Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
text-to-imagefal-ai/flux-subjectSuper fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.
video-to-videofal-ai/wan-vace-apps/long-reframeReframe entire videos scene-by-scene using Wan VACE 2.1
video-to-videofal-ai/id-v2v/relightChange a video’s lighting using a relit reference frame while preserving the scene, subjects, and original performance. ID-V2V Relight propagates the new illumination across the video.
video-to-audiofal-ai/sam-audio/visual-separateAudio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.
image-to-imagefal-ai/qwen-image-edit-plus-lora-gallery/remove-elementRemove unwanted elements (objects, people, text) while maintaining image consistency
image-to-imagefal-ai/fast-lcm-diffusion/image-to-imageRun SDXL at the speed of light
image-to-3dfal-ai/trellis-2/retextureGenerate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.
image-to-imagefal-ai/sdxl-controlnet-union/image-to-imageAn efficent SDXL multi-controlnet image-to-image model.
image-to-imagefal-ai/image-apps-v2/style-transferApply artistic styles like impressionism, cubism, or surrealism to your images.
image-to-3dfal-ai/reconviagen-0.5Generate 3D models from one or more images using ReconViaGen 0.5
image-to-videonvidia/cosmos-3-super/image-to-videoCosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.
image-to-videofal-ai/kandinsky5-pro/image-to-videoKandinsky 5.0 Pro is a diffusion model for fast, high-quality image-to-video generation.
image-to-3dfal-ai/hunyuan3d/v2/mini/turboGenerate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
text-to-imagefal-ai/omnigen-v1OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!
image-to-imagefal-ai/flux-1/dev/image-to-imageFLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.
image-to-imagefal-ai/photomakerCustomizing Realistic Human Photos via Stacked ID Embedding
image-to-imagefal-ai/image-editing/face-enhancementEnhance facial features with professional retouching while maintaining a natural, realistic look
trainingfal-ai/phota/create-profileGenerate profiles using 30-50 images of a subject with Phota.
image-to-image
video-to-audiomirelo-ai/sfx-v1/video-to-audioGenerate synced sounds for any video, and return the new sound track (like MMAudio)
image-to-videofal-ai/ai-avatar/multiMultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.
video-to-videofal-ai/wan-vace-14b/outpaintingVACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
video-to-videowan/v2.6/reference-to-videoWan 2.6 reference-to-video model.
video-to-videofal-ai/lightx/relightUse tlightx capabilities to relight and recamera your videos.
text-to-imagefal-ai/wan/v2.2-a14b/text-to-image/loraWan 2.2's 14B model with LoRA support generates high-fidelity images with enhanced prompt alignment, style adaptability.
image-to-videofal-ai/vidu/q1/image-to-videoVidu Q1 Image to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity from a single image
image-to-imagefal-ai/chrono-editNVIDIA's Logically Consistent and Physics-Aware Image Editing Model
image-to-imagefal-ai/florence-2-large/referring-expression-segmentationFlorence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks