cog-stable-diffusion VS plunkylib

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.

If the chat approach annoys you, you can use libraries like plunkylib which uses more convenient yaml and text files syntax for coordinating the queries. Langchain is another great library that can help abstract that away for you as well.

Really cool! Similarly, you can use https://github.com/Mattie/plunkylib in CLI mode as well (or notebook). Storing your prompts in reusable/expandable text files.

FWIW, I made a Python library that at least helps you iterate on language parameters and prompts using yaml/flat text rather than hard-coding all that. Nothing special, but it's great if you do a lot of adjusting of prompts/parameters for lots of different uses (and for different engines). https://github.com/Mattie/plunkylib Definitely great to use for bots/engines (as I use it for a number already).

Rather than hardcode your params/tokens/prompts, I have a library called plunkylib that makes it easier to define all of that in txt/yaml files so you can mix/match/adjust them easier than changing the code itself. Was noticing things like your summary prompt and some others are in the code-- might be better to have it in parameterized external files.

I released a library called Plunkylib which lets you use text files more comfortably for working with the API and you may find it more pleasant to work with or build your own interactive use cases.