MARS5, a fully open-source (commercially usable) voice-cloning/TTS with break-through prosody and realism.

Domain Consistent Resolution Adapter for Diffusion Models: generating consistent images with resolutions outside of their trained domain

PyTorch implementation of AnimeGAN for fast photo animation

Generate a new image given any input text with Babes 2.0

SDXL finetuned to desi truck art style

remove background for retailer product images

Turns 10 mp4 into 1

a fine-tuned model to detect dragon in images.

# Interior Decoration Space Scaling - First Use Case

Exploring the training and use of DreamBooth, with Bart as a subject

Personalized Image Animator

Model trained on african images from the Official account of Maurice "Pellosh" Bidilou, the thematic is "Photography in the Congo in the 70s".

Generate images from a text prompt

The first Rust-powered model on Replicate.

Honeycomb NLQ Generator hosted with vLLM + AWQ Quantized

All the original Controlnets & QR

Whisper transcription plus speaker diarization

Mixtral-8x22b-v0.1-4bit

Meina Mix V11 Model (Text2Img, Img2Img and Inpainting)

Monitoring Crop Growth Using A.I.