Trending

ltx23-trainer-v2/v2a

Train a LoRA that generates audio (foley / sound design) for a silent video, learning a soundtrack that matches the on-screen action.

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.

Maya1 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.

pixverse/v3.5/effects

Generate high quality video clips with different effects using PixVerse v3.5

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

minimax/h3-max/director

Direct continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.

minimax/h3-max/reference-director

Direct a continuous world in real time with image references and text prompts.

OpenAI spec compatible endpoint of Isaac-01 which is a multimodal vision-language model from Perceptron for various vision language tasks.

robbyant/lingbot-world-2

Explore interactive worlds in real time with movement and camera controls.

Real-time games rendered using VAST's Eden Live 14B

Real-time generative rendering from any reference using VAST's Eden Live 14B

Real-time games rendered using VAST's Eden Live 5B

Real-time generative rendering from any reference using VAST's Eden Live 5B

Remixes a generated song or uploaded audio with Mureka 9.5, using complete lyrics and a prompt that controls genre, mood, instrumentation, arrangement, and vocal gender. Accepts source audio from 10 to 480 seconds, including vocal-only, accompaniment-only, and instrumental tracks.

Run inference on LoRA adapters for TRELLIS.2 model

Generate Infographic Image with Sensenova U1

bernini-r/edit-image

Edit any image with a natural-language instruction using Bernini-R, changing the weather, materials, objects, or style while preserving the original composition.

bernini-r/reference-to-video

Turn up to five reference images into one continuous, consistent video with Bernini-R, with smooth, stable camera motion and no scene cuts.

bernini-r/reference-edit-video

Edit a video guided by reference images with Bernini-R, bringing an object, material, background, style, or weather from a reference image into your video.

bernini-r/edit-video

Edit any video with a natural-language instruction using Bernini-R, changing objects, weather, background, or camera angle while keeping the rest of the scene intact.

bernini-r/text-to-video

Generate high-quality video from a text prompt with Bernini-R, ByteDance's unified video generation and editing model.

scene-finder

Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames.

Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.

Foley Control is a video-to-audio model that automatically generates synchronized sound effects for videos, using text prompts to shape the type of sound while matching the timing and action on screen.