Add sdxl_prompt2prompt_mapper

configs/config_all.yaml

@@ -179,6 +179,12 @@ process:
       lang: en                                                # sample in which language
       tokenization: false                                     # whether to use model to tokenize documents
       substrings: ['http', 'www', '.com', 'href', '//']       # incorrect substrings to remove
+  - sdxl_prompt2prompt_mapper:                              # use the generative model SDXL and image editing technique Prompt-to-Prompt to generate pairs of similar images.
+      hf_diffusion: 'stabilityai/stable-diffusion-xl-base-1.0' # model name of the SDXL model on huggingface
+      num_inference_steps: 50                                 # the larger the value, the better the image generation quality
+      guidance_scale: 7.5                                     # a higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality
+      text_key_second: None                                   # used to store the first caption in the caption pair
+      text_key_third: None                                    # used to store the second caption in the caption pair
   - sentence_split_mapper:                                  # split text to multiple sentences and join them with '\n'
       lang: 'en'                                              # split text in what language
   - video_captioning_from_audio_mapper:                     # caption a video according to its audio streams based on Qwen-Audio model

data_juicer/ops/mapper/__init__.py

@@ -13,8 +13,8 @@
                remove_repeat_sentences_mapper, remove_specific_chars_mapper,
                remove_table_text_mapper,
                remove_words_with_incorrect_substrings_mapper,
-               replace_content_mapper, sentence_split_mapper,
-               video_captioning_from_audio_mapper,
+               replace_content_mapper, sdxl_prompt2prompt_mapper,
+               sentence_split_mapper, video_captioning_from_audio_mapper,
                video_captioning_from_frames_mapper,
                video_captioning_from_summarizer_mapper,
                video_captioning_from_video_mapper, video_face_blur_mapper,
@@ -57,6 +57,7 @@
 from .remove_words_with_incorrect_substrings_mapper import \
     RemoveWordsWithIncorrectSubstringsMapper
 from .replace_content_mapper import ReplaceContentMapper
+from .sdxl_prompt2prompt_mapper import SDXLPrompt2PromptMapper
 from .sentence_split_mapper import SentenceSplitMapper
 from .video_captioning_from_audio_mapper import VideoCaptioningFromAudioMapper
 from .video_captioning_from_frames_mapper import \
@@ -123,6 +124,7 @@
     'AudioFFmpegWrappedMapper',
     'VideoSplitByDurationMapper',
     'VideoFaceBlurMapper',
+    'SDXLPrompt2PromptMapper'
 ]
 
 # yapf: enable