Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
yabalMixTrue25D_v2_71646.safetensors
2.24 GB · SafeTensor · fp16 · pruned
yabalMixTrue25D_v2_71654.safetensors
5.53 GB · SafeTensor · fp32 · full
Download
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION 1.5 · Base Models
Created by
YabaL
on Civitai
Yabal Mix True 2.5D Version 2 is a blend of various anime checkpoints, trying to strike a balance between realism and anime
Creator notes
YabaL_Mix True2.5D - I have integrated the existing checkpoints into a single post - I apologize to those who have posted in the previous gallery as it has been deleted - From now on, the next versions will be updated in this post About version - V1 : A checkpoint that aims for a middle ground between Realistic and animated art - V2 : Enhanced backgrounds for a more realistic feel, and slightly improved character eyes compared to V1, and Continuing to strive for a 2.5D - V3 : a little bit a Changed art style and Enhanced Clothes Details - V4 : 2D inclination increased compared to the previous version - V5 : Aiming for a midpoint between realism and 2D Recommended settings - VAE : vae-ft-mse-840000-ema-pruned - DPM++ 2M Karras // DPM++ 2M SDE Karras - R-ESRGAN 4x+ Anime6b // 4x-UltraSharp - DDtailer. In the default settings, the value of Mask Blur is set to 10. 한국어 - 기존 버전을 삭제하고 하나의 포스트에 통합 했습니다. - 기존 버전의 갤러리 이미지는 삭제 되었습니다. 업로드 하신분께 사과드립니다. - 앞으로는 이 포스트에서 다음 버전이 업데이트 될 예정입니다. 버전별 특징 - V1 : 2.5D를 목표로 두고 만든 모델입니다. 실사와 애니의 중간지점을 목표로 한 모델입니다. - V2 : 배경이 좀더 실사화 되었고, 눈 표현이 좀더 깔끔 합니다. 여전히 2.5D를 목표로 제작 되었습니다. - V3 : 약간의 그림체 변화와 복장 디테일의 증가가 있습니다. - V4 : 전작 대비 2D성향을 증가 시켰습니다. - V5 : 2D랑 반실 중간지점을 목표로 병합 했습니다. - 업스케일러 R-ESRGAN 4x+ Anime6b // 4x-UltraSharp의 차이점이 존재합니다. 애니에 가깝게 만들고 싶으면 Anime6b를 사용하시고 실사와 가깝게 만들고 싶으면 4x-UltraSharp를 권장합니다.
2,720 downloads · 18 likes on Civitai
SHA256
E451AFB69993431364331D0C861B2D08B067AD616799DCB6F9BC905B87E98602
ModelTrends.ai Model ID
#8175
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 SDE Karras
Steps
40
Guidance
7
Seed
3497043745
Size
540x960
Clip skip
2
Prompt
(pin-up curls), (character on front), outdoors, dark hair, dark eyes, lady, masterpiece, best quality, looking at viewer,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,white clothes,lipstick,red pupils,crossed arms,crossed legs,letterboxed,arm support,bad anatomy,tattoo,,colored skin,umbrella, crown,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
40
Guidance
7
Seed
513309515
Size
540x960
Clip skip
2
Prompt
(bob cut), (character on front), outdoors, dark hair, dark eyes, lady, masterpiece, best quality, looking at viewer,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,white clothes,lipstick,red pupils,crossed arms,crossed legs,letterboxed,arm support,bad anatomy,tattoo,,colored skin,umbrella, crown,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
50
Guidance
7
Seed
4240513064
Size
540x960
Clip skip
2
Prompt
(lady:1.2),looking at viewer,(cinematic:0.7),depth of field,dark hair, dark eyes, outdoors,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,lipstick,red pupils,letterboxed,arm support,bad anatomy,tattoo,colored skin, white clothes,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
40
Guidance
7
Seed
1872273295
Size
540x960
Clip skip
2
Prompt
(Long hair with natural waves), (character on front), outdoors, dark hair, dark eyes, lady, masterpiece, best quality, looking at viewer,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,white clothes,lipstick,red pupils,crossed arms,crossed legs,letterboxed,arm support,bad anatomy,tattoo,,colored skin,umbrella,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
50
Guidance
7
Seed
4240513064
Size
540x960
Clip skip
2
Prompt
(lady:1.2),looking at viewer,(cinematic:0.7),depth of field,dark hair, dark eyes, outdoors,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,lipstick,red pupils,letterboxed,arm support,bad anatomy,tattoo,colored skin, white clothes,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
50
Guidance
7
Seed
4240513064
Size
540x960
Clip skip
2
Prompt
(lady:1.2),looking at viewer,(cinematic:0.7),depth of field,dark hair, dark eyes, outdoors,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,lipstick,red pupils,letterboxed,arm support,bad anatomy,tattoo,colored skin, white clothes,
Settings
Sampler
DPM++ 2M Karras
Steps
40
Guidance
7
Seed
3150215366
Size
540x960
Clip skip
2
Prompt
lady, dark hair, dark eyes, looking at viewer, cinematic, depth of field, light, {dress|skirt|pants|shorts|suit|casual|clothes}, {indoors|outdoors} {day|night|dawn}, {stocking|pantyhose|legwear|no_legwear}, ({black|white|ivory|grey|dark|light black} theme),
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,white clothes,lipstick,red pupils,crossed arms,crossed legs,letterboxed,arm support,bad anatomy,tattoo,,colored skin,umbrella,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
40
Guidance
7
Seed
469966986
Size
540x960
Clip skip
2
Prompt
(Messy bun with loose tendrils), (character on front), outdoors, dark hair, dark eyes, lady, masterpiece, best quality, looking at viewer,
Negative prompt
worst quality,low quality,normal quality,watermark,text,error,blurry,signature,artist name,white clothes,lipstick,red pupils,crossed arms,crossed legs,letterboxed,arm support,bad anatomy,tattoo,,colored skin,umbrella,
AI Models for Image, Video & Text Generation
yabalmix true2 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