This is a merge of a curated set of checkpoints to incorporate data that's been trained onto the Pony v6 checkpoint.
The specific merge technique used aims to maintain as many strengths of each merged model while minimizing conflict and "drowning" from tension between them. This is a custom technique I have developed.
Description
FAQ
Comments (8)
Including your prompts in your sample images would be helpful
I will start doing so; I generate the image with my own inference code and haven't implemented adding generation information to the exif yet; it's on my list.
In the meanwhile you can have a look at: https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/04b810c0-e321-49ea-b5e5-a4f8d19dd079/original=true/a.jpeg
@epiTune It is not good to show samples produced by inaccessible tooling.
If your script have weights balancing technique different from A1111 WebUI method, then results will be significantly different. For example, in ComfyUI results had much lower quality before using the A1111 weighting.
@homoludens I do generation using the huggingface diffusers library which I consider to be the industry standard for generation and it's what I consider the most sensible to target to guarantee good coverage across all possible tools.
One of the best models in my collection, thank you!
So fun to hear! Thank you
Agree! This is a great model a favorite of mine!!
Interesting model. It does a lot of things well in a good semi cartoon style. i run over it with a photoreal model to inject details into hair and skin and so forth. its always one of my go tos to check if it can do a prompt
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.