Replicate Models

Jev-Omni (#1 on Image JevBench v0.1): ask a typed yes/no or multiple-choice question about an image, get a calibrated probability per option from one forward pass. Pinned akhilaaa3/Jev-Omni revision, Apache-2.0.

FLUX 3 is Black Forest Labs' text-to-image and image-editing model. Generate images from a prompt, or edit with up to 10 reference images.

Generate and edit images with Ideogram 4.5, the latest for precise image generation.

Precisely edit source images with Ideogram 4.5.

Adds punctuation to text

A unified omni-modal model that can simultaneously receive inputs such as images, audio, text, and video and directly generate coherent text and speech

Photos on Polaroid, including hands holding Polaroid photos

SDXL trained on a variety of spectrograms

SDXL trained on photographs from Victorian-era Britain

SDXL fine-tuned on film noir movie stills

SDXL fine-tuned on Soviet propaganda posters

Typed answers about an image, read from unchanged Qwen3-VL-4B logits in one forward pass.

Predicts virality of short videos using a Meta TRIBE v2 brain-encoding model

Sing any song in any voice. Give a song + a short voice clip and get the song re-sung in that voice, with the original music kept intact. Zero-shot, no training. Works in any language - English, Spanish, French, Italian, Hindi, and more.

Detect NSFW content in sampled video frames with adjustable sensitivity, per-frame scores, and optional screenshots.

Grounding DINO: zero-shot text-prompted object detection (SwinT-OGC). H100 build.

Pruna's highest-quality video model. Generate video from text or images with speed and quality modes, first- and last-frame control, and durations up to 15 seconds.

Generate editable SVG graphics from text prompts with Quiver's Arrow 1.1 model. Great for icons, logos, and illustrations.

Ultralytics YOLO26 instance segmentation (COCO-Seg), selectable size n/s/m/l/x.

Vietnamese F5-TTS. Released by EraX-AI team

OpenAI's fastest model for high-quality, everyday image generation. Generate and edit images from text and image inputs with strong instruction following and sharp text rendering.

OpenAI's most capable image model, built for workflows where editing precision matters most. Generate and edit images from text and image inputs with strong instruction following, sharp text rendering, and detailed control.