imaginAIry
AI
image editing
SHOW HN2023
How HN took it
20 positive, 52 neutral or asking, 3 mixed, 27 critical, out of 102 comments about the project. Thread score -0.06.
Execution: 4 for, 11 againstIdea: 9 for, 5 againstPerformance: 3 for, 2 againstDocs: 0 for, 3 againstDesign: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Easy install and use via pip-style Python package
From 2 comments
Thanks a lot!!! Works perfectly for me (Gentoo Linux + nVidia RTX3060 12GiB VRAM - I installed last week your package and it just worked, experimenting with it since then,…
zepearl on HNWow, it's really impressive to see how advanced AI image generators have become! The ability to create stable diffusion images with a "just works" approach on multiple operating…
88stacks on HN
Selective edits leave parts of images untouched
From 1 comment
This is itself it's own finetuned version of SD so now it won't work with alternative versions. img2img works by just running normal stable diffusion img2img on a noised starting…
bryced on HN
Objections
Needs a CUDA GPU with 11GB VRAM; slow on CPU and Apple Silicon
From 3 comments
What are the most affordable GPUs that will run this? (it said it needs CUDA, min 11GB VRAM, so I guess my relatively puny 4GB 570RX isn't going to cut it!)
GordonS on HNThis is a lot of fun! And they aren't kidding that on a CPU backend it is slooooow :)
tomrod on HNHow to make it use my GPU (I have RTX 3070)? It complains about using sloooow CPU, but I don't see option to switch to GPU, which I think should be sufficient...? I'm running it…
googie on HN
Safety filter blanks nudity silently and is only disabled by undocumented env var
From 1 comment
I am not a fan of software such as this putting in an arbitrarily "safety" feature which can only be disabled via undocumented environment variable. At least make it a flag…
sschueller on HN
Install instructions are confusing
From 1 comment
anyone know how to use this? kind of confusing install instructions in the readme
kewp on HN
Results are inconsistent; faces get distorted
From 2 comments
Thanks a lot!!! Works perfectly for me (Gentoo Linux + nVidia RTX3060 12GiB VRAM - I installed last week your package and it just worked, experimenting with it since then,…
zepearl on HNYes if you're not careful it can ruin the face. You can play with the strength factor to see if something can be worked out. Bigger faces are safer.
bryced on HN
Requests
Web UI or GUI
From 1 comment
Wow that's really impressive (I've seen similar things in research papers for a while now, but having it usable so easily and generic is great). A few questions: - would it be…
goffi on HN
Lower VRAM requirements
From 1 comment
>11GB VRAM Aaarrrgghh let me know when it's down to 4GB like Stable Diffusion The prompt-based masking sounds incredible, with either pixel +/- or Prompt Relevance +/- VERY…
nullish_signal on HN
Pre-download models for Docker caching
From 1 comment
Is there a way to pre-download all models? I want to create a docker image and cache the models.
searchableguy on HN
Integration into automatic1111 webUI
From 1 comment
Hoping that this is quickly implemented into the automatic1111 webUI.
Der_Einzige on HN
Questions
Can it run on a GPU cloud VM or Colab
From 2 comments
How can I try this? Can this be run on a Digitalocean VM? I looked around on DO's products, but none seems to advertise that it has a GPU. So maybe it is not possible?
TekMol on HNHere is a google colab you can try it in: https://colab.research.google.com/drive/1rOvQNs0Cmn_yU1bKWjCOHzGVDgZkaTtO?usp=sharing
bryced on HN
Why models re-download on each prompt
From 2 comments
How does this work? When I run it on a machine with a GPU (pytorch, CUDA etc installed) I still see it downloading files for each prompt. Is the image being generated on the…
perfopt on HNI keep seeing this even when the prompt is unchanged Downloading…
perfopt on HN
Alternatives named
InvokeAI
From 1 comment
The headline and the heavy promotional verbiage on the site seems to be claiming this is some new functionality we didn’t have before. Image2image with text instructions isn’t…
natch on HN
Instruct pix2pix web demo
From 1 comment
A similar tool: Instruct pix2pix to alter images by describing the changes required: https://huggingface.co/timbrooks/instruct-pix2pix#example Edit: Just noticed it is the same…
Gravyness on HN
Automatic1111 webUI
From 1 comment
Hoping that this is quickly implemented into the automatic1111 webUI.
Der_Einzige on HN