image-to-imageImage Preprocessors
fal-ai/image-preprocessors/scribbleScribble preprocessor.
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 51 · 28 per pageAll model endpoints
image-to-image
image-to-imageDocRes
fal-ai/docresEnhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.
trainingERNIE-Image Trainer
fal-ai/ernie-image-trainerLoRA trainer for ERNIE-Image, Baidu's powerful 8B-parameter text-to-image model.
text-to-audioLtx 2.3 Quality
fal-ai/ltx-2.3-quality/text-to-audio/loraText to Audio high-quality using LTX-2.3 with Lora
video-to-videoVideo
bria/video/erase/keypointsHigh-fidelity keypoint-driven video object removal - minimal input, strong temporal consistency. Trained on licensed data for risk-free commercial video editing.
audio-to-videoLTX-2.3 22B
fal-ai/ltx-2.3-22b/audio-to-video/loraGenerate video with audio from audio, text and images using LTX-2.3 and custom LoRA
visionSa2VA 4B Video
fal-ai/sa2va/4b/videoSa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
trainingLTX-2.3 22B Video to Video Trainer
fal-ai/ltx23-v2v-trainerTrain LTX-2.3 22B for video transformation or video-conditioned generation.
visionFlorence 2 Large Region To Category
fal-ai/florence-2-large/region-to-categoryFlorence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
jsonOmnilottie
fal-ai/omnilottie/image-to-lottieConvert your assets into lottie using Omnilottie.
audio-to-videoLtx 2.3 Quality
fal-ai/ltx-2.3-quality/audio-to-video/loraGenerate high-quality video with audio from audio, text and images using LTX-2.3 and custom LoRA
audio-to-audioMirelo SFX1.6
mirelo-ai/sfx1.6/inpaint-audioErase and replace any moment in your audio with AI-driven precision.
image-to-videoLtx 2.3 Quality
fal-ai/ltx-2.3-quality/image-to-video/loraGenerate high-quality video with audio from images using LTX-2.3 and custom LoRA
visionIsaac 0.1 [OpenAI Compatible Endpoint]
perceptron/isaac-01/openai/v1/chat/completionsOpenAI spec compatible endpoint of Isaac-01 which is a multimodal vision-language model from Perceptron for various vision language tasks.
jsonOmnilottie
fal-ai/omnilottie/video-to-lottieConvert your assets into lottie using Omnilottie.
video-to-videoBria Video Eraser
bria/bria_video_eraser/erase/keypointsA high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.
video-to-videoBria's VRMBG 3.0 Realtime
bria/video/background-removal/realtimeRemove video backgrounds in real time with Bria’s VRMBG 3.0 model. Built for live streaming, real-time video apps, content creation, and low-latency workflows that need fast, accurate background removal.
trainingWan-2.1 LoRA Trainer
fal-ai/wan-trainer/t2v-14bTrain custom LoRAs for Wan-2.1 T2V 14B
speech-to-textSpeech-to-Text
fal-ai/speech-to-text/turbo/streamLeverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.
text-to-speechMaya
fal-ai/maya/streamMaya1 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-imageFlorence-2 Large
fal-ai/florence-2-large/region-to-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
trainingLTX 2.3 Trainer (V2) - Video-to-Video IC-LoRA
fal-ai/ltx23-trainer-v2/ic-lora/v2vTrain an IC-LoRA that learns a video-to-video transformation from paired before/after clips, conditioned at inference on a reference (control) video.
text-to-video
text-to-videoInfinity Star
fal-ai/infinity-star/text-to-videoInfinityStar’s unified 8B spacetime autoregressive engine to turn any text prompt into crisp 720p videos - 10× faster than diffusion models.
audio-to-audioWorkflow Utilities Impulse Response
fal-ai/workflow-utilities/impulse-responseFFMPEG Utility for Impulse Response
image-to-imageQwen Image Edit 2509 Lora Gallery
fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portraitGenerate full portrait from a cropped face photo
image-to-imageDocRes-dewarp
fal-ai/docres/dewarpEnhance wraped, folded documents with the superior quality of docres for sharper, clearer results.
image-to-imageImage Preprocessors
fal-ai/image-preprocessors/pidiPIDI (Pidinet) preprocessor.