Merge pull request #1 from bmaltais/main

Proposed file structure rework and required file changes

.gitignore

@@ -1,3 +1,6 @@
 logs
 __pycache__
 wd14_tagger_model
+venv
+*.egg-info
+build

README.md

@@ -26,3 +26,63 @@ All documents are in Japanese currently, and CUI based.
 Including BLIP captioning and tagging by DeepDanbooru or WD14 tagger
 * [Image generation](https://note.com/kohya_ss/n/n2693183a798e)
 * [Model conversion](https://note.com/kohya_ss/n/n374f316fe4ad)
+
+## Windows Required Dependencies
+
+Python 3.10.6 and Git:
+
+- Python 3.10.6: https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe
+- git: https://git-scm.com/download/win
+
+Give unrestricted script access to powershell so venv can work:
+
+- Open an administrator powershell window
+- Type `Set-ExecutionPolicy Unrestricted` and answer A
+- Close admin powershell window
+
+## Windows Installation
+
+Open a regular Powershell terminal and type the following inside:
+
+```powershell
+git clone https://github.com/kohya-ss/sd-scripts.git
+cd sd-scripts
+
+python -m venv --system-site-packages venv
+.\venv\Scripts\activate
+
+pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116
+pip install --upgrade -r requirements_db_finetune.txt
+pip install -U -I --no-deps https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl
+
+cp .\bitsandbytes_windows\*.dll .\venv\Lib\site-packages\bitsandbytes\
+cp .\bitsandbytes_windows\cextension.py .\venv\Lib\site-packages\bitsandbytes\cextension.py
+cp .\bitsandbytes_windows\main.py .\venv\Lib\site-packages\bitsandbytes\cuda_setup\main.py
+
+accelerate config
+
+```
+
+Answers to accelerate config:
+
+```txt
+- 0
+- 0
+- NO
+- NO
+- All
+- fp16
+```
+
+## Upgrade
+
+When a new release comes out you can upgrade your repo with the following command:
+
+```powershell
+cd kohya_diffusers_fine_tuning
+git pull
+.\venv\Scripts\activate
+pip install --upgrade -r <requirement file name>
+```
+
+Once the commands have completed successfully you should be ready to use the new version.

bitsandbytes_windows/cextension.py

@@ -0,0 +1,54 @@
+import ctypes as ct
+from pathlib import Path
+from warnings import warn
+
+from .cuda_setup.main import evaluate_cuda_setup
+
+
+class CUDALibrary_Singleton(object):
+    _instance = None
+
+    def __init__(self):
+        raise RuntimeError("Call get_instance() instead")
+
+    def initialize(self):
+        binary_name = evaluate_cuda_setup()
+        package_dir = Path(__file__).parent
+        binary_path = package_dir / binary_name
+
+        if not binary_path.exists():
+            print(f"CUDA SETUP: TODO: compile library for specific version: {binary_name}")
+            legacy_binary_name = "libbitsandbytes.so"
+            print(f"CUDA SETUP: Defaulting to {legacy_binary_name}...")
+            binary_path = package_dir / legacy_binary_name
+            if not binary_path.exists():
+                print('CUDA SETUP: CUDA detection failed. Either CUDA driver not installed, CUDA not installed, or you have multiple conflicting CUDA libraries!')
+                print('CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.')
+                raise Exception('CUDA SETUP: Setup Failed!')
+            # self.lib = ct.cdll.LoadLibrary(binary_path)
+            self.lib = ct.cdll.LoadLibrary(str(binary_path))            # $$$
+        else:
+            print(f"CUDA SETUP: Loading binary {binary_path}...")
+            # self.lib = ct.cdll.LoadLibrary(binary_path)
+            self.lib = ct.cdll.LoadLibrary(str(binary_path))            # $$$
+
+    @classmethod
+    def get_instance(cls):
+        if cls._instance is None:
+            cls._instance = cls.__new__(cls)
+            cls._instance.initialize()
+        return cls._instance
+
+
+lib = CUDALibrary_Singleton.get_instance().lib
+try:
+    lib.cadam32bit_g32
+    lib.get_context.restype = ct.c_void_p
+    lib.get_cusparse.restype = ct.c_void_p
+    COMPILED_WITH_CUDA = True
+except AttributeError:
+    warn(
+        "The installed version of bitsandbytes was compiled without GPU support. "
+        "8-bit optimizers and GPU quantization are unavailable."
+    )
+    COMPILED_WITH_CUDA = False

bitsandbytes_windows/main.py

@@ -0,0 +1,166 @@
+"""
+extract factors the build is dependent on:
+[X] compute capability
+    [ ] TODO: Q - What if we have multiple GPUs of different makes?
+- CUDA version
+- Software:
+    - CPU-only: only CPU quantization functions (no optimizer, no matrix multipl)
+    - CuBLAS-LT: full-build 8-bit optimizer
+    - no CuBLAS-LT: no 8-bit matrix multiplication (`nomatmul`)
+
+evaluation:
+    - if paths faulty, return meaningful error
+    - else:
+        - determine CUDA version
+        - determine capabilities
+        - based on that set the default path
+"""
+
+import ctypes
+
+from .paths import determine_cuda_runtime_lib_path
+
+
+def check_cuda_result(cuda, result_val):
+    # 3. Check for CUDA errors
+    if result_val != 0:
+        error_str = ctypes.c_char_p()
+        cuda.cuGetErrorString(result_val, ctypes.byref(error_str))
+        print(f"CUDA exception! Error code: {error_str.value.decode()}")
+
+def get_cuda_version(cuda, cudart_path):
+    # https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART____VERSION.html#group__CUDART____VERSION
+    try:
+        cudart = ctypes.CDLL(cudart_path)
+    except OSError:
+        # TODO: shouldn't we error or at least warn here?
+        print(f'ERROR: libcudart.so could not be read from path: {cudart_path}!')
+        return None
+
+    version = ctypes.c_int()
+    check_cuda_result(cuda, cudart.cudaRuntimeGetVersion(ctypes.byref(version)))
+    version = int(version.value)
+    major = version//1000
+    minor = (version-(major*1000))//10
+
+    if major < 11:
+       print('CUDA SETUP: CUDA version lower than 11 are currenlty not supported for LLM.int8(). You will be only to use 8-bit optimizers and quantization routines!!')
+
+    return f'{major}{minor}'
+
+
+def get_cuda_lib_handle():
+    # 1. find libcuda.so library (GPU driver) (/usr/lib)
+    try:
+        cuda = ctypes.CDLL("libcuda.so")
+    except OSError:
+        # TODO: shouldn't we error or at least warn here?
+        print('CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!')
+        return None
+    check_cuda_result(cuda, cuda.cuInit(0))
+
+    return cuda
+
+
+def get_compute_capabilities(cuda):
+    """
+    1. find libcuda.so library (GPU driver) (/usr/lib)
+       init_device -> init variables -> call function by reference
+    2. call extern C function to determine CC
+       (https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__DEVICE__DEPRECATED.html)
+    3. Check for CUDA errors
+       https://stackoverflow.com/questions/14038589/what-is-the-canonical-way-to-check-for-errors-using-the-cuda-runtime-api
+    # bits taken from https://gist.github.com/f0k/63a664160d016a491b2cbea15913d549
+    """
+
+
+    nGpus = ctypes.c_int()
+    cc_major = ctypes.c_int()
+    cc_minor = ctypes.c_int()
+
+    device = ctypes.c_int()
+
+    check_cuda_result(cuda, cuda.cuDeviceGetCount(ctypes.byref(nGpus)))
+    ccs = []
+    for i in range(nGpus.value):
+        check_cuda_result(cuda, cuda.cuDeviceGet(ctypes.byref(device), i))
+        ref_major = ctypes.byref(cc_major)
+        ref_minor = ctypes.byref(cc_minor)
+        # 2. call extern C function to determine CC
+        check_cuda_result(
+            cuda, cuda.cuDeviceComputeCapability(ref_major, ref_minor, device)
+        )
+        ccs.append(f"{cc_major.value}.{cc_minor.value}")
+
+    return ccs
+
+
+# def get_compute_capability()-> Union[List[str, ...], None]: # FIXME: error
+def get_compute_capability(cuda):
+    """
+    Extracts the highest compute capbility from all available GPUs, as compute
+    capabilities are downwards compatible. If no GPUs are detected, it returns
+    None.
+    """
+    ccs = get_compute_capabilities(cuda)
+    if ccs is not None:
+        # TODO: handle different compute capabilities; for now, take the max
+        return ccs[-1]
+    return None
+
+
+def evaluate_cuda_setup():
+    print('')
+    print('='*35 + 'BUG REPORT' + '='*35)
+    print('Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues')
+    print('For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link')
+    print('='*80)
+    return "libbitsandbytes_cuda116.dll"            # $$$
+    
+    binary_name = "libbitsandbytes_cpu.so"
+    #if not torch.cuda.is_available():
+        #print('No GPU detected. Loading CPU library...')
+        #return binary_name
+
+    cudart_path = determine_cuda_runtime_lib_path()
+    if cudart_path is None:
+        print(
+            "WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!"
+        )
+        return binary_name
+
+    print(f"CUDA SETUP: CUDA runtime path found: {cudart_path}")
+    cuda = get_cuda_lib_handle()
+    cc = get_compute_capability(cuda)
+    print(f"CUDA SETUP: Highest compute capability among GPUs detected: {cc}")
+    cuda_version_string = get_cuda_version(cuda, cudart_path)
+
+
+    if cc == '':
+        print(
+            "WARNING: No GPU detected! Check your CUDA paths. Processing to load CPU-only library..."
+        )
+        return binary_name
+
+    # 7.5 is the minimum CC vor cublaslt
+    has_cublaslt = cc in ["7.5", "8.0", "8.6"]
+
+    # TODO:
+    # (1) CUDA missing cases (no CUDA installed by CUDA driver (nvidia-smi accessible)
+    # (2) Multiple CUDA versions installed
+
+    # we use ls -l instead of nvcc to determine the cuda version
+    # since most installations will have the libcudart.so installed, but not the compiler
+    print(f'CUDA SETUP: Detected CUDA version {cuda_version_string}')
+
+    def get_binary_name():
+        "if not has_cublaslt (CC < 7.5), then we have to choose  _nocublaslt.so"
+        bin_base_name = "libbitsandbytes_cuda"
+        if has_cublaslt:
+            return f"{bin_base_name}{cuda_version_string}.so"
+        else:
+            return f"{bin_base_name}{cuda_version_string}_nocublaslt.so"
+
+    binary_name = get_binary_name()
+
+    return binary_name

fine_tune.py

@@ -50,7 +50,7 @@ import numpy as np
 from einops import rearrange
 from torch import einsum
 
-import model_util
+import library.model_util as model_util
 
 # Tokenizer: checkpointから読み込むのではなくあらかじめ提供されているものを使う
 TOKENIZER_PATH = "openai/clip-vit-large-patch14"

finetune/prepare_buckets_latents.py

@@ -14,7 +14,7 @@ import cv2
 import torch
 from torchvision import transforms
 
-import model_util
+import library.model_util as model_util
 
 DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 

requirements_blip.txt

@@ -1,3 +1,4 @@
 timm==0.4.12
 transformers==4.16.2
 fairscale==0.4.4
+.

requirements_db_finetune.txt

@@ -6,3 +6,7 @@ opencv-python
 einops
 pytorch_lightning
 safetensors
+bitsandbytes==0.35.0
+tensorboard
+diffusers[torch]==0.10.2
+.

requirements_wd14_tagger.txt

@@ -1,2 +1,3 @@
 tensorflow<2.11
 huggingface-hub
+.

setup.py

@@ -0,0 +1,3 @@
+from setuptools import setup, find_packages
+ 
+setup(name = "library", packages = find_packages())

tools/convert_diffusers20_original_sd.py

@@ -9,7 +9,7 @@ import os
 import torch
 from diffusers import StableDiffusionPipeline
 
-import model_util
+import library.model_util as model_util
 
 
 def convert(args):

train_db.py

@@ -43,7 +43,7 @@ import cv2
 from einops import rearrange
 from torch import einsum
 
-import model_util
+import library.model_util as model_util
 
 # Tokenizer: checkpointから読み込むのではなくあらかじめ提供されているものを使う
 TOKENIZER_PATH = "openai/clip-vit-large-patch14"