Downloads · 30 days
0
SirVeggie/Aeolian
Aeolian is a machine learning model from SirVeggie. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as creativeml-openrail-m.
Original artist: WLOP\ Patreon: https://www.patreon.com/wlop/posts
Downloads · 30 days
0
Access
Public
Updated Oct 29, 2022
Repo size
8.5 GB
Likes
4
Public
Click a slice to open those files.
.ckpt8.5 GB · 100%
From the Hugging Face model README
Original artist: WLOP
Patreon: https://www.patreon.com/wlop/posts
An original character created and drawn by WLOP for his webcomic Ghostblade.
Token and Class words are what guide the AI to produce images similar to the trained style/object/character. Include any mix of these words in the prompt to produce verying results, or exclude them to have a less pronounced effect. There is usually at least a slight stylistic effect even without the words, but it is recommended to include at least one. Adding token word/phrase class word/phrase at the start of the prompt in that order produces results most similar to the trained concept, but they can be included elsewhere as well. Some models produce better results when not including all token/class words.
3k models are are more flexible, while 5k models produce images closer to the trained concept. I recommend 2k/3k models for normal use, and 5k/6k models for model merging and use without token/class words. However it can be also very prompt specific. I highly recommend self-experimentation.
Aeolian and aeolian_3000 are quite similar with slight differences.
Epoch 5 and 6 versions were earlier in the waifu diffusion 1.3 training process, so it is easier to produce more varied, non anime, results.
token: m_aeolian
class: §¶•
base: waifu diffusion 1.2-e5
notes: 2020 step training
token: m_aeolian
class: §¶•
base: waifu diffusion 1.2-e6
notes: 3000 step training
token: m_concept
class: §
base: waifu diffusion 1.3
notes: 1.3 model, which may give some benefits over 1.2-e5
This embedding is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: