DALL·E Mini generates images from text prompts through an open-source project.
Open source
24 alternativesbytedance/Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
About bytedance/Dolphin
Dolphin is a document image parsing model that converts document images and PDFs into structured output. It uses a two-stage approach: first classifying documents as digital or photographed and performing layout analysis with reading order prediction, then using holistic parsing for photographed documents and parallel element-wise parsing for digital documents.
It provides page-level parsing to JSON and Markdown and element-level parsing for text, tables, formulas, and code. Use requires cloning the repository, installing Python dependencies, and downloading the Dolphin-v2 model weights from Hugging Face. It includes demo scripts for page, element, and layout parsing, multi-page PDF input, and vLLM and TensorRT-LLM inference options.
Key features
- Parses full document pages into structured JSON and Markdown
- Parses individual text, table, formula, and code elements
- Classifies digital versus photographed documents before parsing
- Performs layout analysis with reading order prediction
- Processes single images, single PDFs, and directories including multi-page PDFs
- Supports accelerated inference with vLLM and TensorRT-LLM
Best for: Developers and researchers converting document images and PDFs into structured JSON and Markdown.
Good for
- Handles both digital-born and photographed documents
- Offers page-level and element-level parsing granularities
- Includes multi-page PDF handling and accelerated inference options
bytedance/Dolphin at a glance
- Website
- github.com/bytedance/Dolphin
- Category
- AI & Machine Learning › AI Image Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
bytedance/Dolphin alternatives
Tools and sites you could use instead, ranked by how closely they match.
A custom AUTOMATIC1111 script adds a small template language for generating random Stable Diffusion prompts.
Open source
24 alternatives
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold.
SD.Next is a web interface for AI image and video generation, captioning, and processing.
Open source
24 alternatives
PyTorch Implementation of No Token Left Behind: Explainability-Aided Image Classification and Generation.
Deep-Live-Cam performs real-time face swaps and creates video deepfakes from a single image, according to its repository description.
Open source
24 alternativesPopular in AI Image Generators
Well-known listings from the same topic.
FigureLabsfigurelabs.aiImagePromptGuruimagepromptguru.netAI SVGaisvg.artCGDreamcgdream.aiFlux.1 AIflux1.aiPixraypixray.com
bytedance/Dolphin FAQ
What is needed to run Dolphin?
Clone the repository, run pip install -r requirements.txt, and download the Dolphin-v2 weights from Hugging Face to ./hf_model.
What inputs can page-level parsing accept?
A single document image, a single PDF file, or all documents in a directory, with results saved as JSON and Markdown.
What is element-level parsing?
Parsing of individual element images by specifying element_type as table, formula, text, or code.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.