Do not download if your workflow relies primarily on LoRAs.
If you appreciate the model, leave a thumbs-up. Models with consistently poor appreciation-to-download ratios are removed to keep the space focused. You decide in which direction the development goes.
Highly prompt-sensitive models intended for specialized creative use cases rather than general-purpose generation. Proper prompting is essential for good results.
A low CFG is strongly recommended. Negative prompts and embeddings are usually less important, as crucial parts of that behavior are already merged into the models.
This package contains several distinct models with different intended applications rather than direct variations of one another. The goal is to explore different visual capabilities, aesthetics, and workflows. Community feedback helps determine what works reliably and what still needs refinement.
Nothing groundbreaking, and probably far too late to the SD party. SD1.5 is slowly fading out, so this may become obsolete sooner rather than later.
Description
Low CFG
FAQ
Comments (13)
SD 1.5 is so lightweight I think it has other functions that are worth developing. Thanks for this model.
Thanks!
I agree. I can get a uniqueness in 1.5 that I can't achieve in newer models.
OK - I apologize for my wrong assumption and appreatiate your reaction.
SD 1.5 is the only model i can reasonably run on cpu. im glad people are still making new versions!
@cogn Here you are supported!
@cogn This is definitely the best reason , people can get there toes in with this kind of tool . With the last "AI everything tax" , a low dram / low vram option is always welcome ! https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file
I would like to point out that the era of offline image generation has begun on mobile phones, and with the help of Local Dream, SD 1.5 models can be used on NPUs. So SD 1.5 is far from over.
@mykeehu O.K. I see I'm far from being anywhere near this evolutionary step - what does this mean?
@_CreAi_ All I can say is that it is now possible to generate images on mobile phones, but for the time being, this is only possible with SD 1.5, so it is still worth training the current models. At least until a solution is found for SDXL-based models (or more powerful phones become available, but that will take a few more years).