image-to-imageQwen Image Layered
fal-ai/qwen-image-layered/loraQwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. Use loras to get your custom outputs.
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.
3Kaista-ready endpointsPublic catalog connected
PUBLIC REFERENCE CATALOG
Page 40 · 28 per pageAll model endpoints
image-to-image
video-to-videoLucy 2.1 VTON Realtime
decart/lucy2-vton/realtimeRealtime Try On experience with Decart Lucy 2.1 VTON
image-to-image
text-to-videoInfinitalk
fal-ai/infinitalk/single-textInfinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.
image-to-imageOptimized Latent Consistency (SDv1.5)
fal-ai/lcm-sd15-i2iProduce high-quality images with minimal inference steps. Optimized for 512x512 input image size.
text-to-imageIdeogram V2 Turbo
fal-ai/ideogram/v2/turboAccelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.
text-to-videoKandinsky5
fal-ai/kandinsky5/text-to-video/distillKandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation.
image-to-imageImage Editing Wojak Style
fal-ai/image-editing/wojak-styleTransform your photos into wojak style while keeping the original characters likeness
text-to-videoLongCat Video Distilled
fal-ai/longcat-video/distilled/text-to-video/480pGenerate long videos from text using LongCat Video Distilled
text-to-imageBitdance
fal-ai/bitdanceImage generation with BitDance. Fast, high-resolution photorealistic images using an autoregressive LLM— for efficient, high-quality results.
trainingPhota Create Profile
fal-ai/phota/create-profileGenerate profiles using 30-50 images of a subject with Phota.
video-to-videoLTX Video-0.9.7 13B Distilled
fal-ai/ltx-video-13b-distilled/multiconditioningGenerate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA
text-to-imageOmniGen v1
fal-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!
audio-to-audioStable Audio 3 Small Music Base Audio Inpainting
fal-ai/stable-audio-3/small/music/base/audio-inpaintingStable Audio 3 Small Music Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected music segments guided by text prompts.
image-to-3dHunyuan3D
fal-ai/hunyuan3d/v2/multi-view/turboGenerate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
video-to-videoFlux 3 Extend Video Draft
blackforestlabs/flux-3/extend-video/draftFLUX.3 is Black Forest Labs' frontier audio/video model. Generate fast, low-cost draft previews that continue an existing clip, with a reusable draft cache for full-quality enhancement.
video-to-videoLightx
fal-ai/lightx/relightUse tlightx capabilities to relight and recamera your videos.
image-to-imageTelestyle V2 Style Transfer
fal-ai/telestyle-v2Restyle any image with TeleStyle v2 — provide an original image and a styling reference, and the model re-renders the original in the reference's visual style while preserving its content and composition.
trainingRecraft V4 Styles Pro Create Style
recraft/v4/pro/create-styleCreates a reusable style from your reference images for use with Recraft V4 Styles Pro generation
trainingFlux 2 Klein 9B Base Trainer
fal-ai/flux-2-klein-9b-base-trainer/editFine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.
text-to-imageIdeogram V2A
fal-ai/ideogram/v2aGenerate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.
text-to-imageZ-Image Turbo Seamless Tiling Lora
fal-ai/z-image/turbo/tiling/loraGenerate seamlessly tiling photorealistic images from text using Z-Image Turbo and custom LoRA
image-to-videoMarey Realism V1.5
moonvalley/marey/i2vGenerate a video starting from an image as the first frame with Marey, a generative video model trained exclusively on fully licensed data.
image-to-imageImage Editing Professional Photo
fal-ai/image-editing/professional-photoTurn your casual photos into stunning professional studio portraits with perfect lighting and high-end photography style.
visionSam 3
fal-ai/sam-3/image/embedSAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
visionSa2VA 8B Image
fal-ai/sa2va/8b/imageSa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
text-to-image
text-to-videoLongCat Video
fal-ai/longcat-video/text-to-video/720pGenerate long videos in 720p/30fps from text using LongCat Video