Clay Mullis

clip-guided-diffusion. A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

glide-finetune. Finetune glide-text2im from openai on your own data.

pyglide. A CLI tool for using GLIDE to generate images from text.

retrieval-augmented-diffusion. Retrieval augmented diffusion from CompVis.

laionide. checkpoints for glide finetuned on laion and other datasets. wip.

latent-diffusion-deepspeed. Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)

dalle-pytorch-datasets. Python

pyglide-replicate. Code for https://replicate.com/afiaka87/pyglide

lstein-stable-diffusion. This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements.

dalle-pytorch-pretrained. Pretrained checkpoints from training with DALLE-pytorch

hkss-mods. A collection of info display mods for Hollow Knight: Silksong using BepInEx framework.

DALLE-models. Here is a collection of checkpoints for DALLE-pytorch models, from where you can keep on training or start generating images.

dalle-pytorch. Text to Image Transformer in Pytorch

cog-stable-diffusion. Diffusers Stable Diffusion as a Cog model

pretrained-dataset. Store vectors from a backbone model in advance, load them as needed during training.

ZeroShotTransform. Python

Diff-DALLE. Python

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

glid-3-xl. 1.4B latent diffusion model fine tuning

VQGAN-CLIP. Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

cloob. Python

CodeGen. CodeGen is an open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

clipseg. Python

mobius. A discord bot by/for Clay. Currently a work-in-progress. Not really meant for public consumption.

deep-daze. Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network)

guided-diffusion. Python

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

stylegan-v. Source code for StyleGAN-V

taming-transformers. Jupyter Notebook

poll-bbox-notify-discord. This Python script monitors a specified URL for WebRTC streaming activity and sends notifications to a Discord channel when the streaming status changes.

ldm-finetune. A soft fork of ldm-finetune with new features.

ds-macro. A rudimentary macro input system for Death Stranding in Python.

Augmented_CLIP. Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.

DALLE-datasets. This is a summary of easily available datasets for generalized DALLE-pytorch training.

glid-3. combination of OpenAI GLIDE and Latent Diffusion