AI Image Prompt Generator
Build detailed image prompts for Midjourney, Stable Diffusion and DALL-E.
Write better prompts and keep your token bill honest.
Build detailed image prompts for Midjourney, Stable Diffusion and DALL-E.
Turn a rough idea into a structured prompt that gets a usable answer.
Estimate how many tokens your text costs before you send it.
Create a persona for a chatbot or roleplay character, as a prompt or a character card.
Write valid tool-calling JSON schemas without hand-editing braces.
Work out what an AI feature will cost per call, per day and per month.
Split a dataset into training, validation and test files with a repeatable shuffle.
Read the prompt, seed and settings saved inside an AI-generated PNG.
Convert a conversation into ChatML, Llama 3, Mistral, Gemma or Alpaca prompt templates.
Strip markdown, smart quotes and invisible characters out of generated text.
Compare two embedding vectors by cosine similarity, dot product and distance.
Work out how much GPU memory a local LLM needs to run or fine-tune.
Split long documents into overlapping chunks for embeddings and RAG.
Build a chat API request for OpenAI, Claude, Gemini, Groq or Ollama in cURL, Python, JS or PHP.
See the file size of every GGUF quant of a model, and which ones fit your memory.
Score a prompt on the parts that change the answer, and see what is missing.
Generate robots.txt rules to block GPTBot, ClaudeBot, CCBot and other AI crawlers.
Validate a JSONL file line by line, and check fine-tuning datasets before you upload.
Add aspect ratio, stylize, chaos, style references and more to a Midjourney prompt.
Write both custom instruction boxes, each checked against the 1,500 character limit.
Clean up a pasted chat log into a tidy transcript, Q&A pairs, JSON or CSV.
Find the words and habits that make text read as AI-generated, so you can edit them out.
Estimate what a fine-tune costs to train and run, and when it pays for itself.
Scan untrusted text for prompt injection patterns and hidden characters before a model reads it.
Turn input and output pairs into a clean, consistent few-shot prompt block.
Build a structured system prompt for a chatbot, assistant or custom GPT.
Generate MCP server config for Claude Desktop, Claude Code, Cursor, VS Code and Windsurf.
Turn conversations.json from a ChatGPT or Claude export into readable Markdown files.
Turn question and answer pairs into a JSONL training file for OpenAI, Llama or Gemini.
Estimate the cost and vector storage of embedding a document corpus for RAG.
See whether your text fits a model context window, and how much room is left.
Compare GPT, Claude, Gemini, DeepSeek and Llama by price, context and monthly cost.
Fill a prompt template from spreadsheet rows and get one prompt per row.
Find the right resolution for SDXL, FLUX, DALL-E or Midjourney at any aspect ratio.
Remove markdown from ChatGPT and Claude answers and keep clean plain text.
Build a Stable Diffusion negative prompt from the problems you keep getting.
Convert between tokens, words, characters, pages and reading time.
No tools in this category yet.
Utilities for working with large language models, without sending anything to one. Build and grade prompts, system prompts and personas, check untrusted text for prompt injection, estimate tokens, context windows and API cost, size a local model for your GPU, validate and split fine-tuning datasets, convert chat exports and transcripts, generate MCP and API request code, and control which AI crawlers can read your site. No API key, no model call — every tool runs on what you paste, in your own browser.