Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
image-to-imagefal-ai/finegrain-eraser/bboxFinegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.
image-to-imagebria/fibo-edit/add_object_by_textPrecisely insert new objects into images with structured spatial commands. Context-aware, high-quality editing with seamless blending. Trained on licensed data for risk-free commercial and brand-safe use.
text-to-videofal-ai/cosmos-predict-2.5/distilled/text-to-videoGenerate video from text and videos using NVIDIA's 2B Cosmos Distilled Model
audio-to-audiofal-ai/stable-audio-3/small/music/audio-inpaintingStable Audio 3 Small Music audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a music track guided by text prompts.
image-to-imagefal-ai/image-editing/youtube-thumbnailsGenerate YouTube thumbnails with custom text
image-to-imagefal-ai/image-preprocessors/teedTEED (Temporal Edge Enhancement Detection) preprocessor.
image-to-videofal-ai/minimax/video-01-director/image-to-videoGenerate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.
video-to-videofal-ai/one-to-all-animation/14bOne-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes
trainingfal-ai/flux-2-trainer-v2/editFine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.
text-to-speechfal-ai/vibevoice/0.5bGenerate long speech snippets fast using Microsoft's powerful TTS.
image-to-imagefal-ai/sdxl-controlnet-union/inpaintingAn efficent SDXL multi-controlnet inpainting model.
image-to-3dfal-ai/hunyuan3d-v3/sketch-to-3dCreate your imagined 3D models with just text. Production-ready, export-ready professional assets with realistic lighting and materials in minutes.
video-to-videofal-ai/cogvideox-5b/video-to-videoGenerate videos from videos and prompts using CogVideoX-5B
text-to-video
image-to-imagebria/fibo-edit/sketch_to_colored_imageConvert line drawings and sketches into photorealistic, fully colored images with preserved structure. Trained exclusively on licensed data for safe commercial and design use.
image-to-imagefal-ai/image-editing/age-progressionSee how you or others might look at different ages, from younger to older, while preserving core facial features.
text-to-videofal-ai/pixverse/v5.6/text-to-videoUse the latest pixverse v5.6 model to turn your texts into amazing videos.
audio-to-audiofal-ai/dia-tts/voice-cloneClone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.
text-to-videofal-ai/fast-animatediff/turbo/text-to-videoAnimate your ideas in lightning speed!
image-to-imagerundiffusion-fal/juggernaut-flux/base/image-to-imageJuggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.
image-to-imagefal-ai/image-apps-v2/texture-transformTransform objects with different surface textures like marble, wood, or fabric.
text-to-videofal-ai/magi-distilledMAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts
image-to-videofal-ai/pixverse/v4/image-to-video/fastGenerate fast high quality video clips from text and image prompts using PixVerse v4
image-to-imagefal-ai/image-apps-v2/city-teleportPlace a person’s photo into iconic cities worldwide.
image-to-3dfal-ai/trellis-2-loraRun inference on LoRA adapters for TRELLIS.2 model
text-to-speechfal-ai/maya/batchMaya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
image-to-imagebria/fibo-edit/replace_object_by_textReplace any object in an image using plain language with fine-grained, precise edits and strong prompt adherence. Trained on licensed data for risk-free commercial and brand-safe use.
text-to-videofal-ai/kling-video/v1/standard/effectsGenerate video clips from your prompts using Kling 1.0