Search the full model catalog.

Pulls the text out of an image and translates it, using Google's 12B TranslateGemma and a choice of 54 languages. Google reports it beats the original Gemma 3 27B on text (WMT24++), though not on images (Vistra).

Google's largest TranslateGemma model, used here to read the text in a picture and return it in another language. Its card gives it the family's best scores on both text and image translation tests.

TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art translation models and helping foster innovation for everyone.

TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art translation models and helping foster innovation for everyone.

NVIDIA's 600M-parameter English speech-to-text model, with a cache-aware streaming encoder and an RNN-T decoder. On Wiro it takes one recording and returns the transcript as plain text.

TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art translation models and helping foster innovation for everyone.

The undistilled 9B base model of FLUX.2 [klein], for text-to-image and editing with up to 4 reference images, aimed at research and fine-tuning under a non-commercial license.

Undistilled 4B base model of FLUX.2 [klein] for text-to-image and multi-reference editing. Apache 2.0 licensed and built for fine-tuning and research, with more varied outputs than the distilled models.

FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Black Forest Labs' 9B FLUX.2 [klein] model, step-distilled to 4 inference steps, that generates images from text and edits them with up to 4 reference images in a single checkpoint.

Redraws the person in one photo as a realistic baby version of themselves, then turns that baby into a dance video with sound. Eight preset routines are available, Baby Dance and Solo Twist among them.

Animates a still image into a five-second clip with the distilled LTX-2 checkpoint from Lightricks, generating the picture and its soundtrack together, including dialogue written into the prompt.

Transform any character image into a moving video. Provide a reference image and select an video effect.

The lighter Turbo variant of FLUX.2 [dev], Black Forest Labs' 32B open-weight image model. It works from a prompt alone or edits and combines up to 5 reference images.

Transform images into animated videos using the Wan2.2 Animate Replace model. Generate dynamic video content from static reference images and driving videos.

Transform images into animated videos using the Wan2.2 Animate model. Generate smooth video animations from reference images and driving videos.

Turns one image and a speech or song recording into a talking or singing video that runs as long as the audio. It is a LoRA on Wan2.2-S2V-14B, designed for long clips that keep the same face.

Single-speaker text-to-speech from Microsoft Research, built on Qwen2.5-0.5B and designed for streaming text input. It reads scripts of up to about 10 minutes, primarily in English, with 25 preset voices.

Places one portrait in a birthday or zodiac-season scene and writes your caption into the set, such as an age in gold balloons or a sign name as the title, then animates it.

Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning