Our great sponsors
-
stable-diffusion-webui
Discontinued Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui] (by sd-webui)
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
stable-diffusion
Discontinued This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI] (by lstein)
Hi. Looking good, but you definitely need to add grids. Like setting a batch size (number of imgs to generate simoultaneously, "columns") and a batch count ("rows") to get a NxM grid as output. And, of course, ability to bulk schedule those grids, like 10 grids with 5(simoul imgs)x5(rows) -> start. And you might as well want to implement some features from AUTOMATIC1111 web gui, like Prompt matrix, Attention (and better - prompt weights), X/Y plots etc.
Also, I've not explored any of the batch stuff for stable-diffusion-webui yet, so perhaps this already exists.
I've been using this fork of the CompVis repo. It is CLI based, and tt logs reproduction steps for each image to a file next to the images. It's awesome for going back to last week + tweaking stuff.
I just setup the webui from AUTOMATIC1111 and am liking some of the config options they offer, too. Namely, writing options out alongside every image that's saved:
Related posts
- Einsum in 40 Lines of Python
- Show HN: Free GitHub Copilot CLI with your own model or API
- Show HN: Cognita – open-source RAG framework for modular applications
- Show HN: Data Bonsai: a Python package to clean your data with LLMs
- Ask HN: Seeking On-Premises Website Examples for Uptime Comparison Experiment