Search the full model catalog.

Ask questions about a web page: the app reads the URL, retrieves the passages closest to your question and has the LLM you pick answer from them, with optional per-user chat history.

Writes lyrics from your image and sings them in the style of a reference song you upload, following its vocal style, its instrumental feel or both through YuE's in-context learning.

Turns a picture into a finished song: the app writes lyrics about the image, then YuE sings them over an accompaniment in the genre, instruments, mood and voice you pick.

Places the person from one portrait photo into a new scene described by your prompt. Built on ByteDance's InfiniteYou for FLUX.1-dev, using the variant with higher identity similarity.

Generates new images of a person from one face photo and a prompt. Built on ByteDance's InfiniteYou for FLUX.1-dev, with your own FLUX LoRAs applied on top for style.

Sings new lyrics in the style of a song you upload. YuE's in-context mode uses the first 30 seconds of the reference's vocal stem, backing stem or both as the prompt.

Sings your section-labeled lyrics as a track with vocals and accompaniment, using the open YuE models. Required genre, instrument, mood, gender and timbre tags set the style.

Generates instrumental music from a text description with Meta's MusicGen Large. A token budget sets clip length, about 20 seconds at the default, and guidance sets how closely it follows the prompt.

DeepSeek's mixture-of-experts vision-language model, run here as the Tiny checkpoint. Give it one image and a question and it answers in plain text, from a full caption to a one-line note on what looks odd.

Stability AI's 8.1B-parameter MMDiT text-to-image model from the Stable Diffusion 3.5 release, built for 1 megapixel images in styles that range from photography and 3D to painting and line art.

DAMO-NLP-SG's 2B VideoLLaMA 3 model watches a video clip and answers in English text. It skips image patches that stay the same from frame to frame, so static shots use fewer tokens.

The 2B image checkpoint of DAMO-NLP-SG's VideoLLaMA 3 answers questions about a picture in English. Larger images get more vision tokens, which helps with small print in documents and charts.

Describes images and answers questions about them in plain text. It is the image checkpoint of DAMO-NLP-SG's VideoLLaMA 3, with a SigLIP-derived encoder that takes images of varying sizes.

Answers questions about a video clip or describes it in text. DAMO-NLP-SG built it on Qwen2.5-7B with a SigLIP-based vision encoder, and its training centers on image-text data.

Edits an existing image from a written instruction such as "add a beautiful sunset", with no mask to draw. Fine-tuned from Stable Diffusion 1.5 by Tim Brooks, Aleksander Holynski and Alexei A. Efros.

Qwen2.5-14B-Instruct is the 14.7B instruction-tuned model from Alibaba's Qwen2.5 series, built for chat, multilingual writing, coding help and JSON output.

Qwen reports 83.1 on MATH and 74.5 on Arena-Hard for this 32.5B-parameter Qwen2.5 chat model. On Wiro a request holds about 17,000 input tokens, with JSON mode and function calling.

PixArt-Σ consists of pure transformer blocks for latent diffusion: It can directly generate 1024px, 2K and 4K images from text prompts within a single sampling process.

Sana 1.6B adapted by NVIDIA for 2K text-to-image output: images around 2048 × 2048 in BF16, from prompts in English, Chinese, emoji or a mix.

Half-precision (FP16) weights for Sana 1.6B at 1024px. NVIDIA's model pairs a linear diffusion transformer with a Gemma 2 text encoder and a 32x compression autoencoder.