Multi-step prompt sequences for complex AI workflows.
37 tools found
Multi-step prompting guide for OpenAI's gpt-image-2 model covering photorealism, text rendering, editing workflows, quality-latency tradeoffs, and resolution
Prompt chain that generates time-aligned subtitles in SRT or VTT format from audio files and transcripts using ElevenLabs forced alignment API.
Isolate clear speech from noisy audio files using ElevenLabs' advanced audio processing. Perfect for podcasts, interviews, and voiceovers.
A promptfoo workflow example demonstrating text-to-speech integration with ElevenLabs provider for testing and evaluating TTS prompt configurations.
A prompt chain example demonstrating advanced text-to-speech capabilities using ElevenLabs TTS provider for multi-step audio generation workflows.
Prompt workflow for comparing text-to-image generation models using the ModelsLab API, enabling side-by-side evaluation of image outputs.
Benchmark workflow comparing QuiverAI Arrow 1.1 and Arrow 1.1 Max models across text-to-SVG generation, image-to-SVG vectorization, and chained
A prompt workflow example demonstrating image generation using Replicate's API, configured to run multi-step AI image creation tasks through promptfoo's
Process video frames with GPT-4.1-mini's vision and GPT-4o TTS for narration and description.
Prompt workflow teaching GPT Image generation and editing with instruction-following, customizable quality/size, transparent backgrounds, and mask-based
Cookbook demonstrating OpenAI's input_fidelity parameter for image editing that preserves faces, logos, and fine details when generating or modifying images.
Compare OpenAI API speech-to-text methods for your use case, from file uploads to real-time streaming.
