fastai lesson 1 - bird or forest

experimental model - plz don't use

explore how COG_WEIGHTS works

explore img2img zooming sdxl

SD1.5 and OpenAI's Consistency Decoder

Batch mode for text & image embeddings

stream previews as it is generated

Zeroscope V2 XL & 576w

controlnet_v11p_sd15_inpainting demo

batch inference for dreambooth trainings

draft version of temporalnet v2

this should be same as multi-control but testing different inputs

All the original Controlnets & QR

automatic1111 running on replicate

December 2022 version of dreambooth template

this is a proof of concept for dreambooth that uses tar weights

this is where I test new dreambooths

Template Version for use with Dreambooth API

Template Version for use with Dreambooth API of txt2img & img2img

Template Version for use with Dreambooth API

Template Version for use with Dreambooth API of ControlNet OpenPose

Template Version for use with Dreambooth API

Template Version for use with Dreambooth API

Template Version for use with Dreambooth API

Template Version for use with Dreambooth API of ControlNet Depth

import of deliberate v2

Template Version for use with Dreambooth API of ControlNet Scribble

imports weights into format that works with diffusers

build & push a new replicate cog model, adding zip files to existing image

Compile Stable Diffusion using AIT for A100

BigCode / SantaCoder - 1.1B parameter models trained on the Python, Java, and JavaScript

bfirshbooth trained with Stable Diffusion 2.1

Testing dreambooth 2.1 training - WIP

preview release of Dreambooth supporting Stable Diffusion 2.1

blank stable diffusion

Stable Diffusion 2.0 Preview

mediapipe facial landmark detection demo by Marlene Mhangami

test of replicate.com/openai/whisper updated with more recent ubuntu/cudann