TB-OCR-preview-0.1
Maintainer: yifeihu
115
🎲
| Property | Value |
|---|---|
| Run this model | Run on HuggingFace |
| API spec | View on HuggingFace |
| Github link | No Github link provided |
| Paper link | No paper link provided |
Create account to get full access
Model overview
TB-OCR-preview-0.1 is an end-to-end optical character recognition (OCR) model developed by Yifei Hu that can handle text, math LaTeX, and Markdown formats simultaneously. It takes a block of text as input and returns clean Markdown output, with headers marked by ## and math expressions wrapped in brackets \( inline math \) \[ display math \] for easy parsing. This model does not require separate line detection or math formula detection.
Model inputs and outputs
Inputs
- A block of text containing a mix of regular text, math LaTeX, and Markdown formatting.
Outputs
- Clean Markdown output with headers, math expressions, and other formatting properly identified.
Capabilities
TB-OCR-preview-0.1 can accurately extract and format text, math, and Markdown elements from a given block of text. This is particularly useful for tasks like digitizing scientific papers, notes, or other documents that contain a mix of these elements.
What can I use it for?
TB-OCR-preview-0.1 is well-suited for use cases where you need to convert scanned or photographed text, math, and Markdown content into a more structured, machine-readable format. This could include tasks like automating the digitization of research papers, lecture notes, or other technical documents.
Things to try
Consider combining TB-OCR-preview-0.1 with the TFT-ID-1.0 model, which specializes in text, table, and figure detection for full-page OCR. This can be more efficient than using TB-OCR-preview-0.1 on entire pages, as it allows you to split the text into smaller blocks and process them in parallel.
This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!
Related Models
🎲
TB-OCR-preview-0.1
115
TB-OCR-preview-0.1 is an end-to-end optical character recognition (OCR) model developed by Yifei Hu that can handle text, math LaTeX, and Markdown formats simultaneously. It takes a block of text as input and returns clean Markdown output, with headers marked by ## and math expressions wrapped in brackets \( inline math \) \[ display math \] for easy parsing. This model does not require separate line detection or math formula detection. Model inputs and outputs Inputs A block of text containing a mix of regular text, math LaTeX, and Markdown formatting. Outputs Clean Markdown output with headers, math expressions, and other formatting properly identified. Capabilities TB-OCR-preview-0.1 can accurately extract and format text, math, and Markdown elements from a given block of text. This is particularly useful for tasks like digitizing scientific papers, notes, or other documents that contain a mix of these elements. What can I use it for? TB-OCR-preview-0.1 is well-suited for use cases where you need to convert scanned or photographed text, math, and Markdown content into a more structured, machine-readable format. This could include tasks like automating the digitization of research papers, lecture notes, or other technical documents. Things to try Consider combining TB-OCR-preview-0.1 with the TFT-ID-1.0 model, which specializes in text, table, and figure detection for full-page OCR. This can be more efficient than using TB-OCR-preview-0.1 on entire pages, as it allows you to split the text into smaller blocks and process them in parallel.
Updated Invalid Date
sdxl-lightning-4step
412.2K
sdxl-lightning-4step is a fast text-to-image model developed by ByteDance that can generate high-quality images in just 4 steps. It is similar to other fast diffusion models like AnimateDiff-Lightning and Instant-ID MultiControlNet, which also aim to speed up the image generation process. Unlike the original Stable Diffusion model, these fast models sacrifice some flexibility and control to achieve faster generation times. Model inputs and outputs The sdxl-lightning-4step model takes in a text prompt and various parameters to control the output image, such as the width, height, number of images, and guidance scale. The model can output up to 4 images at a time, with a recommended image size of 1024x1024 or 1280x1280 pixels. Inputs Prompt**: The text prompt describing the desired image Negative prompt**: A prompt that describes what the model should not generate Width**: The width of the output image Height**: The height of the output image Num outputs**: The number of images to generate (up to 4) Scheduler**: The algorithm used to sample the latent space Guidance scale**: The scale for classifier-free guidance, which controls the trade-off between fidelity to the prompt and sample diversity Num inference steps**: The number of denoising steps, with 4 recommended for best results Seed**: A random seed to control the output image Outputs Image(s)**: One or more images generated based on the input prompt and parameters Capabilities The sdxl-lightning-4step model is capable of generating a wide variety of images based on text prompts, from realistic scenes to imaginative and creative compositions. The model's 4-step generation process allows it to produce high-quality results quickly, making it suitable for applications that require fast image generation. What can I use it for? The sdxl-lightning-4step model could be useful for applications that need to generate images in real-time, such as video game asset generation, interactive storytelling, or augmented reality experiences. Businesses could also use the model to quickly generate product visualization, marketing imagery, or custom artwork based on client prompts. Creatives may find the model helpful for ideation, concept development, or rapid prototyping. Things to try One interesting thing to try with the sdxl-lightning-4step model is to experiment with the guidance scale parameter. By adjusting the guidance scale, you can control the balance between fidelity to the prompt and diversity of the output. Lower guidance scales may result in more unexpected and imaginative images, while higher scales will produce outputs that are closer to the specified prompt.
Updated Invalid Date
🧪
TFT-ID-1.0
85
The TFT-ID (Table/Figure/Text IDentifier) model is an object detection model fine-tuned to extract tables, figures, and text sections from academic papers. Developed by Yifei Hu, the model is based on the microsoft/Florence-2 checkpoints and was trained on over 36,000 manually annotated bounding boxes from the Hugging Face Daily Papers dataset. The model takes an image of a single paper page as input and returns bounding boxes for all tables, figures, and text sections present, along with the corresponding labels. This makes it a useful tool for academic document processing workflows, as the extracted text sections can be easily fed into downstream OCR systems. Model Inputs and Outputs Inputs Paper page image**: The model takes an image of a single page from an academic paper as input. Outputs Object detection results**: The model outputs a dictionary containing the bounding boxes and labels for all detected tables, figures, and text sections in the input image. The format is: {'': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]}} Capabilities The TFT-ID model is highly accurate, achieving a 96.78% success rate on a test set of 373 paper pages. It is particularly effective at identifying tables and figures, reaching a 98.84% success rate on a subset of 258 images. The model's ability to extract clean text content from the identified text sections makes it a valuable tool for academic document processing pipelines. However, it is important to note that the TFT-ID model is not an OCR system itself, and the extracted text may still require further processing. What Can I Use It For? The TFT-ID model is well-suited for automating the extraction of tables, figures, and text sections from academic papers. This can be particularly useful for researchers, publishers, and academic institutions looking to streamline their document processing workflows. Some potential use cases include: Academic document processing**: Integrating the TFT-ID model into a document processing pipeline to automatically identify and extract relevant content from academic papers. Literature review automation**: Using the model to rapidly locate and extract tables, figures, and key text sections from a large corpus of academic literature, facilitating more efficient literature reviews. Dataset curation**: Employing the TFT-ID model to generate structured datasets of tables, figures, and text from academic papers, which can then be used to train other AI models. Things to Try One interesting aspect of the TFT-ID model is its ability to handle a variety of table and figure formats, including both bordered and borderless elements. This robustness can be further explored by testing the model on academic papers with diverse layouts and visual styles. Additionally, the model's integration with downstream OCR workflows presents opportunities for experimentation. Users could, for example, evaluate the quality and accuracy of the extracted text sections, and explore ways to optimize the overall document processing pipeline. Finally, the TFT-ID model's exceptional performance on table and figure detection tasks suggests that it could be a valuable component in more complex academic document understanding systems, such as those focused on automated summarization or knowledge extraction.
Updated Invalid Date
🔮
GOT-OCR2_0
260
The GOT-OCR2_0 model, developed by stepfun-ai, is a powerful and versatile optical character recognition (OCR) system that can handle a wide range of text formats, including plain text, formatted text, and even fine-grained OCR with bounding boxes and color information. This model is an upgrade to the previous GOT-OCR model, addressing key issues and enhancing its capabilities. The GOT-OCR2_0 model is built upon the Hugging Face Transformers library and can be used with NVIDIA GPUs for efficient inference. It is capable of performing various OCR-related tasks, from extracting plain text from images to generating formatted output with layout and styling information. The model's flexibility allows users to customize the level of detail in the OCR results, making it suitable for a variety of applications. Similar models such as the GOT-OCR2_0 and kivotos-xl-2.0 have also been developed for image-to-text conversion and text understanding tasks, each with its own unique capabilities and use cases. Model inputs and outputs Inputs Image file:** The GOT-OCR2_0 model takes an image file as input, which can be in various formats such as JPEG, PNG, or BMP. Outputs Plain text OCR:** The model can extract plain text from the input image and return the recognized text. Formatted text OCR:** The model can generate formatted text output, including information about the layout and styling of the text, such as bounding boxes, line breaks, and font colors. Fine-grained OCR:** The model can provide detailed information about the text, including bounding boxes and color information, enabling more advanced text processing and layout analysis. Multi-crop OCR:** The model can handle multiple cropped regions in the input image and generate OCR results for each of them. Capabilities The GOT-OCR2_0 model excels at accurately extracting text from a wide range of image types, including scanned documents, screenshots, and photographs. It can handle both simple and complex layouts, and its ability to recognize formatted text and fine-grained details sets it apart from traditional OCR solutions. One of the key capabilities of this model is its versatility. It can be used for a variety of applications, such as converting physical documents into editable digital formats, automating data entry processes, and enhancing document management systems. The model's flexibility also makes it suitable for use in industries like publishing, legal, and financial services, where accurate text extraction and layout preservation are crucial. What can I use it for? The GOT-OCR2_0 model can be a valuable tool for a wide range of applications that involve text extraction and processing from images. Some potential use cases include: Document digitization:** Converting physical documents, such as forms, contracts, or books, into searchable and editable digital formats. Workflow automation:** Streamlining data entry processes by automating the extraction of relevant information from documents. Content management:** Enhancing document management systems by enabling the extraction and preservation of text layout and formatting. Research and analysis:** Extracting text from images for further processing, such as natural language processing or data analysis. Things to try One interesting aspect of the GOT-OCR2_0 model is its ability to handle fine-grained OCR, which includes the extraction of bounding boxes and color information. This feature can be particularly useful for applications that require precise layout and formatting preservation, such as in the publishing or legal industries. Another interesting aspect is the model's multi-crop OCR capability, which allows it to handle multiple text-containing regions within a single image. This can be beneficial for processing complex documents or images with multiple text elements, such as forms or technical diagrams. To explore the full capabilities of the GOT-OCR2_0 model, you can try experimenting with different input images, testing the various OCR types (plain text, formatted text, fine-grained, and multi-crop), and evaluating the quality and accuracy of the results. The model's versatility and customization options make it a powerful tool for a wide range of text extraction and processing tasks.
Updated Invalid Date