Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
mistoonAmethyst_v20.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<mistoon-amethyst>
About This Model
STABLE DIFFUSION 1.5 · Base Models
Created by
Inzaniak
on Civitai
Creator notes
Join our community Discord: You can now get all my LoRAs in one single package if you subscribe to my Patreon (including those not on CivitAI): How to use this If you are new to the world of Stable Diffusion, you can learn how to run it by yourself here: You'll also need a VAE to use this. For the examples, I've used the Grapefruit one: What's new in v2? I wasn't satisfied by the overall performance of the checkpoint. It often used the same colors and required a low CFG level. With the newer model, you can use a higher CFG level without over saturation and distortion. It's less Disney-ish and more a crossover of vintage western and modern anime style (which is what I wanted to create in the first place). What's this model Mistoon_Amethyst is a variant of my SD model that tries to achieve a Disney pinup style. The starting point for this model was my blend. From there, I then added a few of my custom LoRAs in the mix to change the esthetic (mostly and ). Try also the other flavors: The style It creates realistic and expressive characters with a "disney" twist. All the examples have been created using this version of the model using my workflow. Check the guide if you want to learn more about my workflow. The model can also easily do NSFW stuff (check the last examples). Right now the model is biased over sea backgrounds and cyan clothes (for whatever reason), so I highly recommend addind those to the negative prompt. Guides Learn how to create pictures like mine with my step-by-step tutorials: - - - - - - - Support My Work Check out my Patreon for exclusive content: Do you want a custom LoRA or picture? Check out my commission page: If you want to support my work for free, you can also check out my music/art here: - - -
9,459 downloads · 970 likes on Civitai
SHA256
FC896C44F11404EFBB59B73BBF08A9265AFB7A905104CA9626B92E5998F078D2
ModelTrends.ai Model ID
#7295
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler
Steps
40
Guidance
9
Seed
3280097057
Size
512x768
Clip skip
2
Prompt
orange fins, purple fins, (rvmd person), full body, (masterpiece, absurdres:1.2) <lora:rvmd:0.9>
Negative prompt
(worst quality, low quality:1.3), sparkles, stars, arms, (human), (more than one person:1.4), words, text, watermark, torso
Settings
Sampler
DDIM
Steps
20
Guidance
7
Seed
170611493
Size
512x768
Prompt
girl,(hotify:1.2) ,girl,suspenders,cleavage,field,crop,farm,brown_hair,hat,carrot between breasts ,(masterpiece,detailed,highres:1.4)
Negative prompt
verybadimagenegative_v1.3, badhandv4, text, watermark, signature, letterbox,borders,multiple,multiple panels,2_girl, multiple girls
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
551863209
Size
768x1152
Prompt
girl,(hotify:1.2),sitting,chair,kitchen,food,table,short_hair,bob cut,hair clip,freckles,suspenders,red_hair,cleavage ,(masterpiece,detailed,highres:1.4)
Negative prompt
verybadimagenegative_v1.3, badhandv4, text, watermark, signature, letterbox,borders,multiple,multiple panels,2_girl, multiple girls
Settings
Sampler
Euler a
Steps
35
Guidance
7.2
Seed
226433232
Size
512x768
Prompt
best quality, highres, high detail, sharp focus, soft glow, cinematic shadow, artistic lighting. <lora:Hastur-000001:1> A fullbody beautiful brunette princess in a glittering gown that trails into hastur, king in yellow tentacles.
Negative prompt
lantern, worst quality, bad quality, bad anatomy, lowres, low resolution, easynegative, Unspeakable-Horrors-Composition-4v, Asian-Less-neg,
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
710926562
Size
512x768
Prompt
girl,(prettify:1.2) ,date,restaurant,huge_breasts,cleavage,detailed dress,lace_dress ,sitting,table,food,crowd,window,street ,(masterpiece,detailed,highres:1.4)
Negative prompt
verybadimagenegative_v1.3, badhandv4, text, watermark, signature, letterbox,borders,multiple,multiple panels,2_girl, multiple girls
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
1505591918
Size
768x1152
Prompt
girl,(prettify:1.2) ,date,aquarium,casual_clothes,close-up,red_hair,hair_bun,penguin ,(masterpiece,detailed,highres:1.4)
Negative prompt
verybadimagenegative_v1.3, badhandv4, text, watermark, signature, letterbox,borders,multiple,multiple panels,2_girl, multiple girls
Settings
Sampler
Euler a
Steps
20
Guidance
6
Seed
2257890067
Size
512x768
Prompt
masterpiece, 8k, perfect ligthing, , adult, female, cowboy shot, looking at viewer, (body to the right), looking back, cinematic lighting, Rosetta, (RosettaWaifu:1.1), Hair curled at the ends, (dress:1.8), (extra long white fairy wings), long wings, pink clothes, clothes made from petals, Auburn Hair, (pointy ears), (detailled eyes), green eyes, emerald eyes, shrunken, (smirk:1.3), blush, pixiedust, jungle, ((flowers)), <lora:RosettaTinkerbellDisney-06:0.6> <lora:realisticGlossyFaceSkin_rseromanticRsesofiko:0.3>
Negative prompt
easynegative, ng_deepnegative_v1_75t, (bad-hands-5), (low quality, worst quality, lowres:1.1), text, patreon, watermark, plants, grass, green, reflection, fused fingers, (malformed fingers), malformed hands, ugly hands, (ugly fingers:1.8), ugly feet, (malformed feet:1.6), (too many legs:1.9), (too many arms:1.7), ugly wings, bend wings,
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
3079312193
Size
512x768
Prompt
girl,(prettify:1.2) ,maid,cleaning,dark_skin,living_room,(all fours:1.3),rag,spill,stain,tight_clothes,revealing_clothes,stockings ,(masterpiece,detailed,highres:1.4)
Negative prompt
verybadimagenegative_v1.3, badhandv4, text, watermark, signature, letterbox,borders,multiple,multiple panels,2_girl, multiple girls
AI Models for Image, Video & Text Generation
mistoon amethyst is a base model for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models