hi hn ! i've been experimenting with text-to-image models since the launch of DALLE. one thing i've noticed is that each provider (openai, google, black forest labs) has their own API params to control things like moderation, prompt upscaling, etc. this makes it difficult to know what knobs need to be turned to optimize for common goals like cost, speed of render, quality, etci built param forge to provide a TUI interface to explore those knobs and get automated feedback on could be optimized to help you achieve your goals
interacting with image models via CLI seems a bit counterintuitive but i've found this approach helpful
mostly looking for feedback, any other problems / annoyances you have in this space etc
:)