PJ Gray

When using higher rate rates (or lower frame rates on older devices), the number of frames "in flight" goes up, thus using more memory. Probably need some sort of memory...

Is result needed in Pinecone metadata?

3

I have ported BabyAGI to swift, and had a question about how context is used. (So this is more a discussion point, not an issue) It seems that the context...

My python skills are just not strong enough...anyone have any idea how (or if) ControlNet could be integrated into the CoreML conversion process? https://github.com/lllyasviel/ControlNet#controlnet-with-canny-edge

image2image trace traps on generateImages with 320x512 model

3

I converted a model using: ``` python -m python_coreml_stable_diffusion.torch2coreml --convert-unet --convert-text-encoder --convert-vae-decoder --convert-vae-encoder --convert-safety-checker --bundle-resources-for-swift-cli --latent-w 40 --latent-h 64 --attention-implementation ORIGINAL --model-version stabilityai/stable-diffusion-2-base -o model_output ``` That should give me...

.all vs .cpuAndNeuralEngine?

4

I was assuming that "all" for compute units would choose the best one for your setup, but I tried cpuAndNeuralEngine and got better performance. What's happening here? What does "all"...

In the Stable Diffusion v2 repo, it says: "To augment the well-established [img2img](https://github.com/CompVis/stable-diffusion#image-modification-with-stable-diffusion) functionality of Stable Diffusion, we provide a shape-preserving stable diffusion model." With the current pull request(s) for...

Be able to open to webpage from action menu

2

Currently I think it only uses the image (for saving or sharing) but I want a "view in safari", especially for lower Rez images.

Add MET museum provider

1

http://www.metmuseum.org/research/image-resources/frequently-asked-questions

Digital commonwealth.org has a bunch of images not anywhere else. I thought most were on the BPL Flickr or DPLA but apparently not. A good search to verify this is...