Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
ghostxl_v10BakedVAE.safetensors
6.62 GB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<ghost-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
_GhostInShell_
on Civitai
Creator notes
GhostXL is an anime model. If you like GhostXL, please give it a 5 stars review. It is very inspiring for me to improve GhostXL.(中文版本在liblib和tusi都有) Any questions or corporations? Find me at or by Wechat: ghostinshell10. Thanks Hello everyone, I am GhostInShell, the author of GhostMix. First and foremost, I would like to express my sincerest thanks to each and every user of GhostMix. With so many models out there, it is my honor that you guys choose and love GhostMix. Once again, thank you all. Secondly, I sincerely apologize for the long delay of GhostXL. Because I have high standards for the model and strive for perfection, a lot of time has been spent training and adjusting the model. Although GhostXL-V1.0 is not as good as I had imagined, it has a unique style and meets my standards in various aspects, therefore I decided to release it.Before using GhostXL, I recommend reading the user instructions below. Thank you. User Instructions for GhostXL-V1.0 - After extensive testing, we found that GhostXL-V1.0 can directly generate images with high precision in the resolution range of 1024-1536, and there's no need for upsampling or refining operations. - xx art style: The "xx art style" option allows for fine adjustments of the style. Here are some examples illustrating the effects of different art styles with the same prompts and seeds. (PS: If you want effects similar to GhostMix, the "realistic" or "realistic anime" art styles are personally recommended.) - Personal observation: The compatibility of GhostXL seems slightly less than GhostMix, and its image quality might be a bit inferior, although it tends to produce a higher percentage of satisfactory results. (These comparisons are made against an upscaled version of GhostMix.) The primary reason for releasing GhostXL is the current market's lack of models with this particular style. On the bright side, GhostXL has an edge in producing immediate outputs, making upsampling unnecessary. GhostXL Model Details - Developed by: - Model type: Diffusion-based text-to-image generative model - License: - Finetuned from model: - Config of Finetuning: - OtherMergeModel: Analysis of the Pros and Cons of GhostXL-V1.0 As I mentioned in my previous articles, the main factors I consider when creating models are: 1) Compatibility; 2) Image quality; 3) Rate of generating satisfactory results. - Compatibility: As a model that generates images in a 2D-2.5D style, GhostXL-V1.0 shows lesser compatibility with different styles when compared to GhostMix, especially for 3D styles. GhostXL is a finetune of Animagine XL V3, combined with features from other models (70% base from the finetuned model and 30% from the blend of others). As of the 1.0 version, GhostXL is still primarily a 2D-2.5D model, but I plan to keep developing it to see whether the style compatibility can be improved. For prompts compatibility, thanks to Animagine XL V3, GhostXL gives a good response to prompts such as 'masterpiece', 'best quality', as well as anime characters. However, it doesn't perform as well with more stylized prompts. - Image Quality: Personally, I feel that the image quality is generally satisfactory, considering that GhostXL generates images in the range of 1024-1536 directly (one-stage generation), unlike GhostMix which generates in 512-768 and then undergoes upsampling (a two-stage generation process). I am quite satisfied with the quality it achieves using the one-stage approach. - The Rate of Generating Satisfactory Results: In my experience, I believe GhostXL yields a higher rate of satisfactory results than GhostMix. However, for the same prompts, the variation in results is less broad in GhostXL relative to GhostMix. To increase diversity within the same theme, prompts may need to be adjusted.
Trigger words
realistic anime art style
realistic art style
14,475 downloads · 1,741 likes on Civitai
SHA256
EE1FDC86F76E71CA223D671DA5243C0103E9F2E3D8E80A49C9BDF24B991BA6C0
ModelTrends.ai Model ID
#2395
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
4116579308
Size
512x768
Prompt
(female cat:1.2) wearing a steampunk dress and flatcap with googles and mad-mecharm arm holding an umbrella walking down busy street, steampunk, steam, vignette, light rays, people doing chores, cinematic shot, dramatic lighting, blue sky, <lora:Gearbound_Mechanical_Arm_SDXL:0.8> <lora:Gearbound_Steampunk_Chic_1_SDXL:0.8> mad-stpk-bts, mad-stpk_glvs, mad-stpk-bkpk, steampunk, (masterpiece:1.2), best quality, (hyperdetailed, highest detailed:1.2), high resolution textures
Negative prompt
(low quality, bad quality, worst quality:1.2)
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
1084446672743564
Size
1664x2432
Clip skip
2
Prompt
embedding:lazympos, landscape, low poly clouds <lora:Challenge_Winnifier_2025-06:0> <lora:Polygon_Lora_XL:1>
Negative prompt
embedding:lazyneg, 3d, realistic, photo
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
239599336637652
Size
1664x2432
Clip skip
2
Prompt
lazympos,boneswm, 1girl,solo, maid, gray eyes, black hair, folded ponytail, swept bangs, small breasts, glasses, latex dress, long dress, (skeleton print apron:1.2), confused, ?, thought bubble, question mark, maid headdress made of bones <lora:Challenge_Winnifier_2025-07:0> <lora:Bones_World_Morph_XL:0.8>
Negative prompt
lazyneg,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
382437436391205
Size
1664x2432
Clip skip
2
Prompt
lazympos,boneswm, pirate ship made of bones, ocean, storm, night <lora:Challenge_Winnifier_2025-07:0> <lora:Bones_World_Morph_XL:1>
Negative prompt
lazyneg,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
311752919829971
Size
1664x2432
Clip skip
2
Prompt
lazympos,boneswm, owl made of skulls, cute, forest, night <lora:Challenge_Winnifier_2025-07:0> <lora:Bones_World_Morph_XL:0.8>
Negative prompt
lazyneg,
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
5
Seed
517029587
Size
1024x1536
Clip skip
2
Prompt
masterpiece,best quality,mysterious silhouette woman with hat,by Minjae Lee,Carne Griffiths,Emily Kell,Steve McCurry,Geoffroy Thoorens,Aaron Horkey,Jordan Grimmer,Greg Rutkowski,amazing depth,double exposure,surreal,geometric patterns,intricately detailed,bokeh,perfect balanced,deep fine borders,artistic photorealism,smooth,great masterwork by head of prompt engineering,<lora:Zenpainting l 禅意插画-SDXL_v1.0:0.7>, zen painting illustration,
Negative prompt
(low quality, worst quality:1.4),negativeXL_D,cgi,text,signature,watermark,extra limbs,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
301394258389905
Size
1664x2432
Clip skip
2
Prompt
embedding:lazympos, landscape, mountains made of bubbles, river, valley, clouds <lora:Challenge_Winnifier_2025-03:0> <lora:Bubbles_sdxl-000013:1.2>
Negative prompt
embedding:lazyneg,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
602114950183643
Size
1664x2432
Clip skip
2
Prompt
lazympos,boneswm, octopus made of bones, underwater, sunglasses <lora:Challenge_Winnifier_2025-07:0> <lora:Bones_World_Morph_XL:1>
Negative prompt
lazyneg,
AI Models for Image, Video & Text Generation
ghost 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.
Browse by Model Family
Browse all models