Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| from diffusers import ( | |
| StableDiffusionPipeline, | |
| ControlNetModel, | |
| StableDiffusionControlNetPipeline, | |
| StableDiffusionControlNetImg2ImgPipeline, | |
| AutoPipelineForImage2Image, | |
| DDIMScheduler, | |
| UniPCMultistepScheduler) | |
| from transformers import pipeline | |
| from diffusers.utils import load_image, make_image_grid | |
| from peft import PeftModel, LoraConfig | |
| import os | |
| from PIL import Image | |
| MAX_SEED = np.iinfo(np.int32).max | |
| MAX_IMAGE_SIZE = 1024 | |
| IP_ADAPTER = 'h94/IP-Adapter' | |
| WEIGHT_NAME = "ip-adapter_sd15.bin" | |
| WEIGHT_NAME_plus = "ip-adapter-plus_sd15.bin" | |
| WEIGHT_NAME_face = "ip-adapter-full-face_sd15.bin" | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| model_default = "stable-diffusion-v1-5/stable-diffusion-v1-5" | |
| torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32 | |
| def get_lora_sd_pipeline( | |
| lora_dir='lora_man_animestyle', | |
| base_model_name_or_path=None, | |
| dtype=torch.float16, | |
| adapter_name="default" | |
| ): | |
| unet_sub_dir = os.path.join(lora_dir, "unet") | |
| text_encoder_sub_dir = os.path.join(lora_dir, "text_encoder") | |
| if os.path.exists(text_encoder_sub_dir) and base_model_name_or_path is None: | |
| config = LoraConfig.from_pretrained(text_encoder_sub_dir) | |
| base_model_name_or_path = config.base_model_name_or_path | |
| if base_model_name_or_path is None: | |
| raise ValueError("Укажите название базовой модели или путь к ней") | |
| pipe = StableDiffusionPipeline.from_pretrained(base_model_name_or_path, torch_dtype=dtype) | |
| before_params = pipe.unet.parameters() | |
| pipe.unet = PeftModel.from_pretrained(pipe.unet, unet_sub_dir, adapter_name=adapter_name) | |
| pipe.unet.set_adapter(adapter_name) | |
| after_params = pipe.unet.parameters() | |
| if os.path.exists(text_encoder_sub_dir): | |
| pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder, text_encoder_sub_dir, adapter_name=adapter_name) | |
| if dtype in (torch.float16, torch.bfloat16): | |
| pipe.unet.half() | |
| pipe.text_encoder.half() | |
| return pipe | |
| def long_prompt_encoder(prompt, tokenizer, text_encoder, max_length=77): | |
| tokens = tokenizer(prompt, truncation=False, return_tensors="pt")["input_ids"] | |
| part_s = [tokens[:, i:i + max_length] for i in range(0, tokens.shape[1], max_length)] | |
| with torch.no_grad(): | |
| embeds = [text_encoder(part.to(text_encoder.device))[0] for part in part_s] | |
| return torch.cat(embeds, dim=1) | |
| def align_embeddings(prompt_embeds, negative_prompt_embeds): | |
| max_length = max(prompt_embeds.shape[1], negative_prompt_embeds.shape[1]) | |
| return torch.nn.functional.pad(prompt_embeds, (0, 0, 0, max_length - prompt_embeds.shape[1])), \ | |
| torch.nn.functional.pad(negative_prompt_embeds, (0, 0, 0, max_length - negative_prompt_embeds.shape[1])) | |
| def preprocess_image(image, target_width, target_height, resize_to_224=False): | |
| if isinstance(image, np.ndarray): | |
| image = Image.fromarray(image) | |
| # Если resize_to_224=True, изменяем размер до 224x224 | |
| if resize_to_224: | |
| image = image.resize((224, 224), Image.LANCZOS) | |
| else: | |
| image = image.resize((target_width, target_height), Image.LANCZOS) | |
| image = np.array(image).astype(np.float32) / 255.0 # Нормализация [0, 1] | |
| image = image[None].transpose(0, 3, 1, 2) # Преобразуем в (batch, channels, height, width) | |
| image = torch.from_numpy(image).to(device) | |
| return image | |
| def get_depth_map(image, depth_estimator): | |
| image = depth_estimator(image)["depth"] | |
| image = np.array(image) | |
| image = image[:, :, None] | |
| image = np.concatenate([image, image, image], axis=2) | |
| detected_map = torch.from_numpy(image).float() / 255.0 | |
| depth_map = detected_map.permute(2, 0, 1) | |
| return depth_map | |
| pipe_default = get_lora_sd_pipeline(lora_dir='lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device) | |
| # ---------------------------------------------------------------------------------------------------------------------------------------------------- | |
| def infer( | |
| prompt, | |
| negative_prompt, | |
| width=512, | |
| height=512, | |
| num_inference_steps=50, | |
| model='stable-diffusion-v1-5/stable-diffusion-v1-5', | |
| seed=4, | |
| guidance_scale=7.5, | |
| lora_scale=0.7, | |
| use_control_net=False, # Параметр для включения ControlNet | |
| control_mode=None, # Параметр для выбора режима ControlNet | |
| strength_cn=0.5, # Коэфф. зашумления ControlNet | |
| control_strength=0.5, # Сила влияния ControlNet | |
| cn_source_image=None, # Исходное изображение ControlNet | |
| control_image=None, # Контрольное изображение ControlNet | |
| use_ip_adapter=False, # Параметр для включения IP_adapter | |
| ip_adapter_mode=None, # Параметр для выбора режима IP_adapter | |
| strength_ip=0.5, # Коэфф. зашумления IP_adapter | |
| ip_adapter_strength=0.5,# Сила влияния IP_adapter | |
| ip_source_image=None, # Исходное изображение IP_adapter | |
| ip_adapter_image=None, # Контрольное изображение IP_adapter | |
| progress=gr.Progress(track_tqdm=True) | |
| ): | |
| print('ip_adapter_mode.value = ', ip_adapter_mode.value) | |
| print('control_mode.value = ', control_mode.value) | |
| # Генерация изображений с Ip_Adapter ------------------------------------------------------------------------------------------------------------------ | |
| if use_ip_adapter: #and ip_source_image is not None and ip_adapter_image is not None: | |
| # Режим pose_estimation --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "A man runs through the park against the background of trees. The man's entire figure, face, arms and legs are visible. Anime style. The best quality." | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 4 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_ip = 0.9 # Коэфф. зашумления IP_adapter | |
| # ip_adapter_strength = 0.2 # Сила влияния IP_adapter | |
| # controlnet_conditioning_scale = 0.99 # Сила влияния ControlNet | |
| # use_ip_adapter = True # Параметр для включения IP_adapter | |
| # ip_source_image = load_image("ControlNet_1.jpeg") # Исходное изображение IP_adapter | |
| # ip_adapter_image = load_image("Run.jpeg") # Контрольное изображение IP_adapter | |
| # #ip_adapter_mode = "pose_estimation" # Режим работы Ip_Adapter | |
| if ip_adapter_mode.value == "pose_estimation": | |
| print('ip_adapter_mode.value = ', ip_adapter_mode.value) | |
| # Инициализация ControlNet | |
| controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_ip_adapter = StableDiffusionControlNetPipeline.from_pretrained( | |
| model_default, | |
| controlnet=controlnet, | |
| torch_dtype=torch_dtype | |
| ).to(device) | |
| # Загрузка IP-Adapter | |
| pipe_ip_adapter.load_ip_adapter(IP_ADAPTER, subfolder="models", weight_name=WEIGHT_NAME_plus) | |
| pipe_ip_adapter.set_ip_adapter_scale(ip_adapter_strength) | |
| # Преобразование изображений для IP-Adapter (размер 224x224) | |
| ip_source_image = preprocess_image(ip_source_image, width, height, resize_to_224=True) | |
| ip_adapter_image = preprocess_image(ip_adapter_image, width, height, resize_to_224=True) | |
| # Создаём пайплайн IP_adapter с LoRA, если он ещё не создан | |
| if not hasattr(pipe_ip_adapter, 'lora_loaded') or not pipe_ip_adapter.lora_loaded: | |
| # Загружаем LoRA для UNet | |
| pipe_ip_adapter.unet = PeftModel.from_pretrained( | |
| pipe_ip_adapter.unet, | |
| 'lora_man_animestyle/unet', | |
| adapter_name="default" | |
| ) | |
| pipe_ip_adapter.unet.set_adapter("default") | |
| # Загружаем LoRA для Text Encoder, если она существует | |
| text_encoder_lora_path = 'lora_man_animestyle/text_encoder' | |
| if os.path.exists(text_encoder_lora_path): | |
| pipe_ip_adapter.text_encoder = PeftModel.from_pretrained( | |
| pipe_ip_adapter.text_encoder, | |
| text_encoder_lora_path, | |
| adapter_name="default" | |
| ) | |
| pipe_ip_adapter.text_encoder.set_adapter("default") | |
| # Объединяем LoRA с основной моделью | |
| pipe_ip_adapter.fuse_lora(lora_scale=lora_scale) | |
| pipe_ip_adapter.lora_loaded = True # Помечаем, что LoRA загружена | |
| # Убедимся, что ip_adapter_strength имеет тип float | |
| ip_adapter_strength = float(ip_adapter_strength) | |
| # Используем IP-Adapter с LoRA | |
| prompt_embeds = long_prompt_encoder(prompt, pipe_ip_adapter.tokenizer, pipe_ip_adapter.text_encoder) | |
| negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe_ip_adapter.tokenizer, pipe_ip_adapter.text_encoder) | |
| prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds) | |
| image = pipe_ip_adapter( | |
| prompt_embeds=prompt_embeds, | |
| negative_prompt_embeds=negative_prompt_embeds, | |
| image=ip_adapter_image, #ip_source_image, | |
| ip_adapter_image=ip_source_image, #ip_adapter_image, | |
| strength=strength_ip, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| width=width, | |
| height=height, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| controlnet_conditioning_scale=controlnet_conditioning_scale, | |
| generator=generator, | |
| ).images[0] | |
| else: | |
| # Режим edge_detection --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "The smiling man. His face and hands are visible. Anime style. The best quality." | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 9 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_ip = 0.5 #0.9 # Коэфф. зашумления IP_adapter | |
| # ip_adapter_strength = 0.15 #0.1 # Сила влияния IP_adapter | |
| # controlnet_conditioning_scale = 0.6 # Сила влияния ControlNet | |
| # use_ip_adapter = True # Параметр для включения IP_adapter | |
| # ip_source_image = load_image("005_6.jpeg") # Исходное изображение IP_adapter | |
| # ip_adapter_image = load_image("edges.jpeg") # Контрольное изображение IP_adapter | |
| # #ip_adapter_mode = "edge_detection" # Режим работы Ip_Adapter | |
| if ip_adapter_mode.value == "edge_detection": | |
| print('ip_adapter_mode.value = ', ip_adapter_mode.value) | |
| # Инициализация ControlNet | |
| controlnet_model_path = "lllyasviel/control_v11f1p_sd15_depth" | |
| controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_ip_adapter = StableDiffusionControlNetPipeline.from_pretrained( | |
| model_default, | |
| controlnet=controlnet, | |
| torch_dtype=torch_dtype | |
| ).to(device) | |
| # Загрузка IP-Adapter | |
| #pipe_ip_adapter.load_ip_adapter(IP_ADAPTER, subfolder="models", weight_name=WEIGHT_NAME_face) | |
| pipe_ip_adapter.load_ip_adapter(IP_ADAPTER, subfolder="models", weight_name=WEIGHT_NAME_plus) | |
| pipe_ip_adapter.set_ip_adapter_scale(ip_adapter_strength) | |
| # Преобразование изображений для IP-Adapter (размер 224x224) | |
| ip_source_image = preprocess_image(ip_source_image, width, height, resize_to_224=True) | |
| ip_adapter_image = preprocess_image(ip_adapter_image, width, height, resize_to_224=True) | |
| # Создаём пайплайн IP_adapter с LoRA, если он ещё не создан | |
| if not hasattr(pipe_ip_adapter, 'lora_loaded') or not pipe_ip_adapter.lora_loaded: | |
| # Загружаем LoRA для UNet | |
| pipe_ip_adapter.unet = PeftModel.from_pretrained( | |
| pipe_ip_adapter.unet, | |
| 'lora_man_animestyle/unet', | |
| adapter_name="default" | |
| ) | |
| pipe_ip_adapter.unet.set_adapter("default") | |
| # Загружаем LoRA для Text Encoder, если она существует | |
| text_encoder_lora_path = 'lora_man_animestyle/text_encoder' | |
| if os.path.exists(text_encoder_lora_path): | |
| pipe_ip_adapter.text_encoder = PeftModel.from_pretrained( | |
| pipe_ip_adapter.text_encoder, | |
| text_encoder_lora_path, | |
| adapter_name="default" | |
| ) | |
| pipe_ip_adapter.text_encoder.set_adapter("default") | |
| # Объединяем LoRA с основной моделью | |
| pipe_ip_adapter.fuse_lora(lora_scale=lora_scale) | |
| pipe_ip_adapter.lora_loaded = True # Помечаем, что LoRA загружена | |
| # Убедимся, что ip_adapter_strength имеет тип float | |
| ip_adapter_strength = float(ip_adapter_strength) | |
| # Используем IP-Adapter с LoRA | |
| prompt_embeds = long_prompt_encoder(prompt, pipe_ip_adapter.tokenizer, pipe_ip_adapter.text_encoder) | |
| negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe_ip_adapter.tokenizer, pipe_ip_adapter.text_encoder) | |
| prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds) | |
| # scale = { # по умолчанию в остальных блоках везде 0. | |
| # "down": { | |
| # "block_0": [0.0, 1.0], | |
| # "block_1": [0.0, 1.0], | |
| # }, | |
| # "up": { | |
| # "block_0": [0.0, 1.0, 0.0], | |
| # "block_1": [0.0, 1.0, 0.0], | |
| # }, | |
| # } | |
| # scale = { | |
| # "down": {"block_2": [0.0, 1.0]}, | |
| # "up": {"block_0": [0.0, 1.0, 0.0]}, | |
| # } | |
| # pipe_ip_adapter.set_ip_adapter_scale(scale) | |
| image = pipe_ip_adapter( | |
| prompt_embeds=prompt_embeds, | |
| negative_prompt_embeds=negative_prompt_embeds, | |
| image=ip_adapter_image, #ip_source_image, | |
| ip_adapter_image=ip_source_image, #ip_adapter_image, | |
| strength=strength_ip, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| width=width, | |
| height=height, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| controlnet_conditioning_scale=controlnet_conditioning_scale, | |
| generator=generator, | |
| ).images[0] | |
| else: | |
| # Режим depth_map --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "The smiling girl, best quality, high quality" | |
| # negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality" #"Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 6 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_ip = 0.9 # Коэфф. зашумления IP_adapter | |
| # ip_adapter_strength = 0.5 # Сила влияния IP_adapter | |
| # controlnet_conditioning_scale = 0.99 # Сила влияния ControlNet | |
| # use_ip_adapter = True # Параметр для включения IP_adapter | |
| # ip_adapter_image = load_image("032_3.jpeg") | |
| # depth_map = load_image("depth_map.jpeg") | |
| # #ip_adapter_mode = "depth_map" # Режим работы Ip_Adapter | |
| if ip_adapter_mode.value == "depth_map": | |
| print('ip_adapter_mode.value = ', ip_adapter_mode.value) | |
| # Инициализация ControlNet | |
| controlnet_model_path = "lllyasviel/control_v11f1p_sd15_depth" | |
| controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_ip_adapter = StableDiffusionControlNetPipeline.from_pretrained( | |
| model_default, | |
| controlnet=controlnet, | |
| torch_dtype=torch_dtype | |
| ).to(device) | |
| pipe_ip_adapter.load_ip_adapter(IP_ADAPTER, subfolder="models", weight_name=WEIGHT_NAME) | |
| pipe_ip_adapter.set_ip_adapter_scale(ip_adapter_strength) | |
| image = pipe_ip_adapter( | |
| prompt=prompt, | |
| negative_prompt=negative_prompt, | |
| image=depth_map, | |
| ip_adapter_image=ip_adapter_image, | |
| num_inference_steps=num_inference_steps, | |
| strength=strength_ip, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| guidance_scale=guidance_scale, | |
| controlnet_conditioning_scale=controlnet_conditioning_scale, | |
| generator=generator, | |
| ).images[0] | |
| else: | |
| # Генерация изображений с ControlNet ---------------------------------------------------------------------------------------------------------------- | |
| if use_control_net: #and control_image is not None and cn_source_image is not None: | |
| # Режим pose_estimation --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "A man runs through the park against the background of trees. The man's entire figure, face, arms and legs are visible. Anime style. The best quality." | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 444 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_cn = 0.9 # Коэфф. зашумления ControlNet | |
| # control_strength = 0.92 # Сила влияния ControlNet | |
| # use_control_net = True # Параметр для включения ControlNet | |
| # cn_source_image = load_image("ControlNet_1.jpeg") # Исходное изображение ControlNet | |
| # control_image = load_image("Run.jpeg") # Контрольное изображение ControlNet | |
| # #control_mode = "pose_estimation" # Режим работы ControlNet | |
| if control_mode.value == "pose_estimation": | |
| print('control_mode.value = ', control_mode.value) | |
| # Инициализация ControlNet | |
| controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_controlnet = StableDiffusionControlNetImg2ImgPipeline.from_pretrained( | |
| model_default, | |
| controlnet=controlnet, | |
| torch_dtype=torch_dtype | |
| ).to(device) | |
| # Преобразуем изображения | |
| cn_source_image = preprocess_image(cn_source_image, width, height) | |
| control_image = preprocess_image(control_image, width, height) | |
| # Создаём пайплайн ControlNet с LoRA, если он ещё не создан | |
| if not hasattr(pipe_controlnet, 'lora_loaded') or not pipe_controlnet.lora_loaded: | |
| # Загружаем LoRA для UNet | |
| pipe_controlnet.unet = PeftModel.from_pretrained( | |
| pipe_controlnet.unet, | |
| 'lora_man_animestyle/unet', | |
| adapter_name="default" | |
| ) | |
| pipe_controlnet.unet.set_adapter("default") | |
| # Загружаем LoRA для Text Encoder, если она существует | |
| text_encoder_lora_path = 'lora_man_animestyle/text_encoder' | |
| if os.path.exists(text_encoder_lora_path): | |
| pipe_controlnet.text_encoder = PeftModel.from_pretrained( | |
| pipe_controlnet.text_encoder, | |
| text_encoder_lora_path, | |
| adapter_name="default" | |
| ) | |
| pipe_controlnet.text_encoder.set_adapter("default") | |
| # Объединяем LoRA с основной моделью | |
| pipe_controlnet.fuse_lora(lora_scale=lora_scale) | |
| pipe_controlnet.lora_loaded = True # Помечаем, что LoRA загружена | |
| # Убедимся, что control_strength имеет тип float | |
| control_strength = float(control_strength) | |
| #strength_sn = float(strength_sn) | |
| # Используем ControlNet с LoRA | |
| prompt_embeds = long_prompt_encoder(prompt, pipe_controlnet.tokenizer, pipe_controlnet.text_encoder) | |
| negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe_controlnet.tokenizer, pipe_controlnet.text_encoder) | |
| prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds) | |
| image = pipe_controlnet( | |
| prompt_embeds=prompt_embeds, | |
| negative_prompt_embeds=negative_prompt_embeds, | |
| image=cn_source_image, | |
| control_image=control_image, | |
| strength=strength_cn, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| width=width, | |
| height=height, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| controlnet_conditioning_scale=control_strength, | |
| generator=generator | |
| ).images[0] | |
| else: | |
| # Режим edge_detection --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "The smiling girl. Anime style. Best quality, high quality" # "the mona lisa" | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 8 # 1 8 12 14 18 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_cn = 0.2 # Коэфф. зашумления ControlNet | |
| # control_strength = 0.8 # Сила влияния ControlNet | |
| # use_control_net = True # Параметр для включения ControlNet | |
| # cn_source_image = load_image("edges_w.jpeg") # Исходное изображение ControlNet | |
| # control_image = load_image("027_0_1.jpeg") # Контрольное изображение ControlNet | |
| # #control_mode = "edge_detection" # Режим работы ControlNet | |
| if control_mode.value == "edge_detection": | |
| print('control_mode.value = ', control_mode.value) | |
| controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16, use_safetensors=True) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_controlnet = StableDiffusionControlNetPipeline.from_pretrained( | |
| "stable-diffusion-v1-5/stable-diffusion-v1-5", | |
| controlnet=controlnet, | |
| torch_dtype=torch.float16, | |
| use_safetensors=True | |
| ).to(device) | |
| pipe_controlnet.scheduler = UniPCMultistepScheduler.from_config(pipe_controlnet.scheduler.config) | |
| image = pipe_controlnet( | |
| prompt=prompt, | |
| negative_prompt=negative_prompt, | |
| image=cn_source_image, | |
| control_image=control_image, | |
| strength=strength_cn, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| width=width, | |
| height=height, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| controlnet_conditioning_scale=control_strength, | |
| generator=generator | |
| ).images[0] | |
| else: | |
| # Режим depth_map --------------------------------------------------------------------------------------------------------------------------- | |
| # prompt = "lego batman and robin" #"Lego Harry Potter and Jean Granger" #"Harry Potter and Hagrid in the lego style" #"lego batman and robin" | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 8 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 50 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # strength_cn = 1.0 # Коэфф. зашумления ControlNet | |
| # control_strength = 0.0 # Сила влияния ControlNet | |
| # use_control_net = True # Параметр для включения ControlNet | |
| # cn_source_image = load_image("edges_w.jpeg") # Исходное изображение ControlNet | |
| # control_image = load_image("014_3.jpeg") # Контрольное изображение ControlNet | |
| # #control_mode = "depth_map" # Режим работы ControlNet | |
| if control_mode.value == "depth_map": | |
| print('control_mode.value = ', control_mode.value) | |
| depth_estimator = pipeline("depth-estimation") | |
| depth_map = get_depth_map(control_image, depth_estimator).unsqueeze(0).half().to(device) | |
| controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, use_safetensors=True) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| pipe_controlnet = StableDiffusionControlNetImg2ImgPipeline.from_pretrained( | |
| "stable-diffusion-v1-5/stable-diffusion-v1-5", | |
| controlnet=controlnet, | |
| torch_dtype=torch.float16, | |
| use_safetensors=True | |
| ).to(device) | |
| pipe_controlnet.scheduler = UniPCMultistepScheduler.from_config(pipe_controlnet.scheduler.config) | |
| image = pipe_controlnet( | |
| prompt=prompt, | |
| negative_prompt=negative_prompt, | |
| image=control_image, | |
| control_image=depth_map, | |
| #strength=strength_cn, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного | |
| width=width, | |
| height=height, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| #controlnet_conditioning_scale=control_strength, | |
| generator=generator | |
| ).images[0] | |
| else: | |
| # Генерация изображений с LORA без ControlNet и IP_Adapter --------------------------------------------------------------------------------------------- | |
| # prompt = "A young man in anime style. The image is characterized by high definition and resolution. Handsome, thoughtful man, attentive eyes. The man is depicted in the foreground, close-up or in the middle. High-quality images of the face, eyes, nose, lips, hands and clothes. The background and background are blurred and indistinct. The play of light and shadow is visible on the face and clothes." | |
| # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image." | |
| # seed = 5 | |
| # width = 512 | |
| # height = 512 | |
| # num_inference_steps = 30 | |
| # guidance_scale = 7.5 | |
| # lora_scale = 0.7 | |
| # Инициализация ControlNet | |
| controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype) | |
| generator = torch.Generator(device).manual_seed(seed) | |
| if model != model_default: | |
| pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device) | |
| prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder) | |
| negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder) | |
| prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds) | |
| else: | |
| pipe = pipe_default | |
| prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder) | |
| negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder) | |
| prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds) | |
| pipe.fuse_lora(lora_scale=lora_scale) | |
| params = { | |
| 'prompt_embeds': prompt_embeds, | |
| 'negative_prompt_embeds': negative_prompt_embeds, | |
| 'guidance_scale': guidance_scale, | |
| 'num_inference_steps': num_inference_steps, | |
| 'width': width, | |
| 'height': height, | |
| 'generator': generator, | |
| } | |
| image = pipe(**params).images[0] | |
| return image | |
| # --------------------------------------------------------------------------------------------------------------------------------------------- | |
| examples = [ | |
| "A young man in anime style. The image is characterized by high definition and resolution. Handsome, thoughtful man, attentive eyes. The man is depicted in the foreground, close-up or in the middle. High-quality images of the face, eyes, nose, lips, hands and clothes. The background and background are blurred and indistinct. The play of light and shadow is visible on the face and clothes.", | |
| "A man runs through the park against the background of trees. The man's entire figure, face, arms and legs are visible. Anime style. The best quality.", | |
| "The smiling man. His face and hands are visible. Anime style. The best quality.", | |
| "The smiling girl. Anime style. Best quality, high quality.", | |
| "lego batman and robin", | |
| ] | |
| examples_negative = [ | |
| "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image.", | |
| "Monochrome, lowres, bad anatomy, worst quality, low quality", | |
| ] | |
| css = """ | |
| #col-container { | |
| margin: 0 auto; | |
| max-width: 640px; | |
| } | |
| """ | |
| available_models = [ | |
| "stable-diffusion-v1-5/stable-diffusion-v1-5", | |
| "CompVis/stable-diffusion-v1-4", | |
| ] | |
| # ------------------------------------------------------------------------------------------------------------------------------------------------- | |
| with gr.Blocks(css=css) as demo: | |
| with gr.Column(elem_id="col-container"): | |
| gr.Markdown(" # Text-to-Image Gradio Template from V. Gorsky") | |
| with gr.Row(): | |
| model = gr.Dropdown( | |
| label="Model Selection", | |
| choices=available_models, | |
| value="stable-diffusion-v1-5/stable-diffusion-v1-5", | |
| interactive=True | |
| ) | |
| prompt = gr.Textbox( | |
| label="Prompt", | |
| max_lines=1, | |
| placeholder="Enter your prompt", | |
| ) | |
| negative_prompt = gr.Textbox( | |
| label="Negative prompt", | |
| max_lines=1, | |
| placeholder="Enter a negative prompt", | |
| ) | |
| with gr.Row(): | |
| lora_scale = gr.Slider( | |
| label="LoRA scale", | |
| minimum=0.0, | |
| maximum=1.0, | |
| step=0.01, | |
| value=0.7, | |
| ) | |
| with gr.Row(): | |
| guidance_scale = gr.Slider( | |
| label="Guidance scale", | |
| minimum=0.0, | |
| maximum=10.0, | |
| step=0.01, | |
| value=7.5, | |
| ) | |
| with gr.Row(): | |
| seed = gr.Slider( | |
| label="Seed", | |
| minimum=0, | |
| maximum=MAX_SEED, | |
| step=1, | |
| value=4, | |
| ) | |
| with gr.Row(): | |
| num_inference_steps = gr.Slider( | |
| label="Number of inference steps", | |
| minimum=1, | |
| maximum=100, | |
| step=1, | |
| value=50, | |
| ) | |
| with gr.Accordion("Advanced Settings", open=False): | |
| with gr.Row(): | |
| width = gr.Slider( | |
| label="Width", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=512, | |
| ) | |
| with gr.Row(): | |
| height = gr.Slider( | |
| label="Height", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=512, | |
| ) | |
| # ControlNet ----------------------------------------------------------------------------------------------- | |
| with gr.Blocks(): | |
| with gr.Row(): | |
| use_control_net = gr.Checkbox( | |
| label="Use ControlNet", | |
| value=False, | |
| ) | |
| with gr.Column(visible=False) as control_net_options: | |
| strength_cn = gr.Slider( | |
| label="Strength", | |
| minimum=0.0, | |
| maximum=1.0, | |
| value=0.5, | |
| step=0.01, | |
| ) | |
| control_strength = gr.Slider( | |
| label="Control Strength", | |
| minimum=0.0, | |
| maximum=1.0, | |
| value=0.5, | |
| step=0.01, | |
| ) | |
| control_mode = gr.Dropdown( | |
| label="Control Mode", | |
| choices=[ | |
| "pose_estimation", | |
| "edge_detection", | |
| "depth_map", | |
| ], | |
| value="pose_estimation", | |
| interactive=True, | |
| ) | |
| cn_source_image = gr.Image(label="Upload Source Image") | |
| control_image = gr.Image(label="Upload Control Net Image") | |
| use_control_net.change( | |
| fn=lambda x: gr.Row.update(visible=x), | |
| inputs=use_control_net, | |
| outputs=control_net_options | |
| ) | |
| # IP_Adapter ------------------------------------------------------------------------------------------------ | |
| with gr.Blocks(): | |
| with gr.Row(): | |
| use_ip_adapter = gr.Checkbox( | |
| label="Use IP_Adapter", | |
| value=False, | |
| ) | |
| with gr.Column(visible=False) as ip_adapter_options: | |
| strength_ip = gr.Slider( | |
| label="Strength", | |
| minimum=0.0, | |
| maximum=1.0, | |
| value=0.5, | |
| step=0.01, | |
| ) | |
| ip_adapter_strength = gr.Slider( | |
| label="IP_Adapter Strength", | |
| minimum=0.0, | |
| maximum=1.0, | |
| value=0.5, | |
| step=0.01, | |
| ) | |
| ip_adapter_mode = gr.Dropdown( | |
| label="Ip_Adapter Mode", | |
| choices=[ | |
| "pose_estimation", | |
| "edge_detection", | |
| "depth_map", | |
| ], | |
| value="pose_estimation", | |
| interactive=True, | |
| ) | |
| ip_source_image = gr.Image(label="Upload Source Image") | |
| ip_adapter_image = gr.Image(label="Upload IP_Adapter Image") | |
| use_ip_adapter.change( | |
| fn=lambda x: gr.Row.update(visible=x), | |
| inputs=use_ip_adapter, | |
| outputs=ip_adapter_options | |
| ) | |
| # --------------------------------------------------------------------------------------------------------- | |
| gr.Examples(examples=examples, inputs=[prompt], label="Examples for prompt:") | |
| gr.Examples(examples=examples_negative, inputs=[negative_prompt], label="Examples for negative prompt:") | |
| run_button = gr.Button("Run", scale=1, variant="primary") | |
| result = gr.Image(label="Result", show_label=False) | |
| gr.on( | |
| triggers=[run_button.click, prompt.submit], | |
| fn=infer, | |
| inputs=[ | |
| prompt, | |
| negative_prompt, | |
| width, | |
| height, | |
| num_inference_steps, | |
| model, | |
| seed, | |
| guidance_scale, | |
| lora_scale, | |
| use_control_net, # Параметр для включения ControlNet | |
| control_mode, # Параметр для выбора режима ControlNet | |
| strength_cn, # Коэфф. зашумления ControlNet | |
| control_strength, # Сила влияния ControlNet | |
| cn_source_image, # Исходное изображение ControlNet | |
| control_image, # Контрольное изображение ControlNet | |
| use_ip_adapter, # Параметр для включения IP_adapter | |
| ip_adapter_mode, # Параметр для выбора режима IP_adapter | |
| strength_ip, # Коэфф. зашумления IP_adapter | |
| ip_adapter_strength,# Сила влияния IP_adapter | |
| ip_source_image, # Исходное изображение IP_adapter | |
| ip_adapter_image, # Контрольное изображение IP_adapter | |
| ], | |
| outputs=[result], | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |