This hypernetwork was trained on Anything-V3.0-pruned-fp32 [1a7df6b8] at a res of 512x768. The training dataset included primarily NSFW images and so the model leans heavily toward that type of content. All of the versions were trained at their respective listed training steps and a learning rate of 0.00005. I personally like the results from v1-16000 the best.
For best results please use with the bad-artist embedding.
Recommended keywords: meru, merunyaa, black hair, demon girl, demon tail, freckles, horns, mole, pointy ears, red skin, orange eyes
Recomended negative keywords: multiple moles, multiple horns, glasses, mole on breast, multiple tails
Please download the attached keyword list for additional training keywords.
I'd love to see what people who are better at prompting than me can produce with this! Please post your beautiful creations! Post a comment if you have a recommendation for a character I should train next.
Description
FAQ
Comments (5)
fricking yes! I tried making a gradient but it didnt really work, ty!
Thank you, been trying to find something like this for a shadowrun character but had almost given up hope. Will say its a bit hit or miss on getting a red skin tone
looks amazing, but I can not use in my google colab :c, all the embeddings of 5 megas or more not work here, only the small embeddings of 1 mega or less maybe. Please do a light version :D
Hi i'm getting this error, can you help?
Error loading embedding meruTheSuccubus_v116000.pt
line 206, in load_from_dir
self.load_from_file(fullfn, fn)
line 178, in load_from_file
raise Exception
Exception: Couldn't identify meruTheSuccubus_v116000.pt as neither textual inversion embedding nor diffuser concept.
I'm not getting anything that looks like Meru. I don't know what I'm doing wrong. Does the training data have to go somewhere? Am I using the wrong model? I went and got the anythingv3 model you used(i think its the same) but its not working. Any help would be nice
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.