt_callback(pipeline, i, t, callback_kwargs):
    stop_idx = 10
    if i == stop_idx:
        pipeline._interrupt = True
    return callback_kwargs

pipeline = DiffusionPipeline.from_pretrained(
    "Qwen/Qwen-Image",
    dtype=torch.bfloat16,
    device_map="cuda",  # or "mps", "xpu", "cpu"
)
pipeline(
    prompt="A photo of a cat",
    num_inference_steps=50,
    callback_on_step_end=interrupt_callback,
)

import torch
from PIL import Image
from diffusers import AutoPipelineForText2Image

def latents_to_rgb(latents):
    weights = (
        (60, -60, 25, -70),
        (60,  -5, 15, -50),
        (60,  10, -5, -35),
    )

    weights_tensor = torch.t(torch.tensor(weights, dtype=latents.dtype).to(latents.device))
    biases_tensor = torch.tensor((150, 140, 130), dtype=latents.dtype).to(latents.device)
    rgb_tensor = torch.einsum("...lxy,lr -> ...rxy", latents, weights_tensor) + biases_tensor.unsqueeze(-1).unsqueeze(-1)
    image_array = rgb_tensor.clamp(0, 255).byte().cpu().numpy().transpose(1, 2, 0)

    return Image.fromarray(image_array)

def decode_tensors(pipe, step, timestep, callback_kwargs):
    latents = callback_kwargs["latents"]

    image = latents_to_rgb(latents[0])
    image.save(f"{step}.png")

    return callback_kwargs

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    dtype=torch.float16,
    device_map="cuda"  # or "mps", "xpu", "cpu"
)

image = pipeline(
    prompt="A croissant shaped like a cute bear.",
    negative_prompt="Deformed, ugly, bad anatomy",
    callback_on_step_end=decode_tensors,
    callback_on_step_end_tensor_inputs=["latents"],
).images[0]

from typing import Callable

import torch
from diffusers import ModularPipeline
from diffusers.modular_pipelines import InputParam, LoopSequentialPipelineBlocks, ModularPipelineBlocks


class CallbackOnStepEnd(ModularPipelineBlocks):
    @property
    def inputs(self):
        return [
            InputParam(
                "callback_on_step_end",
                type_hint=Callable,
                description="Called after each scheduler step as `callback(pipe, i, t, {'latents': ...})`; the dict it returns is written back.",
            ),
            InputParam("latents", required=True),
        ]

    def __call__(self, components, block_state, i, t):
        if block_state.callback_on_step_end is not None:
            outputs = block_state.callback_on_step_end(components, i, t, {"latents": block_state.latents})
            block_state.latents = outputs.get("latents", block_state.latents)
        return components, block_state


def walk_denoise_loops(block):
    """Every denoising loop in the blocks, whichever workflow it belongs to."""
    if isinstance(block, LoopSequentialPipelineBlocks) and "denoiser" in block.sub_blocks:
        yield block
    for sub in getattr(block, "sub_blocks", {}).values():
        yield from walk_denoise_loops(sub)


repo_id = "stabilityai/stable-diffusion-xl-base-1.0"
blocks = ModularPipeline.from_pretrained(repo_id).blocks
for loop in walk_denoise_loops(blocks):
    loop.sub_blocks["callback"] = CallbackOnStepEnd()  # appended after the last step of the loop
pipe = blocks.init_pipeline(repo_id)
pipe.load_components(dtype=torch.float16)
pipe.to("cuda")

image = pipe(prompt="A croissant shaped like a cute bear.", callback_on_step_end=decode_tensors, output="images")[0]