Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
text-to-videoalibaba/happy-horse/v1.1/text-to-videoHappy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.
visionfal-ai/florence-2-large/ocrFlorence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
image-to-videofal-ai/ltxv-13b-098-distilled/image-to-videoGenerate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA
text-to-image
video-to-videofal-ai/wan-vace-14b/depthVACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
video-to-videosonilo/v1.1/video-to-video-musicGenerates perfectly synced music for any video. Return a licensed music soundtrack ready for commercial use (optional preservation of the original speech in video)
video-to-video
text-to-videoluma/agent/ray/v3.2/text-to-videoLuma Ray 3.2 generates cinematic video from a text prompt, with control over resolution, duration, and seamless looping, plus reference images to lock in subject and style.
visionfal-ai/moondream2/object-detectionMoondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.
speech-to-textfal-ai/cohere-transcribeCohere Transcribe turns your business audio into accurate text, ready for search, analytics, and automation
image-to-videofal-ai/pixverse/v5/transitionCreate seamless transition between images using PixVerse v5
video-to-videofal-ai/ltx-2.3/extend-videoLTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.
text-to-3dmeshy/v7.1/text-to-3dMeshy 7.1 generates 3D models from text prompts, with untextured preview and textured full modes, standard, low-poly, and Smart Topology options, and geometry resolution up to 4K.
image-to-imagefal-ai/filmInterpolate images with FILM - Frame Interpolation for Large Motion
video-to-videofal-ai/heygen/v2/translate/speedHeygen Translate Model with Extreme Speed
image-to-imagefal-ai/drct-super-resolutionUpscale your images with DRCT-Super-Resolution.
image-to-imagefal-ai/z-image/turbo/controlnetGenerate images from text and edge, depth or pose images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
trainingfal-ai/z-image-trainerTrain LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
image-to-imagefal-ai/retoucherAutomatically retouches faces to smooth skin and remove blemishes.
image-to-imagefal-ai/flux-2-lora-gallery/multiple-anglesGenerates same object from different angles (azimuth/elevation)
audio-to-videofal-ai/wan/v2.2-14b/speech-to-videoWan-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements, and professional camera work for film and television applications
image-to-imagefal-ai/qwen-image-edit/image-to-imageImage to Image Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.
image-to-image
image-to-videofal-ai/wan/v2.2-a14b/image-to-video/loraWan-2.2 image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and images. This endpoint supports LoRAs made for Wan 2.2
image-to-imagefal-ai/phota/enhanceEnhance images while preserving identities with Phota
text-to-3dtripo3d/p2/text-to-3dTripo P2 generates 3D models from a text prompt, with optional PBR textures, adjustable face counts, and triangle or quad mesh topology.
text-to-videofal-ai/hunyuan-videoHunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.
text-to-imagerecraft/v4/style/pro/text-to-imageGenerates raster images that hold a consistent style, from either a saved style ID or reference images attached directly.