Projects

Overview: The Grok Imagine Image API is a powerful tool for generating and editing images using text prompts. It offers flexible pricing, a user-friendly interface, and supports a wide range of models and parameters. Key features: - Supports multiple image resolutions and sizes - Offers a per-image pricing model starting at $0.016 per image - Integrates with OpenAI-compatible endpoints for seamless integration - Provides detailed parameters for fine-tuning and editing images Tech stack: Python Why it matters: This API simplifies the process of generating high-quality images with natural language prompts, making it ideal for creative projects, design, and content creation. Repository: dgihsnwb08756/grok-image-api-ko Primary language: Python GitHub stars: 13 GitHub description: 그록 이매진 — Grok Imagine Image API (`grok-imagine-image`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Overview: This project provides an OpenAI-compatible API endpoint for accessing Imagen 4.0, a cutting-edge image generation model. It includes detailed pricing, model parameters, and a comprehensive API documentation. Key features: - Access to Imagen 4.0 via an OpenAI-compatible API endpoint. - Pricing: $0.04 per image, with no subscription required. - Model parameters: `model`, `prompt`, `size`, `resolution`, `n`, `image_urls`, and `nsfw_check`. - Quickstart guide for developers. Tech stack: Python. Why it matters: This project simplifies the process of integrating cutting-edge AI image generation capabilities into applications, making it accessible to developers without the need for complex billing or subscription models. Repository: dkt4c5gv9mr/imagen-4-api-ko Primary language: Python GitHub stars: 10 GitHub description: 이마젠 — Imagen 4.0 API (`imagen-4.0-apimart`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

### Overview: Imagen 4.0 Prompts: 8 Tested Recipes With Outputs ### Key features: - **Model:** `imagen-4.0-apimart` - **Recipes:** 8 (machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.04 per image — estimated cost of the whole set: $0.32 ### Tech stack: Python ### Why it matters: - **Key One:** A single API key allows access to Imagen 4.0 (`imagen-4.0-apimart`) and image/video/300+ language models with a base URL and `Authorization` header. - **Key Two:** No subscription required, $1 minimum, and charges are based on actual usage. - **Key Three:** All responses are accompanied by a cost (`cost` / `credits_cost`), and failed requests are refunded. - **Key Four:** The prompt structure is designed to be easily copied and adapted, with three rules to follow: name the material, set the light, and pin the framing. ### Other names: - Imagen 4.0 Prompts ### Eight Imagen 4.0 Prompts with Outputs: - **Product / e-commerce:** - Example Render: A frosted glass perfume bottle on a wet black stone slab, single softbox from the left, faint mist, deep charcoal background, crisp label text, commercial product photography. - Cost: $0.04

Overview: Qwen-Image 3.0 API provides text-to-image generation and editing capabilities with a single key for all models, including Qwen-Image 3.0, at a cost of $0.0205712 per image. It supports 1K and 2K resolutions and is compatible with OpenAI's API endpoint. Key features: - Supports Qwen-Image 3.0 (`qwen-image-3.0`) and 300+ other models - Per-image pricing: $0.0205712 for 1K images, $0.0205712 for 2K images - Asynchronous execution, task ID polling, and retry mechanism - Compatible with OpenAI's API endpoint Tech stack: Python Why it matters: This API offers a unified endpoint for generating images across various models, eliminating the need for multiple API keys and reducing costs. It supports both 1K and 2K resolutions and is compatible with OpenAI's API, making it a versatile tool for image generation and editing. GitHub stars: 12

### Overview: MMoCHi is a hierarchical classification system designed for CITE-Seq data, but applicable to diverse single-cell sequencing modalities. It includes tools for integrating data of Antibody Derived Tag (ADT) expression, high-confidence thresholding of cell populations using ADT expression, gene expression, and cell metadata, building a hierarchy of cell subset classifiers, and training and evaluating random forest classifiers at each hierarchy level. ### Key features: - Integrating data of Antibody Derived Tag (ADT) expression - High-confidence thresholding of cell populations using ADT expression, gene expression, and cell metadata - Building a hierarchy of cell subset classifiers - Training and evaluating random forest classifiers at each hierarchy level ### Tech stack: Python ### Why it matters: MMoCHi provides a comprehensive and efficient toolset for analyzing and classifying single-cell sequencing data, particularly CITE-Seq data, by integrating diverse modalities, thresholding for high confidence, and building hierarchical classifiers. Its ability to handle complex data integration and provide precise classification makes it a valuable resource in the field of single-cell biology and immunology.

Overview: Seedance 1.5 Pro API is an OpenAI-compatible endpoint for accessing model id, pricing, and parameters of Seedance 1.5 Pro, providing a comprehensive set of tools for developers. Key features: - Model ID and Pricing - Image-to-Video and Text-to-Video Generation - Real-time Pricing and Billing - Smooth Motion and 4K Quality - Stable and Precise Control Tech stack: Python Why it matters: Seedance 1.5 Pro API simplifies the process of integrating Seedance 1.5 Pro with developers, offering a cost-effective and efficient way to access its advanced features without the need for a subscription plan. Repository: drvscj09me9h/doubao-seedance-1-5-pro-api-ko Primary language: Python GitHub stars: 12 GitHub description: Seedance 1.5 Pro API (`seedance-1.5-pro`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Overview: This repository contains tested Seedance 1.5 Pro prompts, including example renders, duration, and cost information for the model id `seedance-1.5-pro`. The prompts are designed to be machine-readable and include structure, light direction, framing, and setting details. Key features: - 4 tested Seedance 1.5 Pro prompts - Example renders, durations, and costs on the APIMart route - Structure for writing prompts, including subject, light, framing, setting, and finish Tech stack: Python Why it matters: This repository provides a practical guide for developers and artists who want to use Seedance 1.5 Pro with ease, ensuring accurate and efficient rendering of their images and videos without the need for a monthly subscription.

Overview: A simple yet powerful semantic AI search engine, designed for developers looking to enhance their search capabilities. Key features: - Semantic search functionality - Integration with various databases - Real-time updates and indexing - Customizable search filters Tech stack: TypeScript Why it matters: This project offers a robust solution for developers seeking to improve their search engine capabilities, making it easier to find relevant information quickly and efficiently.

### Overview: Nano Banana 2 Lite Prompts: 8 Tested Recipes with Outputs ### Key features: - **Model ID:** `gemini-3.1-flash-lite-image-ext` - **Recipes:** 8 (machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.0125 per image ### Tech stack: Python ### Why it matters: A versatile and affordable way to generate high-quality image prompts without the need for a monthly subscription.

### Overview: Z Image Turbo Prompts offers tested image prompt recipes with example renders, aspect ratios, the model ID (`z-image-turbo`), and the cost per image on the APIMart API route. ### Key Features: - **Model ID:** `z-image-turbo` - **Aspect Ratios:** 1:1, 4:3, 8:5, 8:10, 16:9, 2:3, 3:2, 1:2 - **Cost per Image:** $0.01 ### Tech Stack: Python ### Why It Matters: Teams can leverage Z Image Turbo Prompts to create effective and efficient image prompts, ensuring high-quality renders at a low cost. The structured format allows for easy replication and adaptation of recipes, making it a valuable tool for developers and designers.

Overview: Seedance 2.0 API provides OpenAI-compatible endpoint for generating high-quality video content, including text-to-video and image-to-video models with cinematic motion and HD output. Key features: - Supports text-to-video and image-to-video models - Provides cinematic motion and HD output - Compatible with OpenAI endpoint - Supports various resolutions and aspect ratios - Supports image URLs for style references - Supports model parameters such as prompt, duration, resolution, and size Tech stack: Python Why it matters: Seedance 2.0 API simplifies the process of generating high-quality video content by providing an OpenAI-compatible endpoint, making it easier for developers to integrate into their projects without the need for additional integration or setup.

### Overview: Seedance 2.0 Prompts: 8 Tested Recipes with Outputs Seedance 2.0 Prompts offers tested image prompt recipes, including example renders, aspect ratios, the model ID (`seedance-2.0`), and the cost per image. This repository provides a concise guide to using Seedance 2.0 for image prompts, ensuring efficient and effective use of the API. ### Key Features: - **Model ID:** `seedance-2.0` - **Cost per Image:** $0.066 per second - **Duration:** 5 seconds - **Prompt Structure:** - **Subject:** Concrete Object or Person - **Light:** Direction + Quality - **Framing:** Ratio + Lens Language - **Setting:** Surface, Backdrop, Environment - **Finish:** Render or Film Character ### Tech Stack: - Python ### Why It Matters: - **Efficient Usage:** The cost of $0.066 per second is highly competitive, making it ideal for quick, on-demand image generation. - **Versatile:** The same base URL and authorization token can be used across multiple models, ensuring a comprehensive API experience. - **Real-Time Pricing:** The cost is displayed in the response, making it easy to track usage and manage expenses. ### Repository: - **Repository:** `e3udvo/doubao-seedance-2-0-prompts-fr` - **Stars:** 10 - **Description:** Seedance 2.

### Overview: TIGER is a unified generative model framework designed for multimodal dialogue response generation. It addresses the challenge of generating dialogue responses that are both text and images, providing a superior multimodal conversational experience. ### Key features: - TIGER is capable of handling conversations involving any combination of modalities. - It includes a textual dialogue response generator and a Text-to-Image translator. - The system is designed to be open-domain, capable of generating responses to various dialogue contexts. - Users can customize the system by choosing decoding strategies, adjusting parameters, and modifying prompt templates. ### Tech stack: Python ### Why it matters: TIGER achieves new state-of-the-art results on both automatic and human evaluations, demonstrating its effectiveness in providing a superior multimodal conversational experience.

### Overview: XR2IND-VR is a Unity-based VR application designed for industrial training, featuring three virtual classrooms: tutorial, assembly, and troubleshooting. The app provides interactive 3D models of routers and switches, integrated with a language model assistant (LLM) via a REST API for real-time guidance. ### Key Features: - **Virtual Classrooms**: Tutorial, Assembly, and Troubleshooting rooms. - **Interactive 3D Models**: Three routers/switches with various components. - **Language Model Assistant (LLM)**: Provides real-time guidance through speech. ### Tech Stack: Unity ### Why It Matters: XR2IND-VR blends immersive VR environments with the intelligence of language models, enhancing the training experience with real-time guidance and offline manuals for accuracy. The app is designed for deployment on Meta Quest 3, making it suitable for industrial training and troubleshooting. ### GitHub Stars: 13 ### Repository: giorgosfatouros/XR2IND-VR ### Primary Language: C# ### Deployment Setup: - **Environment Preparation**: 1. Download Unity Hub. 2. Install Unity 2022.3.19f1. 3. Install Meta Quest Link. 4. Enable Quest Link on your Meta Quest 3 headset. ### Whiteboard: - Displays steps and task statuses on whiteboards. ### 3D Models: - Interactive models of routers and switches with various components. ### Speech-to-Text Component: - Uses the Hugging Face Unity API for speech-to-text functionality

Overview: This project is an unofficial re-implementation of "Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack" (ICML2025). The implementation aims to address the safety concerns in fine-tuning-as-a-service scenarios, particularly focusing on the harmful fine-tuning attack that can lead to the forgetting of safety alignment and harmful behavior in the fine-tuned model. Key features: - Implement an unofficial re-implementation of the paper's method. - Address the safety issue in fine-tuning-as-a-service scenarios. - Focus on the harmful fine-tuning attack that can break down the safety alignment of large language models. Tech stack: Python, HuggingFace Transformers, SLURM, and SLURM scripts. Why it matters: This project is crucial for ensuring the safety and reliability of large language models in real-world applications, particularly in scenarios where fine-tuning-as-a-service is prevalent. By providing a robust solution to the harmful fine-tuning attack, it helps mitigate potential risks and maintains the integrity of AI systems.

Overview: My_AI is a private AI assistant that runs entirely on your computer using Ollama, offering 12 languages support and various features like agents, document generation, image creation, voice input/output, and more. It's designed for offline use and can be accessed via mobile or VS Code extension. Key features: - 9 specialized agents and visual workflows - Word, PDF, Excel, and PowerPoint generation - Local image generation - Two-way voice input and output - VS Code extension integration - End-to-end encrypted mobile access - 12 languages support Tech stack: Python Why it matters: My_AI provides a local alternative to ChatGPT, offering comprehensive AI capabilities and language support, making it suitable for both productivity and creative tasks.

Overview: MAVERICS is a suite of test-only visual question answering datasets created from image captions, validated by manual verification, and generated from the COCO and CC3M datasets. Key features: - Test-only visual question answering datasets - Created from COCO and CC3M datasets - Generated from image captions using VQ^2A approach - Manually verified for accuracy Tech stack: Python, JSON Why it matters: MAVERICS provides a controlled environment for evaluating visual question answering models, ensuring that the questions and answers are consistent with the original image captions, thus improving the reliability and accuracy of the evaluation.

### Overview: LangSearch is a Python package designed for easily creating semantic search-based LLM applications. It leverages the power of Large Language Models (LLMs) like ChatGPT, making it highly customizable and extensible. ### Key Features: - **Automatic Data Discovery**: Crawling websites and local data to find relevant content. - **Support for 1000+ MIME Types**: Including HTML, PDF, DOCX, TXT, PNG, MP3, MP4, etc. - **Batteries Included Pipelines**: Preprocessing data with pipelines. - **Data Persistence**: Ensures efficient data synchronization. - **Embeddings**: Utilizes `text2vec-transformers` and `CLIP` models for text and images. - **RAG Methods**: Simple QA and HyDE for retrieval augmented generation. ### Tech Stack: - Python ### Why it Matters: LangSearch simplifies the process of creating semantic search-based LLM applications, making it accessible and efficient for developers working with non-public data. It integrates well with existing Python packages and tools, ensuring a smooth workflow without the need for extensive plumbing. ### Installation: ```bash pip install langsearch ``` ### Documentation: Documentation is available [here](https://langsearch.dibya.online), and code examples are in the `examples` folder. ### Features: 1. **Automatic Data Discovery**: Crawling websites and local data. 2. **Support for 1000+ MIME Types**: Including HTML, PDF, DOCX, TXT, PNG, MP3,

### Overview: Kling 3.0 Turbo Prompts: 8 Tested Recipes With Outputs ### Key Features: - **Model:** `kling-3.0-turbo` - **Recipes:** 4 (machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.1144 per second (estimated cost of the whole set: $0.4576) ### Tech Stack: - Python ### Why It Matters: - **Key 1-Click Access:** Same `https://api.apimart.ai/v1` base URL and `Authorization` header for Kling 3.0 Turbo and 300+ models. - **No Subscriptions Needed:** $1 or less per second, no pre-paid plans required. - **Clear Pricing:** All costs reported in response, refunds for failed tasks. - **Non-Synchronous Design:** Send `task_id` and poll `GET /v1/tasks/{id}` for batch processing and retries. ### Alternative Names: - **Kling** - **可霊** ### Recipes: - **Example Render:** - **Product Ad:** A matte ceramic mug on a dark stone plinth with steam rising, soft key light from the left, shallow depth of field, commercial product photography. - **Cinematic:** A rain-soaked street at night, camera pushing in slowly past neon reflections, figure with an umbrella, 35mm anamorphic, film grain. - **Food Commercial:** Overhead