Run Locally
bittersweetmixPony_bsm.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
by YoshiKage - A mix of CassyAnime with a darker look. Recommendations: Clip skip: 2 Steps: 30 CFG scale: 7 Sampler: Euler a Width: 896 or 832 Height: 1152 or 1216
Creator notes
I am not a native speaker of English. I use automatic translation.
I redid the WMM merge with the addition of a marvelous model!
→
(Since the painting style is quite different from that of WMM, it is uploaded as a separate model!)
Features
-
Marge is going for a darker look (more so than WMM-Dark).
-
Portrayal of mature, cool women, close to 2.5D.
-
Depiction of stable fingers, comparable to WMM.
Actually, this model is still in rough shape...
Specifically, the “eyes” are a bit unstable... Sorry!
(This problem can usually be remedied by using an upscaler!)
But it has the potential to generate great images, so I decided to share it with you!
NSFW images can also be generated.
If there are any problems, this will be removed.
Have fun! And please show me your work!
I'm very happy when someone posts their work!
Don't forget to check “” and “”!
_________________________________________________________________________________________________________
Setting Example:
(This is the setting I use. You may change it to your favorite setting.)
Clip skip: 2
Steps: 30
CFG scale: 7
Sampler: Euler a
Schedule type: Automatic
(Combinations like "DPM++ 2M SDE" or "DPM++ 2M" and "Karras" are fine. But I prefer the combination of "Euler a" and "Automatic"!)
Width: 896 or 832
Height: 1152 or 1216
VAE: none (Or Use your favorite one!)
Upscaler: R-ESRGAN 4x+ Anime6B or Your favorite one!
Upscale by: 1.5~2
Hires steps: 15
Denoising strength: 0.2~0.3
_________________________________________________________________________________________________________
Positive prompt:
At least “score_9,” is required.
As for “score_8_up, score_7_up,” you can do without it... As far as I have tried...
Or you can try any prompt you like.
_________________________________________________________________________________________________________
Negative prompt:
Nothing is needed!
“ score_6, score_5, score_4, “ could be added, but would only be a lucky charm.
(I tried it several times and it made no significant difference)
If text is displayed, just add “ username, ”. It will almost certainly improve the image.
If there is a mosaic, add “ censored, mosaic censoring, bar censor, ”. This will improve the situation.
_________________________________________________________________________________________________________
Notice:
If the image is “too realistic”, please try the following solutions
Add the tag “anime,” to the positive.
Add “realistic,” to the negative.
However, this will make the image somewhat unstable. Therefore, it is not recommended.
If you want more “anime style”, try my other models “” and “”!
Waiting for lots of posts and reviews!
_________________________________________________________________________________________________________
WMMマージにマーベラスなモデルを追加してやり直しました!
→CassyAnime2.5D
(WMMとはかなり画風が違うので、別モデルとしてアップします!)
特徴
マージはダークな雰囲気を目指している(WMM-Darkよりもっと)
2.5Dに近い、成熟したクールな女性の描写
WMMと同等の安定した手指の描写
実はこのモデル、まだ荒削りです...
具体的には、「目」がちょっと不安定です...。すみません!
(この問題は通常、アップスケーラーを使うことで改善できます!)
でも、素晴らしい画像を生成する可能性があるので、皆さんと共有することにしました!
楽しんでください!そして、あなたの作品を見せてください!
誰かが自分の作品を投稿してくれると、私はとても嬉しいです!
"MMM"と"WMM"のチェックをお忘れなく!
Setting Example:
(私が使用している設定です。お好みの設定に変更してください)
Clip skip: 2
Steps: 30
CFG scale: 7
Sampler: Euler a
Schedule type: Automatic
("DPM++ 2M SDE"や"DPM++ 2M"と"Karras"のような組み合わせもいいです。しかし、私は"Euler a"と"Automatic"の組み合わせが好きです!)
Width: 896 or 832
Height: 1152 or 1216
VAE: none (または好きなものを使ってください!)
Upscaler: R-ESRGAN 4x+ Anime6B or (または好きなものを使ってください!)
Upscale by: 1.5~2
Hires steps: 15
Denoising strength: 0.2~0.3
ポジティブプロンプト:
少なくとも "score_9 "は必要です。
"score_8_up,score_7_up "については、なくても大丈夫です。私が試した限りでは...
あるいは、好きなプロンプトを試すこともできます。
ネガティブプロンプト:
何も必要ありません!
"score_6, score_5, score_4, " を追加することも可能ですが、お守りにしかならないと思います。
(何度か試したが、大きな違いはなかった)。
テキストが表示されている場合は、"username,"を追加してください。
モザイクがかかっている場合は、"censored, mosaic censoring, bar censor,"を追加してください。 これで改善されます。
お知らせ
画像が"リアルすぎる"場合は、以下の解決策をお試しください。
ポジティブに"anime,"というタグを追加する。
ネガティブに "realistic,"を追加する。
ただし、これは画像を多少不安定にします。したがって、お勧めできません。
もっと"アニメ風"にしたい場合は、私の他のモデル"MMM"と"WMM"を試してみてください!
たくさんの投稿とレビューを待っています!
SHA256
425083976ACCB9E12613E07A56A459420E667B4EF5CCF4647066DBCDFEF72126
ModelTrends.ai Model ID
#14336
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
DPM++ 2M
Steps
30
Guidance
7
Seed
2430937188
Size
832x1216
Clip skip
2
Prompt
score_9, 1girl,solo,burgundy hair,twin hair buns,hair behind ear,orange eyes,red eyes eyebrows,eyelashes,blush lips,green beads earrings,red cropped cheongsam,yellow lining,flame fire print,sleeveless,bare shoulders,midriff,skirt,bare thighs,facing virewer,looking at viewer,simple background,brown background,sinozick style,flat color,<lora:add-detail-xl:1>,<lora:perfect-eyes:1>,<lora:Sinozick_Style_XL_Pony:0.71>
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
7
Seed
2323223475
Size
832x1216
Clip skip
2
Prompt
score_9, 1girl,teenager,solo,ginger hair,twin hair buns,hair behind ear,emerald eyes,yellow eyebrows,eyelashes,blush lips,purple beads earrings,green cheongsam,blue lining,dragon print,sleeveless,bare shoulders,(sandals),standing,facing virewer,looking at viewer,full body,simple background,brown background,sinozick style,flat color,<lora:add-detail-xl:1>,<lora:perfect-eyes:1>,<lora:Sinozick_Style_XL_Pony:0.71>
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2628200167
Size
832x1216
Clip skip
2
Prompt
score_9, score_8_up, score_7_up,girl, silver hair, tied hair, gradient blue dress, sitting, looking at viewer, cowboy shot, galaxy, stars, Illumination, dark room, planetarium,
Negative prompt
score_4, score_5, score_6,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2963469096
Size
832x1216
Clip skip
2
Prompt
score_9, girl, blonde hair, long hair, Dolly eye, gothic dress, headdress, dark room, looking at viewer, focus on eyes, hug Stuffed black cat,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
3235297601
Size
832x1216
Clip skip
2
Prompt
score_9, girl, long hair, gradient hair, volcanic background, lava, horns, scales, wings, black sclera,looking at viewer, from side, bokeh,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2700185009
Size
832x1216
Clip skip
2
Prompt
score_9, 1girl, black hair, long hair, blunt bangs, looking at viewer, head tilt,
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
7
Seed
1208594216
Size
832x1216
Clip skip
2
Prompt
score_9, 1girl,solo,dark purple hair,(close-up portrait),twin hair buns,hair behind ear,aqua eyes,purple eyebrows,eyelashes,blush lips,yellow beads earrings,blue cheongsam,yellow lining,floral print,sleeveless,bare shoulders,facing virewer,looking at viewer,simple background,dark pink background,sinozick style,flat color,<lora:add-detail-xl:1>,<lora:perfect-eyes:1>,<lora:Sinozick_Style_XL_Pony:0.71>
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
8
Seed
678112241
Size
832x1216
Prompt
score_9, score_8_up, score_7_up,1girl,solo,intense blonde hair,long hair,straight hair,swept bangs,hair behind ear,green eyes,clover shaped earrings,blush lips,pink lips,floral markings on face,brown eyebrows,nostrils,green collar,silver necklace,green overalls,overalls straps,bare shoulders,green framed eyewear,close-up portrait,graffiti wall,looking at viewer,facing viewer,smile
Similar Models
AI Models for Image, Video & Text Generation
bittersweetmix xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion XL 1.0 modelsMore Stable Diffusion XL 1.0 Base Modelsponytypeanimerealisticbaseponyxlgirlsbase modelwoman
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026








