Browse the public fal model directory. Models become callable through Kaista Cloud only after supply, pricing, and compatibility review.
text-to-imagefal-ai/flux-lora/streamSuper fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
video-to-videofal-ai/ltx-2.3-22b/video-to-video/loraGenerate video with audio from videos using LTX-2.3 and custom LoRA
visionfal-ai/marlin/findMarlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?
trainingfal-ai/ltx23-trainer-v2/ic-lora/a2aTrain an IC-LoRA that transforms one audio clip into another, conditioned at inference on a reference audio clip.
trainingfal-ai/ltx23-trainer-v2/ic-lora/av2avTrain an IC-LoRA for a joint audio+video transformation, conditioned on a reference clip's video and audio to produce a matching target.
trainingfal-ai/ltx23-trainer-v2/ic-lora/av2av-maskedTrain an IC-LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.
trainingfal-ai/ltx23-trainer-v2/ic-lora/v2v-maskedTrain an IC-LoRA that regenerates only the masked region of a video, guided by the kept pixels and a separate reference/control video.
trainingfal-ai/ltx23-trainer-v2/a2aTrain a LoRA that transforms one audio clip into another, learning a reference→target mapping from paired audio examples.
trainingfal-ai/ltx23-trainer-v2/a2vTrain a LoRA that generates video from a start image plus a conditioning audio track, producing motion that matches the sound.
trainingfal-ai/ltx23-trainer-v2/audio-extend-prefixTrain a LoRA that continues an audio clip forward in time, generating the audio that follows a short clean prefix.
trainingfal-ai/ltx23-trainer-v2/audio-extend-suffixTrain a LoRA that generates the lead-in to an audio clip, extending audio backward in time from its ending.
trainingfal-ai/ltx23-trainer-v2/audio-inpaintTrain a LoRA that regenerates masked time spans of an audio clip while keeping the rest unchanged.
trainingfal-ai/ltx23-trainer-v2/av2avTrain a LoRA for a joint audio+video transformation, conditioned on a reference clip (its video and audio) to produce a matching target clip.
trainingfal-ai/ltx23-trainer-v2/av2av-maskedTrain a LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.
trainingfal-ai/ltx23-trainer-v2/extend-prefixTrain a LoRA that continues a video forward in time — supply an opening clip at inference and the model generates what comes next.
trainingfal-ai/ltx23-trainer-v2/extend-suffixTrain a LoRA that generates the lead-in to a video, extending a clip backward in time from its ending.
trainingfal-ai/ltx23-trainer-v2/inpaintTrain a LoRA that regenerates a masked region of a video while keeping the rest unchanged, blending the new content with its surroundings.
trainingfal-ai/ltx23-trainer-v2/interpolateTrain a LoRA that generates the video between keyframes — supply first/last (and optional middle) frames at inference and the model fills the in-between motion.
trainingfal-ai/ltx23-trainer-v2/outpaintTrain a LoRA that expands the video frame outward, keeping an inner rectangle fixed and generating the surrounding region.
trainingfal-ai/ltx23-trainer-v2/v2aTrain a LoRA that generates audio (foley / sound design) for a silent video, learning a soundtrack that matches the on-screen action.
trainingfal-ai/ltx23-trainer-v2/v2v-maskedTrain a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.
trainingfal-ai/ltx23-trainer-v2/v2vTrain a LoRA that learns a video-to-video transformation from paired before/after clips, steered at inference by a reference (control) video.
video-to-videofal-ai/ltx-2.3-quality/deblurDeblur high-quality video using LTX-2.3
image-to-imagefal-ai/qwen-image-edit-2509-lora-gallery/shirt-designApply designs/graphics onto people's shirts
image-to-videofal-ai/ai-avatar/multi-textMultiTalk model generates a multi-person conversation video from an image and text inputs. Converts text to speech for each person, generating a realistic conversation scene.
video-to-videofal-ai/ltx-2.3-quality/outpaint/loraOutpaint high-quality video using LTX-2.3 with Lora
text-to-videofal-ai/ltx-2.3-quality/text-to-video/loraGenerate high-quality video with audio from text using LTX-2.3 and custom LoRA
image-to-imagefal-ai/qwen-image-edit-2509-lora-gallery/next-sceneCreate cinematic transitions and scene progressions (camera movements, framing changes)