Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
text-to-audiofal-ai/stable-audio-3/small/music/base/text-to-audioStable Audio 3 Small Music Base is the foundational 459 million parameter checkpoint generating full music compositions up to 2 minutes from text prompts, intended as the unmodified base for fine-tuning.
image-to-imagefal-ai/image-editing/retouchRetouch photos of faces. Remove blemishes and improve the skin.
video-to-videofal-ai/sam2/videoSAM 2 is a model for segmenting images and videos in real-time.
audio-to-videofal-ai/longcat-single-avatar/image-audio-to-videoLongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.
text-to-speechfal-ai/minimax/preview/speech-2.5-hdGenerate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
text-to-imagefal-ai/hidream-o1-image/devUnified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.
image-to-videofal-ai/pixverse/v4.5/transitionCreate seamless transition between images using PixVerse v4.5
image-to-videofal-ai/vidu/q1/reference-to-videoGenerate video clips from your multiple image references using Vidu Q1
text-to-imagefal-ai/nucleus-imageNucleus-Image is a text-to-image generation model built on a sparse mixture-of-experts (MoE) diffusion transformer architecture.
image-to-imagefal-ai/flux-control-lora-canny/image-to-imageFLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.
3d-to-3dtripo3d/tripo/segmentAutomatically splits a 3D model into semantic parts for editing, texturing, and rigging.
text-to-video
video-to-videofal-ai/luma-dream-machine/ray-2-flash/reframeAdjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.
text-to-speechfal-ai/qwen-3-tts/text-to-speech/0.6bBring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model
image-to-imagefal-ai/hidream-o1-image/dev/editUnified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.
video-to-videodecart/lucy-edit/proEdit outfits, objects, faces, or restyle your video - all with maximum detail retention.
text-to-imagefal-ai/glm-imageCreate high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.
image-to-imagefal-ai/flux/srpo/image-to-imageFLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.
image-to-imagefal-ai/image-editing/background-changeReplace your photo's background with any scene you desire, from beach sunsets to urban landscapes, with perfect lighting and shadows
text-to-3dfal-ai/hyper3d/rodin/v2.5/text-to-3d/fastRodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.
video-to-videofal-ai/ltx-2.3/retake-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.
video-to-videofal-ai/wan-22-vace-fun-a14b/depthVACE Fun for Wan 2.2 A14B from Alibaba-PAI
text-to-imageimagineart/imagineart-1.5-preview/text-to-imageImagineArt 1.5 text-to-image model generates high-fidelity professional-grade visuals with lifelike realism, strong aesthetics, and text that actually reads correctly.
video-to-textnvidia/nemotron-3-nano-omni/videoVideo reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts video plus a prompt and returns text.
text-to-image
video-to-videoveed/video-background-removal/green-screenRemove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.
visionfal-ai/florence-2-large/captionFlorence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
video-to-videofal-ai/wan/v2.2-a14b/video-to-videoWan-2.2 video-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and source videos.