decart/lucy-5b/image-to-video

Lucy-5B is a model that can create 5-second I2V videos in under 5 seconds, achieving >1x RTF end-to-end

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

flux-krea-lora/stream

Super 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.

flux-lora/stream

Super 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.

ideogram/custom-models

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

ltx-2-19b/distilled/extend-video/lora

Extend videos with audio using LTX-2 Distilled and custom LoRA

ltx-2-19b/distilled/video-to-video

Generate video with audio from videos using LTX-2 Distilled

ltx-2-19b/distilled/video-to-video/lora

Generate video with audio from videos using LTX-2 Distilled and custom LoRA

ltx-2-19b/extend-video/lora

Extend video with audio using LTX-2 and custom LoRA

ltx-2-19b/video-to-video/lora

Generate video with audio from videos using LTX-2 and custom LoRA

ltx-2.3-quality/cross-eyed

Cross-eyes for high-quality video using LTX-2.3

ltx23-trainer-v2/a2a

Train a LoRA that transforms one audio clip into another, learning a reference→target mapping from paired audio examples.

ltx23-trainer-v2/audio-extend-prefix

Train a LoRA that continues an audio clip forward in time, generating the audio that follows a short clean prefix.

ltx23-trainer-v2/audio-extend-suffix

Train a LoRA that generates the lead-in to an audio clip, extending audio backward in time from its ending.

ltx23-trainer-v2/audio-inpaint

Train a LoRA that regenerates masked time spans of an audio clip while keeping the rest unchanged.

ltx23-trainer-v2/av2av

Train a LoRA for a joint audio+video transformation, conditioned on a reference clip (its video and audio) to produce a matching target clip.

ltx23-trainer-v2/av2av-masked

Train a LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.

ltx23-trainer-v2/extend-prefix

Train a LoRA that continues a video forward in time — supply an opening clip at inference and the model generates what comes next.

ltx23-trainer-v2/extend-suffix

Train a LoRA that generates the lead-in to a video, extending a clip backward in time from its ending.

ltx23-trainer-v2/ic-lora/a2a

Train an IC-LoRA that transforms one audio clip into another, conditioned at inference on a reference audio clip.

ltx23-trainer-v2/ic-lora/av2av

Train an IC-LoRA for a joint audio+video transformation, conditioned on a reference clip's video and audio to produce a matching target.

ltx23-trainer-v2/ic-lora/av2av-masked

Train 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.

ltx23-trainer-v2/ic-lora/v2v-masked

Train an IC-LoRA that regenerates only the masked region of a video, guided by the kept pixels and a separate reference/control video.

ltx23-trainer-v2/interpolate

Train 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.

ltx23-trainer-v2/v2v-masked

Train a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.

PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.

Turn photos into mind-blowing, dynamic videos. Your images can can come to life with sharp details, impressive character control and cinematic camera moves.

Turbo is the model to use when you feel the need for speed. Turn your image to stunning video up to 3x faster – all with high quality outputs.