Spustit lokálně
ghostxl_v10BakedVAE.safetensors
6.62 GB · SafeTensor · fp16 · full
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
O tomto modelu
STABLE DIFFUSION XL 1.0 · Základní modely
Poznámky autora
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.
Spouštěcí slova
realistic anime art style
realistic art style
SHA256
EE1FDC86F76E71CA223D671DA5243C0103E9F2E3D8E80A49C9BDF24B991BA6C0
ID modelu ModelTrends.ai
#2395
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
DPM++ 2M
Kroky
30
Guidance
7
Seed
4116579308
Velikost
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
Negativní prompt
(low quality, bad quality, worst quality:1.2)
Nastavení
Sampler
Euler a
Kroky
30
Guidance
5
Seed
1084446672743564
Velikost
1664x2432
Clip skip
2
Prompt
embedding:lazympos, landscape, low poly clouds <lora:Challenge_Winnifier_2025-06:0> <lora:Polygon_Lora_XL:1>
Negativní prompt
embedding:lazyneg, 3d, realistic, photo
Nastavení
Sampler
Euler a
Kroky
30
Guidance
5
Seed
239599336637652
Velikost
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>
Negativní prompt
lazyneg,
Nastavení
Sampler
Euler a
Kroky
30
Guidance
5
Seed
382437436391205
Velikost
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>
Negativní prompt
lazyneg,
Nastavení
Sampler
Euler a
Kroky
30
Guidance
5
Seed
311752919829971
Velikost
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>
Negativní prompt
lazyneg,
Nastavení
Sampler
DPM++ 2M Karras
Kroky
30
Guidance
5
Seed
517029587
Velikost
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,
Negativní prompt
(low quality, worst quality:1.4),negativeXL_D,cgi,text,signature,watermark,extra limbs,
Nastavení
Sampler
Euler a
Kroky
30
Guidance
7
Seed
301394258389905
Velikost
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>
Negativní prompt
embedding:lazyneg,
Nastavení
Sampler
Euler a
Kroky
30
Guidance
5
Seed
602114950183643
Velikost
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>
Negativní prompt
lazyneg,
Podobné modely
AI modely pro generování obrázků, videa a textu
ghost xl je základní model pro rodinu Stable Diffusion XL 1.0 uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Stable Diffusion XL 1.0, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Další modely Stable Diffusion XL 1.0Další Základní modely Stable Diffusion XL 1.0animecomicsdrawingsbasebase modelvideo gamegame characterphotorealistic
Procházet podle rodiny modelů
Modely Text / LLM
411
Modely Anima
509
Modely Chroma
14
Modely Flux
1,071
Modely Flux 2 / Klein
1,237
Modely MiniMax H3
331
Modely Hunyuan
197
Modely Ideogram
20
Modely Krea2
674
Modely Qwen
17
Modely Qwen2
36
Modely Ltx2
150
Modely Stable Diffusion 1.5
6,465
Modely Stable Diffusion XL 1.0
15,432
Modely Zimage
804
Modely Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Vyrobeno v Japonsku
|
© 2026
