takuma104

# Diffusers' ControlNet Implementation Subjective Evaluation
# https://github.com/takuma104/diffusers/tree/controlnet

import einops
import numpy as np
import pytest
import torch

from diffusers import StableDiffusionControlNetPipeline

takuma104

takuma104

import torch
from diffusers import UNet2DConditionModel

mem_bytes = torch.cuda.max_memory_allocated()
torch.cuda.reset_peak_memory_stats()
controlnet = UNet2DConditionModel.from_pretrained("takuma104/control_sd15_canny", subfolder="controlnet").cuda()
mem_bytes = torch.cuda.max_memory_allocated()
print(mem_bytes)

takuma104

import torch
import pytest
import PIL.Image
import numpy as np
from diffusers.utils import (
    PIL_INTERPOLATION,
)

# `batch` = batch_size * num_images_per_prompt
# When the input is a single image or a tensor with b==1, repeat it the `batch` times.

takuma104

import torch
import torch.nn.functional as F
import safetensors.torch
import sys


def load_checkpoint(fn):
    if fn.endswith(".safetensors"):
        checkpoint = safetensors.torch.load_file(fn)
    else:

takuma104

#!/bin/bash

models=("canny" "depth" "pose" )

for model in "${models[@]}"
do
    echo $model
    python merge_controlnet_diff.py --sd15 ../wd-1-5-beta2/checkpoints/wd-1-5-beta2-fp32.safetensors --control diff_control_wd15beta2_$model.safetensors --dst control_wd15beta2_$model.safetensors --fp16
done

takuma104

# Script for converting a HF Diffusers saved pipeline to a ControlNet checkpoint.
# *Only* converts the ControlNet.
# Does not convert optimizer state or any other thing.

import argparse
import os.path as osp
import re

import torch
from safetensors.torch import load_file, save_file

takuma104

Usage

from clip_text_custom_embedder import text_embeddings
from diffusers import StableDiffusionPipeline
import torch

takuma104

import math
import safetensors
import torch
from diffusers import DiffusionPipeline

"""
Kohya's LoRA format Loader for Diffusers

Usage:
```py

takuma104

import torch
import sys
from safetensors.torch import load_file
from diffusers import StableDiffusionPipeline

state_dict = load_file('some_lora.safetensors')
new_state_dict = {}
for key, value in state_dict.items():
    if "lora_down" in key:
        lora_name = key.split(".")[0]