Grad-CAM visualizations for Align before Fuse

The Pastel Model with highres upscale

an implementation of 3.6b Japanese large language model

Super High Quality Depth Maps 🗺️: An End-to-End Tile-Based Framework 🏗️ for High-Resolution Monocular Metric Depth Estimation 🔍📏

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

Create illusions with img2img and masking support

A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team

Fusing Diffusion Paths for Controlled Image Generation

SDXL fine-tuned on paper collages

POC CUDA implementation of an rgb2grayscale function

Creates an SD illusion from drawing + adds depth

Some scrappy experiments 🫣

👻

Generate "algorithmic symphony" one-liners with grammar-constrained CodeLlama

A linear estimator on top of clip to predict the aesthetic quality of pictures

Undi95's Borealis 10.7B Mistral DPO Finetune, GGUF Q5_K_M quantized by Undi95.

LoRA, fp16 Foto-Assisted-Diffusion-FAD_V0

Robust face restoration algorithm for old photos/AI-generated faces - (A40 GPU)

🖼️ Super fast 1.5B Image Captioning/VQA Multimodal LLM (Image-to-Text) 🖋️

SDXL, but faster