visionNSFW Filter
fal-ai/imageutils/nsfwPredict the probability of an image being NSFW.
EXPLORE / MODEL DIRECTORY
Explore models.Know what runs.
Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
2Kaista-ready endpointsPublic catalog connected
PUBLIC REFERENCE CATALOG
Page 8 · 28 per pageAll model endpoints
vision
text-to-videoSeedance 2.5 US Text to Video
bytedance/seedance-2.5/us/text-to-videoUS-hosted ByteDance Seedance 2.5 generates cinematic video from text with synchronized audio, up to 30-second duration, and 480p, 720p or 1080p output.
text-to-audioMiniMax Music 3
minimax/music-3MiniMax Music 3 is a high-performance music generation model for creating complete songs up to five minutes long
image-to-3dTripo H3.1 Multiview to 3D
tripo3d/h3.1/multiview-to-3dGenerate 3D models from multiple view images using Tripo H3.1.
image-to-videoKling O3 Reference to Video [Standard]
fal-ai/kling-video/o3/standard/reference-to-videoTransform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.
image-to-imageFlux 2 Max
fal-ai/flux-2-max/editFLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.
video-to-videoDepth Anything Video
fal-ai/depth-anything-videoGenerates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.
image-to-3dMeshy 7.1 Image to 3D
meshy/v7.1/image-to-3dMeshy 7.1 generates 3D models from a single image, with standard, low-poly, and Smart Topology modes, optional textures and PBR maps, and geometry resolution up to 4K.
image-to-videoMischief 1
tbc/mischief-1/image-to-videoTBC mischief 1 is the world's first neuron-derived video model. Generate videos 5x faster at a fraction of the cost, so you can explore more ideas, experiment freely, and make more mischief.
video-to-videoTopaz Upscale Video Generative
topaz/upscale/video/generativeProfessional generative video upscaling powered by Topaz Labs. Starlight models rebuild detail that is not in the source, with Fast variants at half the price. Best for low-quality, compressed or archive footage.
video-to-videoGemini Omni Flash 1.1 Edit
google/gemini-omni-flash/v1.1/editGemini Omni Flash 1.1 is Google's multimodal video model. This endpoint edits video through natural-language instruction, applying the requested change while preserving the parts of the scene you want kept, and carrying character and scene consistency across successive edits.
text-to-audioStable Audio 3
fal-ai/stable-audio-3/medium/text-to-audioStable Audio 3 Medium is a 1.4 billion parameter latent diffusion model that generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for safe commercial use.
text-to-audioMinimax Music
fal-ai/minimax-music/v2Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.
image-to-imageCrystal Upscaler
clarityai/crystal-upscalerAn advanced image enhancement tool designed specifically for facial details and portrait photography, utilizing Clarity AI's upscaling technology.
audio-to-audioElevenLabs Audio Isolation
fal-ai/elevenlabs/audio-isolationIsolate audio tracks using ElevenLabs advanced audio isolation technology.
trainingTrain Flux LoRA
fal-ai/flux-lora-fast-trainingTrain styles, people and other subjects at blazing speeds.
image-to-imageSam 3 1
fal-ai/sam-3-1/imageSAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.
image-to-videoHeyGen Video Image to Video
heygen/heygen-video/image-to-videoHeyGen Video animates your image as the first frame of a 5 to 15 second clip, with generated sound, built on MiniMax H3 and post-trained by HeyGen.
image-to-image
image-to-video
image-to-imageGemini 3.1 Flash Image Preview
fal-ai/gemini-3.1-flash-image-preview/editGemini 3.1 Flash Image (a.k.a. Nano Banana 2) is Google's new state-of-the-art fast image generation and editing model
image-to-imageSeedream
bytedance/seedream/v5/lite/editImage editing endpoint for the fast Lite version of Seedream 5.0, supporting high quality intelligent image editing with multiple inputs.
unknownOpenRouter [Audio]
openrouter/router/audioRun any audio capable LLM with fal. Process audio files — transcription, analysis, understanding — using Gemini (Google) models. Supports wav, mp3, aiff, aac, ogg, flac, m4a. Powered by OpenRouter.
image-to-imageSeedream 5.0 Pro Layerize
bytedance/seedream/v5/pro/layerizeSplits a finished image into independent, editable transparent-PNG layers — background plus separate elements, from a text description, returning 2 to 17 layers per call for non-destructive reuse in design tools.
image-to-imageFLUX 2 Pro Outpaint
fal-ai/flux-2-pro/outpaintOutpainting generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.
text-to-speechQwen 3 TTS - Text to Speech [1.7B]
fal-ai/qwen-3-tts/text-to-speech/1.7bBring 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
text-to-imageFLUX.1 [schnell]
fal-ai/flux-1/schnellFastest inference in the world for the 12 billion parameter FLUX.1 [schnell] text-to-image model.
image-to-videoWan v2.2 A14B
fal-ai/wan/v2.2-a14b/image-to-videofal-ai/wan/v2.2-A14B/image-to-video