Translate audio while keeping the original style, pronunciation and tone of your original audio.
Best-in-class clothing virtual try on in the wild (non-commercial use only)
Embed text with Qwen2-7b-Instruct
GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.
Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.
Convert scanned or electronic documents to markdown, very very very fast
Generate high quality videos from a prompt
Flux finetuned for black and white line art.
SDXL finetuned on line art
SOTA open-source model for chatting with videos and the newest model in the Qwen family
F5-TTS, a new state-of-the-art in open source voice cloning
Zonos-v0.1 beta, a SOTA text-to-speech Transformer model with extraordinary expressive range, built by Zyphra.
Finetuned E5 embeddings for instruct based on Mistral.
MiniCPM LLama3-V 2.5, a new SOTA open-source VLM that surpasses GPT-4V-1106 and Phi-128k on a number of benchmarks.
Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!
make meow emojis!
An example using Garden State Llama to ReFT on the Golden Gate bridge.