cog-stable-diffusion VS stable-diffusion

Stable Diffusion

stable-diffusion: A latent text-to-image diffusion model capable of generating photorealistic images given any text input

Next, make a Flask app so your app can receive the inbound text message to your Twilio phone number. That string is then passed to Replicate 's stable diffusion model to generate photo-realistic images given that prompt.

The Azure Function App executes a serverless function that: a) Runs the text summary model (Azure Cognitive Service for Language) b) Runs the image generation model (stable-diffusion on Replicate AI) c) Uploads the image to Azure Blob Storage

I'm testing prompts online because it's faster than my computer: https://replicate.com/stability-ai/stable-diffusion

There isn't a direct integration with Zapier, but you can use the Webhooks & API calls within Zapier to connect to Stable diffusion. The simplest way is to do it through Replicate: https://replicate.com/stability-ai/stable-diffusion

I ended up using stable diffusion from replicate. They don't have a filter on the input text, they just analyse the output for NSWF and block it if it seems to be NSFW. So sometimes NSWF-ish pictures may slip through.

I'm getting same-ish results as mine with replicate. They don't have PLMS as an option and euler trips that silly porn filter on the dressed pirates for whatever reason, but it seems to closely match.

Stable Diffusion: It is based on a kind of diffusion model called a latent diffusion model, which is trained to remove noise from images in an iterative process. It is one of the first text-to-image models that can run on consumer hardware and has its code and model weights publicly available.

Which is a 1-click install of Stable Diffusion with an alternative web interface. You can choose a different approach but this one is pretty simple and I am new to this stuff.

an invisible watermarking of the outputs, to help viewers identify the images as machine-generated.

It sounds like you just want to set up Stable Diffusion to run locally. I don't think your computer's specs will be able to do it. You need a graphics card with a decent amount of VRAM. Stable diffusion is in Python as is almost every AI open source project I've seen. If you can get your hands on a system with an Nvidia RTX card with as much VRAM as possible, you're in business. I have an RTX 3060 with 12 gigs of VRAM and I can run stable diffusion and a whole variety of open source LLMs as well as other projects like face swap, Roop, tortoise TTS, sadtalker, etc...

Use specific GPU on multi GPU systems · Issue #87 · CompVis/stable-diffusion · GitHub

I dealt with this in one of my posts. At least SD 1.1 till 1.5 are all trained on a batch size of 2048. The version pretty much everyone uses (1.5) is first pretrained at a resolution of 256x256 for 237K steps on laion2B-en, at the end of those training steps it will have seen roughly 500M images in laion2B-en. After that it is pre-trained for 194K steps on laion-high-resolution at a resolution of 512x512, which is a subset of 170M images from laion5B. Finally it is trained for 1.110K steps on LAION aesthetic v2 5+. This is easily verified by taking a glance at the model card of SD 1.5. Though that one doesn't specify for part of the training exactly which aesthetic set was used for part of the training, for that you have to look at the CompVis github repo. Thus at the end of it all both the most recent images and the majority of images will have come from LAION aesthetic v2 5+ (seeing every image approx 4 times). Realistically a lot of the weights obtained from pretraining on 2B will have been lost, and only provided a good starting point for the weights.

stable diffusion · CompVis/stable-diffusion@2ff270f · GitHub