ad astra per asperga 
(added colab instructions)
Colab:
-
Open automatic1111's colab: https://colab.research.google.com/drive/1Iy-xW9t1-OQWhb0hNxueGij8phCyluOh
-
Replace this cell:
#@title Normal 1.4 model
# get a token from https://huggingface.co/settings/tokens
user_token = "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" #@param {type:"string"}
user_header = f"\"Authorization: Bearer {user_token}\""
!wget --header={user_header} https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt -O model.ckpt
With:
!apt install megatools
!megadl "https://mega.co.nz/#!FxclSKoL!EFSM4nLlXMuOvBLkoZNmtOH4Y8oycjrU7h2Hn6mKl1k"
-
Run (it'll take a few minutes to download)
-
Refer to Marsey as
a sks catin your prompt.a photo of a sks cat as a gardeneretc
Download the weights: https://models.rdra.ma/
Development on Stable Diffusion has been happening at a wild pace, and there's already written a working implementation of DreamBooth for it. Whereas Textual Inversion refines your prompt, DreamBooth is able to finetune the model itself to teach it new concepts. I did one run with 87 Marseys and another with just 3 upscaled ones. So far the upscaled run (u1000.ckpt) is looking best.
See the Textual Inversion posts for a comparison with that. DreamBooth is far better at keeping her colors consistent and producing recognizable images. Decent results were something like 1 in 50 before, now they're nearly every image.
a photo of Marsey
a photo of a spaceman Marsey in outer space
a photo of Marsey as a gardener
I love that it creates real Marseys too 
a photo of Marsey running away from a dinosaur
Missing the 
. Might be overfitting and improve with better regularization in DreamBooth.
a photo of Marsey cooking in the kitchen
These models also work with Deforum to create animations:
There's still plenty of low-hanging fruit to suggest these will get better quickly - the DreamBooth repo doesn't do regularization correctly, and we'll get a free bump in quality when SDv1.5 is released. The plague of AIposting continues
Jump in the discussion.
No email address required.
comparison of characters and styles in different marsey attempts. "sks cat" is dreambooth version, "fmarsey" is float-trip's original, "smarsey2" is my (shit) attempt at using textual-inversion
smaller model: https://mega.nz/file/AWsDGIAC#3EXe-ChMJaIBOlale2--ld6usX55Q9H6iqLVnRHlvNA
Jump in the discussion.
No email address required.
version that has what the originals would look like unmodified by style
comparison of holding a sword
Jump in the discussion.
No email address required.
Comparison of CFG scales
lol she be gooning with friends
Jump in the discussion.
No email address required.
horny marsey
Jump in the discussion.
No email address required.
porn
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
[row] marsey holding [column]
Jump in the discussion.
No email address required.
More options
Context
More options
Context
textual inversion is no good with this. I just trained embeddings off of the new model here - https://models.rdra.ma/embeddings/
elephant in the style of *(old model/embeddings)elephant in the style of *(new model/embeddings)could be related to this: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion/issues/15
at some point it might be worth commissioning Marsey in 3-5 more standard poses for the AI to learn from. a few issues (like her tail) seem to stem from the dataset
Jump in the discussion.
No email address required.
More options
Context
More options
Context