Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

to draw abstract shapes with sponge スポンジ状 and cell theme.

Because initial dataset contains only my abstract renders without any real world's items so it is hard to activate it, and very hard to interact with humans or other objects . But possible and results can be awesome.

SD1.5x version will be publish soon it can produce more clean output (and much better in less then 1024*1024) and capable to interaction with (realistic) girls.

Lexicon / prompt 辞書

activation by these tags working not very good, need to improve training:

in v045 seems like color is most important: different combinations and change sequence can make image good or waste.

Tags for v045+ (v04 in brackets)

es11es - you can skip it. Each file contain this tag, so it have to work as global trigger but weak

pink es11pong, (ethernalSponge04) - creates sponge like texture good with asteroid, blob, textile, landscape surface

colorful esb11elt, (sbelt04) - structure with thick voids between belts. Also capable create belts mess, liana, probably veins but not tested

esb11elt, esb11el25d, - for belts that lie on flat surface, but has significant 3d volume-looking

esb11elt, esb11el3d, - for 3d belts

blue es11grat, - we can view backgrond behind it, thinner then belts

white es11cells, - create cells over some background

esc11omb (comboPol04) - create cell-texture and shapes like comb, sea stars. Good with comb, hexagon

esb11lob, (blobsponge04) - helps to create finite bodies, but not seamless texture.

es11urfac - surface, but not blobs

esn11udle (snudle04) - noodle (pasta) like elements

addition tags:

pores, holes, - for thin or thick holes in surface / 表面の穴

seamless texture,

colorful red border | outline

gradient | star sky | simple| yellow | aqua background,

3d, DOF, blob, asteroid - helps to create finite bodies, but not seamless texture.

net, cage, web, threads, thread - thin version of es11grat grate, usually 1-pixel. web create more round shapes like typical spider web

prickly, needles, barbed, spiny,

object, - single or multiple objects that not spread all canvas

multiple objects, - that not spread all canvas

thick, thin, - change texture scale, especially for belts and holes

roots,

portal, orb

lattice, fence, grate

polka dot, polka dot background

beige, yellow theme,

architecture, building,

bionic, organic shape

futurism, futuristic,

no humans

Usually avoid tags:

corals, sea life, anemone because it is very easy shift SD to draw unstylish semi-natural forms that looks bad. Sometimes better to set negative prompt corals or anemone

Negative request

common negative (that you use with girls render) sometimes can prevent this model to draw anything good. So be very careful, Empty neg or only "blur" is ok. Need to find what makes it better.

cut gems, - in combination with organic shape improve roundness of shapes

grayscale, - to make it more vivid

coral, anemone, food

balls, eyes, -

Typical workflow in ComfyUI ##TODO##

Settings

  • Strength: each subject need different, precise and separate control of model and clip strength. 0.2 ... 0.8 is ok.

  • SDXL version work better with 1Mpx resolution e.g. 1024*1024

  • CFG 5...15

  • Step 25-45, sometimes produce better then very precise steps

About and TODO

if you want to continue training yourself - i can publish dataset as it contains only my own images

Images Generated With This Model

Loading...

Similar Models

Essenz - Better Photography (Style LoRa for SDXL 1.0)
V2
Essenz - Better Photography (Style LoRa for SDXL 1.0)
(5.00)
0
3 Ratings
Chrome Tech - XL World Morph
V2
Chrome Tech - XL World Morph
(5.00)
0
8 Ratings
filter(滤镜)
V1
filter(滤镜)
(5.00)
0
1 Ratings
Linyada - LoRA
V1
Linyada - LoRA
(0.00)
0
0 Ratings
🎄Xmas Tech - World Morph🎄
V1
🎄Xmas Tech - World Morph🎄
(5.00)
0
5 Ratings
Killer7 Art Style - Animation
V1
Killer7 Art Style - Animation
(0.00)
0
0 Ratings
Essenz - Darkest Dungeon [Chris Bourassa] (Style LoRa for SDXL 1.0)
V2
Essenz - Darkest Dungeon [Chris Bourassa] (Style LoRa for SDXL 1.0)
(5.00)
0
5 Ratings
Essenz - Jean Giraud/Moebius [Voyage d'Hermès] (Style LoRa for SDXL 1.0)
V2
Essenz - Jean Giraud/Moebius [Voyage d'Hermès] (Style LoRa for SDXL 1.0)
(0.00)
0
0 Ratings
filter(滤镜)
V1
filter(滤镜)
(0.00)
0
0 Ratings
Mecha Style XL | Goofy Ai
V2
Mecha Style XL | Goofy Ai
(4.50)
0
2 Ratings

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.