Model Card for Model ID
This LoRA model generates the cute yellow slime that was familiar in Android devices.
Model Details
This is LoRA-C3Lier (with conv2d-3x3). Activation word is blob
.
There are epoch-80 model with some flexibility in prompting and epoch-160 model that are somewhat over-fitted. If you use the epoch-160 model, reduce the weights to about 0.7
when applying.
The model was trained on a 192*192 pixel image, it is better to generate with a similar size for icon-like images. Normal images may break down if they are too large.
The base model is ACertainty: https://huggingface.co/JosephusCheung/ACertainty
This LoRA was trained on the following blobmoji font (ASL 2.0) images: https://github.com/C1710/blobmoji
Total 267 images are used for 89 different images, each with a white, black, or gray background. The prompts are blob
and Unicode CLDR Short Name and Keywords (e.g., blob, grinning face, black background, face, grin, grinning face
).
It is trained by sd-scripts
, network_dim=4, alpha=1, conv_div=4, conv_alpha=1, unet only
. See model metadata for details.
Examples
All images are generated with ACertainty, cherrypicked.
epoch 80, weight 1.0
blob, grinning face, gray background, face, grin, grinning face
seed : 338444264
sampler: k_euler_a
steps : 40
scale : 7.5
blob, climbing mountain
seed : 136505587
sampler: k_euler_a
steps : 40
scale : 7.5
epoch 160, weight 0.7
blob, smiling, with cat ears, white background, face, smiling, smiling face
seed : 1461364854
sampler: k_euler_a
steps : 40
scale : 7.5
1girl holding blob, at street
seed : 946785248
sampler: k_euler_a
steps : 40
scale : 7.5
blob running in akihabara
seed : 1181241943
sampler: k_euler_a
steps : 40
scale : 7.5