# Copyright 2024 Stability AI, Katherine Crowson and The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import math
import numpy as np
import torch

def compute_density_for_timestep_sampling(
    weighting_scheme: str, batch_size: int, logit_mean: float = None, logit_std: float = None, mode_scale: float = None
):
    """
    Compute the density for sampling the timesteps when doing SD3 training.

    Courtesy: This was contributed by Rafie Walker in https://github.com/huggingface/diffusers/pull/8528.

    SD3 paper reference: https://arxiv.org/abs/2403.03206v1.
    """
    if weighting_scheme == "logit_normal":
        # See 3.1 in the SD3 paper ($rf/lognorm(0.00,1.00)$).
        u = torch.normal(mean=logit_mean, std=logit_std, size=(batch_size,), device="cpu")
        u = torch.nn.functional.sigmoid(u)
    elif weighting_scheme == "mode":
        u = torch.rand(size=(batch_size,), device="cpu")
        u = 1 - u - mode_scale * (torch.cos(math.pi * u / 2) ** 2 - 1 + u)
    else:
        u = torch.rand(size=(batch_size,), device="cpu")
    return u


def compute_loss_weighting_for_sd3(weighting_scheme: str, sigmas=None):
    """
    Computes loss weighting scheme for SD3 training.

    Courtesy: This was contributed by Rafie Walker in https://github.com/huggingface/diffusers/pull/8528.

    SD3 paper reference: https://arxiv.org/abs/2403.03206v1.
    """
    if weighting_scheme == "sigma_sqrt":
        weighting = (sigmas**-2.0).float()
    elif weighting_scheme == "cosmap":
        bot = 1 - 2 * sigmas + 2 * sigmas**2
        weighting = 2 / (math.pi * bot)
    else:
        weighting = torch.ones_like(sigmas)
    return weighting