import torch import torchvision.transforms.functional as TF import numpy as np import random import os import sys from diffusers.utils import load_image from diffusers import EulerDiscreteScheduler, T2IAdapter import gradio as gr from pipeline_t2i_adapter import PhotoMakerStableDiffusionXLAdapterPipeline from face_utils import FaceAnalysis2, analyze_faces from style_template import styles from aspect_ratio_template import aspect_ratios # global variable base_model_path = 'SG161222/RealVisXL_V4.0' face_detector = FaceAnalysis2(providers=['CPUExecutionProvider', 'CUDAExecutionProvider'], allowed_modules=['detection', 'recognition']) face_detector.prepare(ctx_id=0, det_size=(640, 640)) try: if torch.cuda.is_available(): device = "cuda" elif sys.platform == "darwin" and torch.backends.mps.is_available(): device = "mps" else: device = "cpu" except: device = "cpu" MAX_SEED = np.iinfo(np.int32).max STYLE_NAMES = list(styles.keys()) DEFAULT_STYLE_NAME = "Photographic (Default)" ASPECT_RATIO_LABELS = list(aspect_ratios) DEFAULT_ASPECT_RATIO = ASPECT_RATIO_LABELS[0] enable_doodle_arg = False if torch.cuda.is_available() and torch.cuda.is_bf16_supported(): torch_dtype = torch.bfloat16 else: torch_dtype = torch.float16 if device == "mps": torch_dtype = torch.float16 # load adapter adapter = T2IAdapter.from_pretrained( "TencentARC/t2i-adapter-sketch-sdxl-1.0", torch_dtype=torch_dtype, variant="fp16" ).to(device) pipe = PhotoMakerStableDiffusionXLAdapterPipeline.from_pretrained( base_model_path, adapter=adapter, torch_dtype=torch_dtype, use_safetensors=True, variant="fp16", ).to(device) pipe.load_photomaker_adapter( "TencentARC/PhotoMaker-V2", subfolder="", weight_name="photomaker-v2.bin", trigger_word="img", pm_version="v2", ) pipe.id_encoder.to(device) pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config) # pipe.set_adapters(["photomaker"], adapter_weights=[1.0]) pipe.fuse_lora() pipe.to(device) def generate_image( upload_images, prompt, negative_prompt, aspect_ratio_name, style_name, num_steps, style_strength_ratio, num_outputs, guidance_scale, seed, use_doodle, sketch_image, adapter_conditioning_scale, adapter_conditioning_factor, progress=gr.Progress(track_tqdm=True) ): if use_doodle: sketch_image = sketch_image["composite"] r, g, b, a = sketch_image.split() sketch_image = a.convert("RGB") sketch_image = TF.to_tensor(sketch_image) > 0.5 # Inversion sketch_image = TF.to_pil_image(sketch_image.to(torch.float32)) adapter_conditioning_scale = adapter_conditioning_scale adapter_conditioning_factor = adapter_conditioning_factor else: adapter_conditioning_scale = 0. adapter_conditioning_factor = 0. sketch_image = None # check the trigger word image_token_id = pipe.tokenizer.convert_tokens_to_ids(pipe.trigger_word) input_ids = pipe.tokenizer.encode(prompt) if image_token_id not in input_ids: raise gr.Error(f"Cannot find the trigger word '{pipe.trigger_word}' in text prompt! Please refer to step 2️⃣") if input_ids.count(image_token_id) > 1: raise gr.Error(f"Cannot use multiple trigger words '{pipe.trigger_word}' in text prompt!") # determine output dimensions by the aspect ratio output_w, output_h = aspect_ratios[aspect_ratio_name] print(f"[Debug] Generate image using aspect ratio [{aspect_ratio_name}] => {output_w} x {output_h}") # apply the style template prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt) if upload_images is None: raise gr.Error(f"Cannot find any input face image! Please refer to step 1️⃣") input_id_images = [] for img in upload_images: input_id_images.append(load_image(img)) id_embed_list = [] for img in input_id_images: img = np.array(img) img = img[:, :, ::-1] faces = analyze_faces(face_detector, img) if len(faces) > 0: id_embed_list.append(torch.from_numpy((faces[0]['embedding']))) if len(id_embed_list) == 0: raise gr.Error(f"No face detected, please update the input face image(s)") id_embeds = torch.stack(id_embed_list) generator = torch.Generator(device=device).manual_seed(seed) print("Start inference...") print(f"[Debug] Seed: {seed}") print(f"[Debug] Prompt: {prompt}, \n[Debug] Neg Prompt: {negative_prompt}") start_merge_step = int(float(style_strength_ratio) / 100 * num_steps) if start_merge_step > 30: start_merge_step = 30 print(start_merge_step) images = pipe( prompt=prompt, width=output_w, height=output_h, input_id_images=input_id_images, negative_prompt=negative_prompt, num_images_per_prompt=num_outputs, num_inference_steps=num_steps, start_merge_step=start_merge_step, generator=generator, guidance_scale=guidance_scale, id_embeds=id_embeds, image=sketch_image, adapter_conditioning_scale=adapter_conditioning_scale, adapter_conditioning_factor=adapter_conditioning_factor, ).images return images, gr.update(visible=True) def swap_to_gallery(images): return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False) def upload_example_to_gallery(images, prompt, style, negative_prompt): return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False) def remove_back_to_files(): return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True) def change_doodle_space(use_doodle): if use_doodle: return gr.update(visible=True) else: return gr.update(visible=False) def remove_tips(): return gr.update(visible=False) def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: if randomize_seed: seed = random.randint(0, MAX_SEED) return seed def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]: p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME]) return p.replace("{prompt}", positive), n + ' ' + negative def get_image_path_list(folder_name): image_basename_list = os.listdir(folder_name) image_path_list = sorted([os.path.join(folder_name, basename) for basename in image_basename_list]) return image_path_list def get_example(): case = [ [ get_image_path_list('./examples/scarletthead_woman'), "instagram photo, portrait photo of a woman img, colorful, perfect face, natural skin, hard shadows, film grain", "(No style)", "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", ], [ get_image_path_list('./examples/newton_man'), "sci-fi, closeup portrait photo of a man img wearing the sunglasses in Iron man suit, face, slim body, high quality, film grain", "(No style)", "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", ], ] return case ### Description and style logo = r"""
PhotoMaker logo
""" title = r"""

PhotoMaker V2：与PhotoMaker V1相比，改进了ID保真度和更好的可控性

""" description = r""" 使用方法可参考🎬 这个视频 🎬.
个性化步骤：
1️⃣ 上传您想要自定义的某个人的图像。一张或多张图片都行，建议多张。此工具不进行人脸检测，上传图像中的人脸应该占据图像的大部分。
2️⃣ 输入文本提示符，确保按照您想要自定义的类单词使用触发词: `img`, 例如： `man img` 、 `woman img` 或 `girl img`。
3️⃣ 选择您喜欢的风格模板。
4️⃣ (可选：新特性) 选择“启用绘图涂鸦...”选项，然后在画布上绘图
5️⃣ 单击提交按钮开始自定义。 """ tips = r""" ### 使用技巧 1. 上传多张要定制的人的照片，以**提高身份识别精度**。 2. 如果您发现使用涂鸦进行控制时图像质量很差，您可以减少`conditioning scale`和`factor of the adapter`。 """ # We have provided some generate examples and comparisons at: [this website](). css = ''' .gradio-container {width: 85% !important} ''' with gr.Blocks(css=css) as demo: gr.Markdown(logo) gr.Markdown(title) gr.Markdown(description) # gr.DuplicateButton( # value="Duplicate Space for private use ", # elem_id="duplicate-button", # visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1", # ) with gr.Row(): with gr.Column(): files = gr.Files( label="上传/选择一张或多张人脸照片", file_types=["image"] ) uploaded_files = gr.Gallery(label="你的图片", visible=False, columns=5, rows=1, height=200) with gr.Column(visible=False) as clear_button: remove_and_reupload = gr.ClearButton(value="移除并重新上传", components=files, size="sm") prompt = gr.Textbox(label="Prompt", info="尝试类似'a photo of a man/woman img'的词, 'img'是触发词，必须包含", placeholder="A photo of a [man/woman img]...") style = gr.Dropdown(label="风格", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME) aspect_ratio = gr.Dropdown(label="输出纵横比", choices=ASPECT_RATIO_LABELS, value=DEFAULT_ASPECT_RATIO) submit = gr.Button("提交") enable_doodle = gr.Checkbox( label="启用绘图涂鸦进行控制", value=enable_doodle_arg, info="启用此选项后，PhotoMaker将通过T2I-Adapter根据您在画布上的涂鸦生成内容（质量可能会降低）", ) with gr.Accordion("T2I-Adapter-涂鸦 (可选)", visible=False) as doodle_space: with gr.Row(): sketch_image = gr.Sketchpad( label="Canvas", type="pil", crop_size=[1024, 1024], layers=False, canvas_size=(350, 350), brush=gr.Brush(default_size=5, colors=["#000000"], color_mode="fixed") ) with gr.Group(): adapter_conditioning_scale = gr.Slider( label="Adapter conditioning scale", minimum=0.5, maximum=1, step=0.1, value=0.7, ) adapter_conditioning_factor = gr.Slider( label="Adapter conditioning factor", info="Fraction of timesteps for which adapter should be applied", minimum=0.5, maximum=1, step=0.1, value=0.8, ) with gr.Accordion(open=False, label="高级选项"): negative_prompt = gr.Textbox( label="Negative Prompt", placeholder="low quality", value="nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry", ) num_steps = gr.Slider( label="Number of sample steps", minimum=20, maximum=100, step=1, value=50, ) style_strength_ratio = gr.Slider( label="Style strength (%)", minimum=15, maximum=50, step=1, value=20, ) num_outputs = gr.Slider( label="Number of output images", minimum=1, maximum=4, step=1, value=2, ) guidance_scale = gr.Slider( label="Guidance scale", minimum=0.1, maximum=10.0, step=0.1, value=5, ) seed = gr.Slider( label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, ) randomize_seed = gr.Checkbox(label="Randomize seed", value=True) with gr.Column(): gallery = gr.Gallery(label="生成图片") usage_tips = gr.Markdown(label="使用技巧", value=tips, visible=False) files.upload(fn=swap_to_gallery, inputs=files, outputs=[uploaded_files, clear_button, files]) remove_and_reupload.click(fn=remove_back_to_files, outputs=[uploaded_files, clear_button, files]) enable_doodle.select(fn=change_doodle_space, inputs=enable_doodle, outputs=doodle_space) input_list = [ files, prompt, negative_prompt, aspect_ratio, style, num_steps, style_strength_ratio, num_outputs, guidance_scale, seed, enable_doodle, sketch_image, adapter_conditioning_scale, adapter_conditioning_factor ] submit.click( fn=remove_tips, outputs=usage_tips, ).then( fn=randomize_seed_fn, inputs=[seed, randomize_seed], outputs=seed, queue=False, api_name=False, ).then( fn=generate_image, inputs=input_list, outputs=[gallery, usage_tips] ) gr.Examples( examples=get_example(), inputs=[files, prompt, style, negative_prompt], run_on_click=True, fn=upload_example_to_gallery, outputs=[uploaded_files, clear_button, files], ) demo.launch(server_name='0.0.0.0', share=True)