Colorful
Type | |
Downloads | 8,434 |
Last Update | Mar 24, 2023 |
Versions | 8 |
Base Model | SD 1.5 |
Tags |
Versatile model with a high variety of styles
Thank you so much for the feedback and examples of your work! It's very motivating.
Do you like what I do? Feel free to buy me a coffee ☕
Model Advantages
- Colorful
- Creative
- Understands simple requests
- Complex details
- Open license
Versions
Rating | (5) |
Downloads | 2,711 |
Uploaded | Mar 13, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 71B5EA121F |
more shadows/details
Rating | (4) |
Downloads | 2,485 |
Uploaded | Mar 02, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 F0407EAF51 |
Added photorealism, with no loss of artistry
Rating | (2) |
Downloads | 892 |
Uploaded | Feb 20, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 00CAF369A7 |
Mixed with https://huggingface.co/thiros/YuzuLemonTea
Script is here: https://github.com/recoilme/losslessmix/
The anime models are very dark, so I mixed with the colorful_v1.4, start from simple mix with some share (0.5 or 0.7, don't remember): result
And mix result with different share about 10 times, before anime was converted to semi - real.
python3 weightedsim.py colorful_v14.ckpt yuzulemonmilk.ckpt --s .77
python3 weightedsim.py colorful_v14.ckpt merged-0.77.ckpt --s .76
python3 weightedsim.py colorful_v14.ckpt merged-0.76.ckpt --s .75
#After that i mix again with good old, not anime models like unstableinkdream
python3 weightedsim.py colorful_sr.ckpt unstableinkdream.ckpt --out ttt
Rating | (1) |
Downloads | 276 |
Uploaded | Feb 19, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 AFDCB0E1DA |
new merging algorithm:
https://github.com/recoilme/losslessmix
Please stop asking me how to run this and how to work with it
this models was removed:
portrait.ckpt
izumi.ckpt
vintedois.ckpt
unreal.ckpt
hunter69.ckpt
analog.ckpt
wavyfusion.ckpt
uberRealisticPornMerge.ckpt
has3dkx.ckpt
Rating | (0) |
Downloads | 1,065 |
Uploaded | Feb 14, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 AA62F827F6 |
Mixed with brilliant unstableinkdream
Rating | (0) |
Downloads | 299 |
Uploaded | Feb 13, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 5CC4878492 |
Agorithm: losslessmix
Rating | (2) |
Downloads | 431 |
Uploaded | Feb 09, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 BDC102DD59 |
Completely redesigned. New unique mixing algorithm. All parts with free license, merged with script:
python3 merge3_mindiff.py a.ckpt c_openj.ckpt d_f222.ckpt --out tst
models:
a_stable_diffusion.ckpt
c_openjourney.ckpt
d_f222.ckpt
h_eimisanime.ckpt
i_portrait.ckpt
m_vintedois.ckpt
q_unreal.ckpt
r_hunter69.ckpt
u_wstanding.ckpt
y_rpg.ckpt
t_analog.ckpt
x_uberRealisticPornMerge.ckpt
Rating | (1) |
Downloads | 272 |
Uploaded | Feb 07, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 7C21351886 |
first release
I wanted to create something new. First of all, I blended five or so inconsistent models like anime with 3D, etc. using custom blending algorithms (minmax & maxdiff). It doesn't make any mathematical sense. The result is an absolute trash, with unpredictable results, but bright and acidic
After that, I tried to stabilize the model by adding new, trained models (not mixes), already with the classical weighted sum algorithm, trying to keep brightness and variety.
I don't know exactly how well it worked. I do not specify weights, because in half of the cases there were none, the algorithm just loosened the tensors, but the composition involved these models:
colorful = abehcmiqruwx.ckpt
a_stable_diffusion.ckpt
b_redshift_diffusion.ckpt
c_openjourney.ckpt
d_f222.ckpt
e_minillbgr.ckpt
h_eimisanime.ckpt
i_portrait.ckpt
m_vintedois.ckpt
q_unreal.ckpt
r_hunter69.ckpt
u_analog.ckpt
w_wavyfusion.ckpt
x_uberRealisticPornMerge.ckpt