o Gi@s,dZdZdZdZdZdZdZdZdZdZ d S) a Prompt templates for QwenImage pipelines. This module centralizes all prompt templates used across different QwenImage pipeline variants: - QwenImage (base): Text-only encoding for text-to-image generation - QwenImage Edit: VL encoding with single image for image editing - QwenImage Edit Plus: VL encoding with multiple images for multi-reference editing - QwenImage Layered: Auto-captioning for image decomposition z<|im_start|>system Describe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|> <|im_start|>user {}<|im_end|> <|im_start|>assistant "a<|im_start|>system Describe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|> <|im_start|>user <|vision_start|><|image_pad|><|vision_end|>{}<|im_end|> <|im_start|>assistant @a<|im_start|>system Describe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|> <|im_start|>user {}<|im_end|> <|im_start|>assistant z7Picture {}: <|vision_start|><|image_pad|><|vision_end|>a^<|im_start|>system You are a helpful assistant.<|im_end|> <|im_start|>user # Image Annotator You are a professional image annotator. Please write an image caption based on the input image: 1. Write the caption using natural, descriptive language without structured formats or rich text. 2. Enrich caption details by including: - Object attributes, such as quantity, color, shape, size, material, state, position, actions, and so on - Vision Relations between objects, such as spatial relations, functional relations, possessive relations, attachment relations, action relations, comparative relations, causal relations, and so on - Environmental details, such as weather, lighting, colors, textures, atmosphere, and so on - Identify the text clearly visible in the image, without translation or explanation, and highlight it in the caption with quotation marks 3. Maintain authenticity and accuracy: - Avoid generalizations - Describe all visible information in the image, while do not add information not explicitly shown in the image <|vision_start|><|image_pad|><|vision_end|><|im_end|> <|im_start|>assistant u<|im_start|>system You are a helpful assistant.<|im_end|> <|im_start|>user # 图像标注器 你是一个专业的图像标注器。请基于输入图像，撰写图注: 1. 使用自然、描述性的语言撰写图注，不要使用结构化形式或富文本形式。 2. 通过加入以下内容，丰富图注细节： - 对象的属性：如数量、颜色、形状、大小、位置、材质、状态、动作等 - 对象间的视觉关系：如空间关系、功能关系、动作关系、从属关系、比较关系、因果关系等 - 环境细节：例如天气、光照、颜色、纹理、气氛等 - 文字内容：识别图像中清晰可见的文字，不做翻译和解释，用引号在图注中强调 3. 保持真实性与准确性： - 不要使用笼统的描述 - 描述图像中所有可见的信息，但不要加入没有在图像中出现的内容 <|vision_start|><|image_pad|><|vision_end|><|im_end|> <|im_start|>assistant N) __doc__QWENIMAGE_PROMPT_TEMPLATE#QWENIMAGE_PROMPT_TEMPLATE_START_IDXQWENIMAGE_EDIT_PROMPT_TEMPLATE(QWENIMAGE_EDIT_PROMPT_TEMPLATE_START_IDX#QWENIMAGE_EDIT_PLUS_PROMPT_TEMPLATE QWENIMAGE_EDIT_PLUS_IMG_TEMPLATE-QWENIMAGE_EDIT_PLUS_PROMPT_TEMPLATE_START_IDX#QWENIMAGE_LAYERED_CAPTION_PROMPT_EN#QWENIMAGE_LAYERED_CAPTION_PROMPT_CNr r j/home/ubuntu/.local/lib/python3.10/site-packages/diffusers/modular_pipelines/qwenimage/prompt_templates.pys