Pheme generates a variety of conversational voices in 16 kHz for phone-call applications

image to image style transfer using STROTSS loss

SDXL LoRA finetuned on Vermeer paintings

DreamBooth safetensors model use RealVisXL

A latent text-to-image diffusion model capable of generating photo-realistic images given any text input

Morphs vector paths towards a text prompt

A model for testing pydantic cog that yields images one word at a time.

Multi-stage text-to-video generation

ControlNet Line Art Anime

Lightweight multimodal model for visual question answering, reasoning and captioning

Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation

Mediapipe Blendshape Labeler - Predicts the blend shapes of an image.

A Vision-Language Model with An Ensemble of Experts

Detects protein in DAB image

Real-ESRGAN for image upscaling on an A100

Upscale images with the latent diffusion superresolution model

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Diffusion-based semantic image editing with mask guidance

Turn two prompts into one image

Paintings in the style of selected artists with weights, from the Construction Series of GymDreams8.