Projects

### Overview: Nano Banana 2 Lite Prompts: Test Recipes with Example Renders, Aspect Ratios, Model ID (`gemini-3.1-flash-lite-image-ext`), and Cost Per Image. ### Key Features: - **Model ID:** `gemini-3.1-flash-lite-image-ext` - **Aspect Ratios:** 1:1, 4:3, 16:9 - **Cost Per Image:** $0.0125 ### Tech Stack: - Python ### Why It Matters: Nano Banana 2 Lite Prompts offer tested image prompt recipes, aspect ratios, and model IDs, making it a valuable resource for developers looking to enhance their projects with professional-grade image prompts.

**Overview:** Seedance 1.5 Pro Prompts: 8 Tested Recipes with Outputs **Key features:** - **Model:** `seedance-1.5-pro` - **Recipes:** 4 (Machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.0104 per second — Estimated cost of the whole set: $0.0416 **Tech Stack:** Python **Why It Matters:** - **Key:** One API Key, Access to all models via `https://api.apimart.ai/v1` - **Cost:** $1 per charge, Pay-as-you-go - **Cost Tracking:** Real-time cost reported on completion - **Asynchronous Design:** Batch and retry tasks through queues **Repository:** ukvv6hjermhm/seedance-1-5-pro-prompts-cn **Primary Language:** Python **GitHub Stars:** 8 **GitHub Description:** Seedance 1.5 Pro Prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`seedance-1.5-pro`) and the cost per image.

### Overview: Nano Banana Pro prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`gemini-3-pro-image-preview`) and the cost per image. ### Key features: - **Model ID:** `gemini-3-pro-image-preview` - **Aspect Ratios:** 1:1, 4:3, 3:4, 8:5, 8:9, 16:9, 2:1, 3:2, 1:16 - **Cost per Image:** $0.03 (4K $0.04) ### Tech Stack: Python ### Why it Matters: Nano Banana Pro (`gemini-3-pro-image-preview`) offers a cost-effective solution for image prompts, providing high-quality results at a minimal price point. The API is compatible with OpenAI and supports various aspect ratios, making it versatile for different use cases.

### Overview: Gemini Nano Banana 2.1 API (`gemini-nano-banana-2.1`) is a powerful model id and pricing endpoint for OpenAI-compatible API. It offers a seamless and efficient way to access 300+ models, including text-to-image and reference-image editing, via the APIMart image API. ### Key features: - **Model ID and Pricing:** Supports the `gemini-nano-banana-2.1` model with per-image pricing based on resolution. - **OpenAI-Compatible Endpoint:** Provides an OpenAI-compatible API route `https://api.apimart.ai/v1`. - **Pricing Model:** Charges based on the number of generated images, with a minimum charge of $1 for the first request. - **Real-Time Pricing:** Prices are updated in real-time on the pricing page. - **Token Rates:** Text input costs $1.2/M, image input costs $1.2/M, text output costs $6/M, and image output costs $24/M. - **Asynchronous Design:** Supports batch processing and retries without requiring custom integrations. - **Model Page:** Detailed model page for the specific tier and features. ### Tech stack: Python ### Why it matters: - **Key, Entire Directory Access:** Same base URL and `Authorization` header for accessing multiple models. - **Cost-Effective:** Charges $0.0137 per image, with no subscription or prepayment required. - **Immediate Feedback:** Reports actual cost for completed tasks, with failed tasks automatically

### Overview: A minimal Node.js RESTful server for a Retrieval-Augmented Generation (RAG) system using ChromaDB and Ollama! ### Key features: - Chat with private documents securely! - Search and query your data easily using Natural Language only! - Keep all your LLMs up to date with the latest data. - Use any open source LLM of your choice. [Browse LLMs](https://ollama.com/library) - This repo can be used as a template to easily integrate LLMs with RAG functionality into your MERN (or any other node.js) stack apps. ### Tech stack: JavaScript ### Why it matters: This project provides a comprehensive solution for integrating a Retrieval-Augmented Generation (RAG) system with ChromaDB and Ollama, making it easy to build and deploy a secure, up-to-date, and domain-specific knowledge base application.

### Overview: Nano Banana 2 Lite Prompts: 8 Tested Recipes with Outputs <!-- conv-kit:v1 --> <p align="center"> <img src="assets/badges/price.svg" alt="observed unit price"> <img src="assets/badges/billing.svg" alt="billing model"> <img src="assets/badges/compat.svg" alt="OpenAI-compatible endpoint"> </p> <p align="center"> <img src="assets/01-product-hero-perfume.jpg" width="820" alt="Sample render via the APIMart image API"> </p> > **from $0.0125 per image** — um único endpoint compatível com OpenAI em `https://api.apimart.ai/v1`, sem plano mensal. *(observado em 2026-10-12)* **[Get an API key](https://go.apimart.ai/k-242320)** · **[Live pricing](https://go.apimart.ai/k-43b64d)** · **[Model page](https://go.apimart.ai/k-856b52)** · [⚡ 60-second quickstart](#quickstart) **Por que os times usam Nano Banana 2 Lite (`gemini-3.1-flash-lite-image-ext`) via APIMart** - **Uma chave, o catálogo inteiro.** A mesma base URL `https://api.apim

Overview: This project provides an educational implementation of Flash Attention v2 in CUDA, focusing on clarity and ease of understanding. It includes features like tiling, CUDA Tensor Cores support, and variable-length sequences. Key features: - Flash Attention v2 algorithm with tiling - CUDA Tensor Cores for matrix operations - FP16 and BF16 support - Variable-length sequences (continuous batching) - Causal masking - Flash decoding Tech stack: Python Why it matters: This project simplifies the Flash Attention algorithm, making it accessible for developers to understand and modify, while maintaining the core concepts for educational purposes.

Overview: This project is an implementation of the paper "Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model," focusing on sarcasm detection using a hierarchical fusion model in Twitter data. Key features: - Hierarchical Fusion Model - Multi-Modal Data Integration - Twitter-Specific Preprocessing Tech stack: Python, PyTorch Why it matters: This project provides a practical solution for sarcasm detection in Twitter data, leveraging advanced machine learning techniques to improve the accuracy of sarcasm detection in social media platforms. Repository: wrk226/pytorch-multimodal_sarcasm_detection Primary language: Jupyter Notebook GitHub stars: 14 GitHub description: It is the implementation of paper "Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model"

Overview: Prompt Forge 是一个用于生成 NovelAI 提示词的工具，它能将一句话翻译成符合特定风格的标签流，然后在本地运行「NAI 整理 + 提示词体检」，生成的提示词可编辑并可保存。它提供了一个纯本地、零运行时依赖的解决方案，适用于多种OpenAI接口。 Key features: - 只做 NovelAI — 正向统一 danbooru 标签流、负向统一 UC； - 生成后本地再跑一遍「NAI 整理 + 体检」； - 提供可编辑的置顶破限词、角色设定、细分标签与拼装板、设定集、历史与保存库； - 纯本地、零运行时依赖，直连任意 OpenAI 兼容接口。 Tech stack: JavaScript。 Why it matters: Prompt Forge 是一个简化了生成 NovelAI 提示词过程的工具，它能将一句话翻译成符合特定风格的标签流，然后在本地运行「NAI 整理 + 提示词体检」，生成的提示词可编辑并可保存。它提供了一个纯本地、零运行时依赖的解决方案，适用于多种OpenAI接口。 Repository: yu20000505/prompt-forge Primary language: JavaScript GitHub stars: 12 GitHub description: 一句话生成 NovelAI 出图提示词：正向 danbooru 标签流 + UC 负向，生成后本地再跑

Overview: Wan 2.7 Image API is a model id, pricing, and parameters for the OpenAI-compatible API endpoint, providing high-quality image generation at a cost of $0.0216 per image. Key features: - Supports multiple model versions for high-quality images - Offers flexible pricing with a minimum cost of $1 per task - Tracks and reports costs in real-time - Provides API key for easy integration Tech stack: Python Why it matters: This API allows developers to leverage Wan 2.7 Image model for generating high-quality images at a competitive cost, making it ideal for various applications requiring image generation without the need for a monthly subscription.

Overview: Qwen-Image 3.0 Pro API is a high-fidelity image generation service that offers 1K and 2K output resolutions at a cost of $0.0285712 per image, making it an ideal choice for developers seeking advanced image capabilities without the need for a monthly subscription. Key features: - Supports 1K and 2K output resolutions - Charges $0.0285712 per image, by resolution - Compatible with OpenAI-compatible API endpoint - Asynchronous processing, task results available via `GET /v1/tasks/{task_id}` - Pricing is based on the actual cost of the generated images Tech stack: Python Why it matters: Qwen-Image 3.0 Pro API is designed for developers who need advanced image capabilities without the overhead of a monthly subscription. It offers a single endpoint that can be used for multiple models, making it a cost-effective solution for image generation projects. GitHub stars: 12 Repository: z3phc/qwen-image-3-0-pro-api-fr

Overview: GPT Image 1.5 API is an OpenAI-compatible model serving image generation via APIMart, featuring token-based pricing and an endpoint compatible with multiple models. Key features: - Supports OpenAI's GPT Image 1.5 model - Offers token-based billing for text and image inputs - Compatible with various image resolution tiers - Supports API key authentication and direct pricing Tech stack: Python Why it matters: Provides a convenient and flexible way to integrate image generation into applications, with detailed pricing and billing information available.

Overview: This project provides a FLUX 2 Pro API endpoint (`flux-2-pro`) that offers model id, pricing, parameters, and copy-paste examples for the OpenAI-compatible APIMart endpoint. It simplifies access to 300+ models via a single base URL and `Authorization` header. Key features: - Supports 300+ models including image, video, and language models. - Provides pricing per megapixel based on output size. - Offers a $0.024 per image cost for the first 1MP, with a minimum $1 monthly subscription. - Reports completed tasks with their exact cost and returns failed tasks with a refund. - Designed for non-blocking, non-retrying batch processing. Tech stack: Python Why it matters: This API is useful for developers looking to integrate FLUX 2 Pro with APIMart, simplifying the process of accessing and managing models without the need for a subscription or complex setup. Repository: zbrg4-to41d4s/flux2-api-ja Primary language: Python GitHub stars: 14

### Overview: Seedance 1.0 Pro Prompts: A Comprehensive Guide to Image Prompt Recipes ### Key Features: - **Model ID:** `seedance-1.0-pro` - **Cost per Image:** $0.0184 per second - **Effective Price:** $0.0736 for the set of 4 recipes - **Aspect Ratios:** 16:9, 4:3, 3:2, etc. - **Duration:** 5 seconds per image - **Prompt Structure:** Structured in JSON format for easy integration - **Example Renders:** Detailed renders for each recipe ### Tech Stack: - Python ### Why It Matters: Seedance 1.0 Pro Prompts offer a cost-effective and efficient way to generate high-quality image prompts. The structured prompts help in achieving better results by focusing on specific details and avoiding unnecessary elements, ensuring that the final output is tailored to the desired aesthetic and context.

### Overview: NLPCC 2024 Shared Task 10: Regulating Large Language Models focuses on developing methods to detect and mitigate undesirable outputs from large language models, ensuring the reliability and ethical standards of the generated content. ### Key features: - Multimodal Hallucination Detection for Multimodal Large Language Models - Detoxifying Large Language Models ### Tech stack: Python ### Why it matters: This task is crucial for maintaining the integrity and ethical standards of large language models, ensuring that the outputs are reliable and adhere to community guidelines and ethical standards.

Overview: Z Image Turbo API (`z-image-turbo`) is an OpenAI-compatible endpoint that provides high-speed image generation from text prompts, offering flexible aspect ratios and a billing model based on delivered images. Key features: - One key for access to Z Image Turbo (`z-image-turbo`) and 300+ additional image, video, and language models. - Minimal $1 cost, no need for monthly subscription. - Returns the exact amount in the task's cost field. - Asynchronous processing by default, with task IDs for monitoring. Tech stack: Python Why it matters: Z Image Turbo is an efficient tool for generating stunning images from text prompts, making it a valuable asset for developers and creatives looking to streamline their workflows. GitHub stars: 14

### Overview: Qwen Image 3.0 API (`qwen-image-3.0`) is an OpenAI-compatible endpoint providing high-quality image generation at a cost-effective rate. It supports 1K and 2K resolutions and is priced at $0.0206 per image. The API is designed for teams to seamlessly integrate into their projects without the need for a monthly subscription. ### Key Features: - **One Key, Entire Catalog:** Access to Qwen Image 3.0 and 300+ other models via a single base URL and `Authorization` header. - **$1 Minimum, Pay as You Go:** No subscription or prepaid plans required; pay only for the number of calls made. - **Charge Backs:** The price is reported in the response, ensuring accurate tracking of usage. - **Async by Design:** Submit tasks, retrieve `task_id`, and poll for task status using `GET /v1/tasks/{id}`. ### Tech Stack: - Python ### Why It Matters: - **One Key, Entire Catalog:** The same `https://api.apimart.ai/v1` base URL and `Authorization` header reach Qwen Image 3.0 and 300+ other models. - **$1 Minimum, Pay as You Go:** No subscription or prepaid plans required; pay only for the number of calls made. - **Charge Backs:** The price is reported in the response, ensuring accurate tracking of usage. - **Async by Design:** Submit tasks, retrieve `task_id`, and poll for task

Overview: Nano Banana API (`gemini-2.5-flash-image-preview`) is an OpenAI-compatible endpoint providing fast text-to-image and reference-image editing services. It offers a single key for access to Nano Banana and supports 300+ models including Gemini 2.5 Flash Image, enabling seamless integration with APIMart. Key features: - Access to Nano Banana and 300+ models via a single key - Pricing by resolution, with a default rate of $0.0125 per image - Automatic task polling for progress and task completion - Minimal cost with no need for upfront payments - Asynchronous processing with task IDs and real-time cost reporting Tech stack: Python Why it matters: Nano Banana simplifies access to advanced image editing tools, making it easier for developers to integrate cutting-edge AI capabilities into their projects without the complexity of multiple APIs or upfront costs.

### Overview: This repository provides a collection of 8 tested Nano Banana prompts, each accompanied by an example render, aspect ratio, and the call cost on the `gemini-2.5-flash-image-preview` model. The cost is estimated at $0.0125 per image, making it a cost-effective option for image prompts. ### Key Features: - **Nano Banana Prompts**: 8 tested recipes with example renders, aspect ratios, and the model id (`gemini-2.5-flash-image-preview`) and cost per image. - **API Key**: Access to the Nano Banana prompts via the APIMart image API. - **Model Compatibility**: OpenAI-compatible endpoint, no need for a monthly subscription. - **Cost Estimation**: Estimated cost of the whole set: $0.1. - **Asynchronous Processing**: Tasks are processed in batches, and the cost is returned in the response. ### Tech Stack: Python ### Why It Matters: The Nano Banana prompts offer a cost-effective and efficient way to generate image prompts, especially for those looking to experiment with different materials and lighting setups. The API key allows for easy access to the Nano Banana model without the need for a monthly subscription, making it a practical solution for developers and designers.

Overview: A financial chatbot powered by llama-2 family of models and Retrieval-Augmented Generation (RAG) to answer finance-related questions and cite sources. Key features: - Uses llama-cpp-python for the LLM with the fastest inference on CPU. - Scrapes data from Zerodha Varsity for the RAG database. - Answers questions concisely and cites sources, improving the quality of the generated text. Tech stack: Jupyter Notebook Why it matters: This project showcases the capabilities of RAG and the potential of LLMs on CPUs, demonstrating how to create a chatbot using one's own data and reducing inference time significantly. Repository: 007prateekd/fin-edubot GitHub stars: 13 GitHub description: A financial chatbot powered by llama-2 family of models and Retrieval-Augmented Generation (RAG) to answer finance-related questions and cite sources on your CPU.