git clone https://github.com/lllyasviel/ControlNet

conda env create -f environment.yaml

mkdir training

wget https://huggingface.co/lllyasviel/ControlNet/blob/main/training/fill50k.zip

unzip fill50k

python tutorial_dataset_test.py

python tool_add_control_sd21.py models/wd-15-2.6-186k.ckpt models/control-wd15-2.6-186k-ini.ckpt 

import json
import cv2
import numpy as np

from torch.utils.data import Dataset


class MyDataset(Dataset):
    def __init__(self):
        self.data = []
        with open('./training/fill50k/prompt.json', 'rt') as f:
            for line in f:
                self.data.append(json.loads(line))

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        item = self.data[idx]

        source_filename = item['source']
        target_filename = item['target']
        prompt = item['prompt']

        source = cv2.imread('./training/fill50k/' + source_filename)
        target = cv2.imread('./training/fill50k/' + target_filename)

        # Do not forget that OpenCV read images in BGR order.
        source = cv2.cvtColor(source, cv2.COLOR_BGR2RGB)
        target = cv2.cvtColor(target, cv2.COLOR_BGR2RGB)

        # Normalize source images to [0, 1].
        source = source.astype(np.float32) / 255.0

        # Normalize target images to [-1, 1].
        target = (target.astype(np.float32) / 127.5) - 1.0

        return dict(jpg=target, txt=prompt, hint=source)

from share import *

import pytorch_lightning as pl
from torch.utils.data import DataLoader
from tutorial_dataset import MyDataset
from cldm.logger import ImageLogger
from cldm.model import create_model, load_state_dict


# Configs
resume_path = './models/control_sd21_ini.ckpt'
batch_size = 4
logger_freq = 300
learning_rate = 1e-5
sd_locked = True
only_mid_control = False


# First use cpu to load models. Pytorch Lightning will automatically move it to GPUs.
model = create_model('./models/cldm_v21.yaml').cpu()
model.load_state_dict(load_state_dict(resume_path, location='cpu'))
model.learning_rate = learning_rate
model.sd_locked = sd_locked
model.only_mid_control = only_mid_control


# Misc
dataset = MyDataset()
dataloader = DataLoader(dataset, num_workers=0, batch_size=batch_size, shuffle=True)
logger = ImageLogger(batch_frequency=logger_freq)
trainer = pl.Trainer(gpus=1, precision=32, callbacks=[logger])


# Train!
trainer.fit(model, dataloader)

python tutorial_train_sd21 .py

model:
  target: cldm.cldm.ControlLDM
  params:
+  parameterization: "v"
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "jpg"
    cond_stage_key: "txt"
    control_key: "hint"
    image_size: 64
    channels: 4
    cond_stage_trainable: false
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False
    only_mid_control: False

    control_stage_config:
      target: cldm.cldm.ControlNet
      params:
        use_checkpoint: True
        image_size: 32 # unused
        in_channels: 4
        hint_channels: 3
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_head_channels: 64 # need to fix for flash-attn
        use_spatial_transformer: True
        use_linear_in_transformer: True
        transformer_depth: 1
        context_dim: 1024
        legacy: False

    unet_config:
      target: cldm.cldm.ControlledUnetModel
      params:
        use_checkpoint: True
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_head_channels: 64 # need to fix for flash-attn
        use_spatial_transformer: True
        use_linear_in_transformer: True
        transformer_depth: 1
        context_dim: 1024
        legacy: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          #attn_type: "vanilla-xformers"
          double_z: true
          z_channels: 4
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
          - 1
          - 2
          - 4
          - 4
          num_res_blocks: 2
          attn_resolutions: []
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity

    cond_stage_config:
      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
      params:
        freeze: True
        layer: "penultimate"