falai

minimax h3 max — fal's post-trained h3 for stronger prompt adherence and aesthetics. text-to-video, image-to-video with end frame, and reference-based generation. 480p/768p, 5-15s, ~3s per 5s clip.

creates videos where an image appears to talk using advanced lip-sync technology.

creates high-quality, animated videos instantly from any static image.

generates high-quality video content from static images.

text-to-image and image-to-image generation with flux.1 [dev] lora support. custom style adaptation and fine-tuned model variations from black forest labs.

text-to-image and image-to-image generation with flux.2 [klein] lora support. available in 4b and 9b parameter sizes. custom style adaptation and fine-tuned model variations from black forest labs.

advanced text-to-image model creating ultra-high-fidelity 4k visuals with lifelike realism and refined aesthetics.

kokoro tts - lightweight text-to-speech with multiple languages and voices

dia tts - generate realistic dialogue with emotion control, natural nonverbals, and voice cloning