From a4f3112cbeacef74b7ad2266fed5d7f65e52aeb1 Mon Sep 17 00:00:00 2001 From: chflame163 Date: Tue, 10 Dec 2024 22:21:12 +0800 Subject: [PATCH] Florence2 nodes support Florence-2-Flux and Florence-2-Flus-Large --- README.md | 5 +- README_CN.MD | 1 + py/florence2_ultra.py | 4 +- py/imagefunc.py | 104 +++++++++++++++++++++--------------------- pyproject.toml | 2 +- 5 files changed, 60 insertions(+), 56 deletions(-) diff --git a/README.md b/README.md index 3c82419..2a219fd 100644 --- a/README.md +++ b/README.md @@ -25,14 +25,14 @@ Some JSON workflow files in the ```workflow``` directory, That's examples of git clone https://github.com/chflame163/ComfyUI_LayerStyle_Advance.git ``` -* Or download the zip file and extracted, copy the resulting folder to ```ComfyUI\custom_ Nodes``` +* Or download the zip file and extracted, copy the resulting folder to ```ComfyUI\custom_nodes``` ### Install dependency packages * for ComfyUI official portable package, double-click the ```install_requirements.bat``` in the plugin directory, for Aki ComfyUI package double-click on the ```install_requirements_aki.bat``` in the plugin directory, and wait for the installation to complete. * Or install dependency packages, open the cmd window in the ComfyUI_LayerStyle plugin directory like - ```ComfyUI\custom_ Nodes\ComfyUI_LayerStyle_Advance``` and enter the following command, + ```ComfyUI\custom_nodes\ComfyUI_LayerStyle_Advance``` and enter the following command,   for ComfyUI official portable package, type: @@ -144,6 +144,7 @@ Please try downgrading the ```protobuf``` dependency package to 3.20.3, or set e **If the dependency package error after updating, please double clicking ```repair_dependency.bat``` (for Official ComfyUI Protable) or ```repair_dependency_aki.bat``` (for ComfyUI-aki-v1.x) in the plugin folder to reinstall the dependency packages. +* Florence2 add support [gokaygokay/Florence-2-Flux-Large](https://huggingface.co/gokaygokay/Florence-2-Flux-Large) and [gokaygokay/Florence-2-Flux](https://huggingface.co/gokaygokay/Florence-2-Flux) models, download Florence-2-Flux-Large and Florence-2-Flux folder from [BaiduNetdisk](https://pan.baidu.com/s/1wBwJZjgMUKt0zluLAetMOQ?pwd=d6fb) or [huggingface](https://huggingface.co/chflame163/ComfyUI_LayerStyle/tree/main/ComfyUI/models/florence2) and copy to ```ComfyUI\models\florence2`` folder. * Discard the dependencies required for the [ObjectDetector YOLOWorld](#ObjectDetectorYOLOWorld) node from the requirements. txt file. To use this node, please manually install the dependency package. * Strip some nodes from [ComfyUI Layer Style](https://github.com/chflame163/ComfyUI_LayerStyle) to this repository. diff --git a/README_CN.MD b/README_CN.MD index a9d0b53..3fcbb17 100644 --- a/README_CN.MD +++ b/README_CN.MD @@ -120,6 +120,7 @@ If this call came from a _pb2.py file, your generated code is out of date and mu ## 更新说明 **如果本插件更新后出现依赖包错误，请双击运行插件目录下的```install_requirements.bat```(官方便携包)，或 ```install_requirements_aki.bat```(秋叶整合包) 重新安装依赖包。 +* Florence2 节点支持[gokaygokay/Florence-2-Flux-Large](https://huggingface.co/gokaygokay/Florence-2-Flux-Large) 和 [gokaygokay/Florence-2-Flux](https://huggingface.co/gokaygokay/Florence-2-Flux)模型。从[百度网盘](https://pan.baidu.com/s/1wBwJZjgMUKt0zluLAetMOQ?pwd=d6fb) 或者 [huggingface](https://huggingface.co/chflame163/ComfyUI_LayerStyle/tree/main/ComfyUI/models/florence2) 下载Florence-2-Flux-Large 和 Florence-2-Flux 两个目录，并放到```ComfyUI\models\florence2``文件夹。 * 从requirements.txt 中废弃 [ObjectDetector YOLOWorld](#ObjectDetectorYOLOWorld) 节点所需的依赖。如需使用此节点，请手动安装依赖包。 * 从ComfyUI Layer Style 剥离部分节点至本仓库。 diff --git a/py/florence2_ultra.py b/py/florence2_ultra.py index 4749f99..ac2b38c 100644 --- a/py/florence2_ultra.py +++ b/py/florence2_ultra.py @@ -27,7 +27,9 @@ fl2_model_repos = { "base-PromptGen-v1.5":"MiaoshouAI/Florence-2-base-PromptGen-v1.5", "large-PromptGen-v1.5":"MiaoshouAI/Florence-2-large-PromptGen-v1.5", "base-PromptGen-v2.0":"MiaoshouAI/Florence-2-base-PromptGen-v2.0", - "large-PromptGen-v2.0":"MiaoshouAI/Florence-2-large-PromptGen-v2.0" + "large-PromptGen-v2.0":"MiaoshouAI/Florence-2-large-PromptGen-v2.0", + "Florence-2-Flux":"gokaygokay/Florence-2-Flux", + "Florence-2-Flux-Large":"gokaygokay/Florence-2-Flux-Large" } def fixed_get_imports(filename) -> list[str]: diff --git a/py/imagefunc.py b/py/imagefunc.py index a20748f..285bbfc 100644 --- a/py/imagefunc.py +++ b/py/imagefunc.py @@ -1253,58 +1253,6 @@ def pixel_spread(image:Image, mask:Image) -> Image: return tensor2pil(torch.from_numpy(fg.astype(np.float32))) -def generate_text_image(text:str, font_path:str, font_size:int, text_color:str="#FFFFFF", - vertical:bool=True, stroke_width:int=1, stroke_color:str="#000000", - spacing:int=0, leading:int=0) -> tuple: - - lines = text.split("\n") - if vertical: - layout = "vertical" - else: - layout = "horizontal" - char_coordinates = [] - if layout == "vertical": - x = 0 - y = 0 - for i in range(len(lines)): - line = lines[i] - for char in line: - char_coordinates.append((x, y)) - y += font_size + spacing - x += font_size + leading - y = 0 - else: - x = 0 - y = 0 - for line in lines: - for char in line: - char_coordinates.append((x, y)) - x += font_size + spacing - y += font_size + leading - x = 0 - if layout == "vertical": - width = (len(lines) * (font_size + spacing)) - spacing - height = ((len(max(lines, key=len)) + 1) * (font_size + spacing)) + spacing - else: - width = (len(max(lines, key=len)) * (font_size + spacing)) - spacing - height = ((len(lines) - 1) * (font_size + spacing)) + font_size - - image = Image.new('RGBA', size=(width, height), color=stroke_color) - draw = ImageDraw.Draw(image) - font = ImageFont.truetype(font_path, font_size) - index = 0 - for i, line in enumerate(lines): - for j, char in enumerate(line): - x, y = char_coordinates[index] - if stroke_width > 0: - draw.text((x - stroke_width, y), char, font=font, fill=stroke_color) - draw.text((x + stroke_width, y), char, font=font, fill=stroke_color) - draw.text((x, y - stroke_width), char, font=font, fill=stroke_color) - draw.text((x, y + stroke_width), char, font=font, fill=stroke_color) - draw.text((x, y), char, font=font, fill=text_color) - index += 1 - return (image.convert('RGB'), image.split()[3]) - def watermark_image_size(image:Image) -> int: size = int(math.sqrt(image.width * image.height * 0.015625) * 0.9) return size @@ -1393,6 +1341,58 @@ def decode_watermark(image:Image, watermark_image_size:int=94) -> Image: ret_image = normalize_gray(ret_image) return ret_image +# def generate_text_image(text:str, font_path:str, font_size:int, text_color:str="#FFFFFF", +# vertical:bool=True, stroke_width:int=1, stroke_color:str="#000000", +# spacing:int=0, leading:int=0) -> tuple: +# +# lines = text.split("\n") +# if vertical: +# layout = "vertical" +# else: +# layout = "horizontal" +# char_coordinates = [] +# if layout == "vertical": +# x = 0 +# y = 0 +# for i in range(len(lines)): +# line = lines[i] +# for char in line: +# char_coordinates.append((x, y)) +# y += font_size + spacing +# x += font_size + leading +# y = 0 +# else: +# x = 0 +# y = 0 +# for line in lines: +# for char in line: +# char_coordinates.append((x, y)) +# x += font_size + spacing +# y += font_size + leading +# x = 0 +# if layout == "vertical": +# width = (len(lines) * (font_size + spacing)) - spacing +# height = ((len(max(lines, key=len)) + 1) * (font_size + spacing)) + spacing +# else: +# width = (len(max(lines, key=len)) * (font_size + spacing)) - spacing +# height = ((len(lines) - 1) * (font_size + spacing)) + font_size +# +# image = Image.new('RGBA', size=(width, height), color=stroke_color) +# draw = ImageDraw.Draw(image) +# font = ImageFont.truetype(font_path, font_size) +# index = 0 +# for i, line in enumerate(lines): +# for j, char in enumerate(line): +# x, y = char_coordinates[index] +# if stroke_width > 0: +# draw.text((x - stroke_width, y), char, font=font, fill=stroke_color) +# draw.text((x + stroke_width, y), char, font=font, fill=stroke_color) +# draw.text((x, y - stroke_width), char, font=font, fill=stroke_color) +# draw.text((x, y + stroke_width), char, font=font, fill=stroke_color) +# draw.text((x, y), char, font=font, fill=text_color) +# index += 1 +# return (image.convert('RGB'), image.split()[3]) + def generate_text_image(width:int, height:int, text:str, font_file:str, text_scale:float=1, font_color:str="#FFFFFF",) -> Image: image = Image.new("RGBA", (width, height), (0, 0, 0, 0)) draw = ImageDraw.Draw(image) diff --git a/pyproject.toml b/pyproject.toml index be98e18..9e21ef3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,7 +1,7 @@ [project] name = "comfyui_layerstyle_advance" description = "The nodes detached from ComfyUI Layer Style are mainly those with complex requirements for dependency packages." -version = "2.0.1" +version = "2.0.2" license = "MIT" dependencies = ["numpy", "matplotlib", "scikit_image", "scikit_learn", "opencv-contrib-python", "pymatting", "timm", "blend_modes", "transformers", "diffusers", "loguru", "colour-science", "huggingface_hub", "segment_anything", "addict", "omegaconf", "yapf", "wget", "iopath", "mediapipe", "typer_config", "fastapi", "rich", "google-generativeai", "ultralytics", "transparent-background", "accelerate", "onnxruntime", "bitsandbytes", "peft", "protobuf", "hydra-core", "blind-watermark", "qrcode", "pyzbar", "psd-tools", "wandb"]