cuuupid / idm-vton
Best-in-class clothing virtual try on in the wild (non-commercial use only)
cuuupid / research
Deep Research ported to Cog!
cuuupid / mel-medarda-tts
TTS with the voice of Mel Medarda from Arcane, trained using Zonos-v0.1
cuuupid / zonos
Zonos-v0.1 beta, a SOTA text-to-speech Transformer model with extraordinary expressive range, built by Zyphra.
cuuupid / markitdown
Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.
cuuupid / qwen2-vl-2b
SOTA open-source model for chatting with videos and the newest model in the Qwen family
cuuupid / cogvideox-5b
Generate high quality videos from a prompt
cuuupid / flux-lineart
Flux finetuned for black and white line art.
cuuupid / gte-qwen2-7b-instruct
Embed text with Qwen2-7b-Instruct
cuuupid / whisper-webrtc
Talk to an AI "friend" with ultra low latency over WebRTC
cuuupid / glm-4v-9b
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.
cuuupid / sdxl-lineart
SDXL finetuned on line art
cuuupid / garden-state-llama
Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!
cuuupid / golden-gate-llama
An example using Garden State Llama to ReFT on the Golden Gate bridge.
cuuupid / e5-mistral-7b-instruct
Finetuned E5 embeddings for instruct based on Mistral.
cuuupid / sdxl-meow
make meow emojis!
cuuupid / marker
Convert scanned or electronic documents to markdown, very very very fast
cuuupid / seamless_expressive
Translate audio while keeping the original style, pronunciation and tone of your original audio.
cuuupid / minicpm-llama3-v-2.5
MiniCPM LLama3-V 2.5, a new SOTA open-source VLM that surpasses GPT-4V-1106 and Phi-128k on a number of benchmarks.