Jesse Andrews

I did an initial pass at integrating this: https://github.com/replicate/cog/pull/737

@KianNH - thanks - reading https://blog.cloudflare.com/building-full-stack-with-pages/ it seems like `PagesFunction` is the way to go!

This is still the case - we do not yet support lists/arrays of input: ``` TypeError: Unsupported input type typing.List[float] for parameter `nums`. Supported input types are: str, int, float,...

In discussion with @andreasjansson this morning, it appears the lack of `exclude` capabilities in dockerfile `COPY` will limit complicate the "quick fix" (@bfirsh unless you of any magic we can...

@yorickvP I haven't run this - but the weights are/were base64 datauris inside a json file! this is extremely painful

@RangerMauve are you saying potentially: - we create a `primary` hyperdrive, and add it to our dat-store - and any mounted hyperdrives we add to `primary` would be peered by...

you can use docker to push a local image - `docker push r8.im/user/model`

A simple http server I wrote to test this ``` from http.server import BaseHTTPRequestHandler, HTTPServer import os class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): def _file_path(self): path = os.getcwd() + self.path print(path) return path def...

> - The "large-v2" model is trained for more epochs with regularization and shows improved performance compared to the previous large. > - It has the same architecture as the...

Samples of dreambooth weights in cog-stable-diffusion schedulers: - K_EULER - https://replicate.com/p/tl3etpeouzhttlkad4yyzhcsde - DPMSolverMultistep - https://replicate.com/p/5t43x5ytxfekzovctkmibe2o7i - DDIM - https://replicate.com/p/gdfutv6knnev3oypczoqwx2ixa