Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
trainingfal-ai/ltx23-trainer-v2/interpolateTrain a LoRA that generates the video between keyframes — supply first/last (and optional middle) frames at inference and the model fills the in-between motion.
trainingfal-ai/ltx23-trainer-v2/outpaintTrain a LoRA that expands the video frame outward, keeping an inner rectangle fixed and generating the surrounding region.
trainingfal-ai/ltx23-trainer-v2/v2aTrain a LoRA that generates audio (foley / sound design) for a silent video, learning a soundtrack that matches the on-screen action.
trainingfal-ai/ltx23-trainer-v2/v2v-maskedTrain a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.
image-to-videofal-ai/pixverse/v3.5/image-to-video/fastGenerate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast
speech-to-textfal-ai/speech-to-text/turbo/streamLeverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.
worldsminimax/h3-max/directorDirect continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.
worldsminimax/h3-max/reference-directorDirect a continuous world in real time with image references and text prompts.