Model
.ai
追蹤開放 AI 模型
建立者
liudinglin
(Civitai)
AbyysOrangeMix3 by liudinglin A midpoint of artistic but bends towards anime - the model has been tuned to combine realistic textures, a artistic style that also feels like an oil colour style, and a cute anime-style face.
創作者說明
▼Some tips - Discussion: I warmly welcome you to share your creations made using this model in the discussion section. If you encounter any issues, please feel free to add a comment, and both the community and I will do our best to help and provide solutions. 您也可以使用中文在讨论区与我交流。 吾生也有涯,而知也无涯。👩‍🍳 - VAE: Given the color variation that different VAEs bring to this model, I have not baked a specific VAE onto the model. The VAE used in the sample image is kl-f8, and I appreciate its color saturation.However, perhaps you prefer orangemix.vae (NAI.vae) or others? Please feel free to try them out. - Sample image: I am terribly sorry! It seems that I triggered a bug related to the "DPM++ SDE Karras" sampler and batch generation while creating the sample image, which resulted in the inability to reproduce the sample image through the seed. However, you should be able to obtain a similar image to mine by using the same settings. Once again, I apologize for any inconvenience caused. - Wrong limb: Was it a necessary compromise for the sake of the model's diversity and creativity? In any case, please try to generate images in batches and select the high-quality works from them. Perhaps I will release an inpainting model later on? Credit for this model goes to the original author(s) and the maintainer on HuggingFace, . Consider checking out their repository on and giving it a like! Also, check out their profile on ! ▼About The main model, "AOM3 (AbyssOrangeMix3)", is a purely upgraded model that improves on the problems of the previous version, "AOM2". "AOM3" can generate illustrations with very realistic textures and can generate a wide variety of content. There are also three variant models based on the AOM3 that have been adjusted to a unique illustration style. These models will help you to express your ideas more clearly.   AOM3 Features: high-quality, realistic textured illustrations can be generated. There are two major changes from AOM2. 1: Models for NSFW such as nsfw and hard have been improved: the models after nsfw in AOM2 generated creepy realistic faces, muscles and ribs when using Hires.fix, even though they were animated characters. These have all been improved in AOM3. 2: sfw/nsfw merged into one model. Originally, nsfw models were separated because adding NSFW content (models like NAI and gape) would change the face and cause the aforementioned problems. Now that those have been improved, the models can be packed into one. In addition, thanks to excellent extensions such as , the model file size could be reduced (1.98 GB per model). ▼Variations AOM3A1 Features: Anime like illustrations with flat paint. Cute enough as it is, but I really like to apply LoRA of anime characters to this model to generate high quality anime illustrations like a frame from a theatre version. AOM3A2 Features: Oil paintings like style artistic illustrations and stylish background depictions. In fact, this is mostly due to the work of Counterfeit 2.5, but the textures are more realistic thanks to the U-Net Blocks Weight Merge. AOM3A3 Features: Midpoint of artistic and kawaii. the model has been tuned to combine realistic textures, a artistic style that also feels like an oil colour style, and a cute anime-style face. Can be used to create a wide range of illustrations. AOM3A1B AOM3A1B added. The model was merged by mistakenly selecting 'Add sum' when 'Add differences' should have been selected in the AOM3A3 recipe. It was an unintended merge, but we share it because the illustrations produced are consistently good results. In my review, this is an illustration style somewhere between AOM3A1 and A3. MORE In addition, these U-Net Blocks Weight Merge models take numerous steps but are carefully merged to ensure that mutual content is not overwritten.   (Of course, all models allow full control over adult content.) - 🔐 When generating illustrations for the general public: write "nsfw" in the negative prompt field - 🔞 It can be generated without putting it in. If you include it, the atmosphere will be more NSFW. Description for enthusiast AOM3 was created with a focus on improving the nsfw version of AOM2, as mentioned above.The AOM3 is a merge of the following two models into AOM2sfw using U-Net Blocks Weight Merge, while extracting only the NSFW content part. (1) NAI: trained in Danbooru (2)gape: Finetune model of NAI trained on Danbooru's very hardcore NSFW content. In other words, if you are looking for something like AOM3sfw, it is AOM2sfw.The AOM3 was merged with the NSFW model while removing only the layers that have a negative impact on the face and body. However, the faces and compositions are not an exact match to AOM2sfw.AOM2sfw is sometimes superior when generating SFW content. I recommend choosing according to the intended use of the illustration.See below for a comparison between AOM2sfw and AOM3. ▼How to use - Prompts - Negative prompts is As simple as possible is good. (worst quality, low quality:1.4) - Using "3D" as a negative will result in a rough sketch style at the "sketch" level. Use with caution as it is a very strong prompt. - How to avoid Real Face (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (abs, muscular, rib:1.0), - How to avoid Bokeh (depth of field, bokeh, blurry:1.4) - 🔰Basic negative prompts sample for Anime girl ↓ - v1 nsfw, (worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (dusty sunbeams:1.0),, (abs, muscular, rib:1.0), (depth of field, bokeh, blurry:1.4),(motion lines, motion blur:1.4), (greyscale, monochrome:1.0), text, title, logo, signature - v2 nsfw, (worst quality, low quality:1.4), (lip, nose, tooth, rouge, lipstick, eyeshadow:1.4), ( jpeg artifacts:1.4), (depth of field, bokeh, blurry, film grain, chromatic aberration, lens flare:1.0), (1boy, abs, muscular, rib:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, tit
Civitai 上 232,055 次下載 · 24,859 個讚
SHA256
5493A0EC491F5961DBDC1C861404088A6AE9BD4007F6A3A7C5DEE8789CDC1361
AbyssOrangeMix3 (AOM3) 熱度趨勢
熱度分數,過去 12 個月
熱度分數
9,255°
本週
▼
0.5%
9,257° 當時,9,255° 現在
本月
▼
2.1%
9,266° 當時,9,255° 現在
過去一年
▼
25.8%
9,393° 當時,9,255° 現在
AbyssOrangeMix3 (AOM3): 熱度分數,過去 12 個月7,000°7,802°8,604°9,406°10,208°Oct 2025Dec 2025Mar 2026May 2026Aug 2026Oct 20269,255°ModelTrends.ai
7,000°
基準值
分數範圍是從 0° 到 9,999°。低於 7,000° 的部分是留給還沒被任何來源報告的模型,它們會有一個替代數字,讓列表保持完整。7,000° 是有測量數據開始的地方:有真實數據但幾乎沒下載的模型會在基準值,之後的度數才是測量結果。基準值本身不代表模型好壞,只有基準值以上的度數才會區分模型。
+249°
Civitai 下載量
此版本在 Civitai 上有 232,055 次下載。下載量是最重要的成分,且以對數刻度計算:下載量增加十倍,熱度增加 300°,因此一百萬下載的模型不會比一千下載的熱度高一千倍。六個下載來源共用此一項,依其數量比例分配。
+1,556°
AI Horde 生成圖像數
志願者 AI Horde 用這個模型生成了 1,447,572 張圖。每張圖算作一次下載,使用量和下載量一樣重要。
+68°
生成網站數
這個模型在 PixAI 上的複製品有 63,488 次下載和生成執行。每次執行算一次下載,下載計算方式和 Civitai 一樣;這些都合併計入下載項目。
+661°
喜歡數
各來源共有 25,600 個喜歡和讚。每個喜歡相當於半次下載,採用同樣的對數刻度。
+180°
採用率
大約每天 247 次下載,根據兩次來源讀取間的變化計算,不是用整個生命週期平均。速度佔下載項目的四分之一,能反映新熱潮,但不會讓一天的爆量超過多年累積。
+150°
完整模型
+150° 因為這是完整模型:檢查點,也就是權重本身。LoRA 或嵌入是別人權重的附加,不會比同人氣的檢查點更熱。
−609°
年齡
−609° 因為 SD15 權重是在 2022 發布的。每個模型都繼承它所用權重的年齡:每年扣 150°,最多扣 750°,扣分會持續增加。沒有這項,排行榜頂端會是 2022 和 2023 年的檢查點,因為下載有多年累積。
顯示詳細分析
這個網站上的每個數字都可以查證。這個模型的熱度分數是 9,255°,這裡會一步步拆解它的組成,每加一項就會顯示目前的總分:基準值、每個來源增加的度數、模型類型的加分,以及權重年齡帶來的扣分。顏色對應上方圖表的區間。最後的詞彙表會解釋每個術語。
  1. 1
    從基準值開始。
    為什麼是 7,000° 而不是零:分數範圍是 0° 到 9,999°,低於 7,000° 的部分是留給還沒被任何來源報告的模型,它們有替代數字,讓列表完整且不會超過有數據的模型。7,000° 是有測量數據開始的地方。有真實數據但幾乎沒下載的模型會在這裡;之後的度數是測量結果,基準值以上有十個十倍下載的階段,每階段增加 300°。基準值對所有模型都一樣,不會決定排名;真正區分模型的是基準值以上的度數。
    7,000°
    累計總和
  2. 2
    加入下載量。
    總共 1,743,115 個下載等值,來自 Civitai 下載量, AI Horde 生成圖像數, 生成網站數。下載量增加十倍會增加相同的 300°,所以大小很重要,但不會主導分數。
    +249° Civitai 下載量
    +1,556° AI Horde 生成圖像數
    +68° 生成網站數
    +1,873°
    8,873°
    累計總和
  3. 3
    加入喜歡數。
    25,600 個喜歡和讚,權重是下載量的一半。
    +661°
    9,534°
    累計總和
  4. 4
    加入採用率。
    目前大約每天 247 次下載,根據兩次讀取間的差異計算,權重是下載量的四分之一。
    +180°
    9,714°
    累計總和
  5. 5
    完整模型的額外加分。
    檢查點包含權重本身;附加元件不會超過同樣受歡迎度的完整模型。
    +150°
    9,864°
    累計總和
  6. 6
    移除年齡。
    SD15 權重於 2022 發布:每年扣除 150°,最多扣除 750°,直到達到上限。
    −609°
    9,255°
    累計總和
  7. =
    熱度分數。
    這個模型在本網站所有排行榜上的位置。沒有其他因素會調整它。
    9,255°
詞彙表:這裡使用的術語
熱度分數
一個數字,表示模型目前的使用和需求程度,範圍從 0° 到 9,999°。本網站所有標示「最熱門」的排行榜都是依此排序,沒有其他排序依據。
底線
每個有實際數據的模型起始於 7,000°。分數範圍是 0° 到 9,999°;底線以下保留給沒有數據的模型,確保有數據的模型總是排名較前。底線對所有人相同,不影響排名;超過底線的度數才是評分依據。
下載等值
分數中視為下載的所有項目加總:下載本身、每個種子節點算 1,000、每張 AI Horde 圖像和每次生成網站的執行算一。
對數刻度
以十為單位計數,不是以一為單位:從 1,000 到 10,000 下載增加的度數,和從 10,000 到 100,000 增加的度數相同。這樣能防止巨頭壓過其他模型。
喜歡數
來自各來源的讚和喜歡,每個在對數刻度上算半個下載量。
採用率
模型目前每天的下載次數,根據兩次來源讀取的差異計算。權重是下載量的四分之一。
實測與估算
實測表示有兩個來源的讀數,且差異是真實的。估算表示只知道今天的總數,過去的數據則分散在模型的整個生命週期;網站會說明顯示的是哪一種。
種子節點
指在線上保留權重檔案供他人透過種子下載的人,或是提供相同服務的鏡像站。每一個種子節點算作1,000次下載。
AI Horde
一個志願者網絡,利用捐贈的電腦免費生成圖片。它用某模型生成的圖片數量是公開的,每張圖片算作一次下載。
生成網站
自己托管模型並讓人使用它生成圖片的網站,例如PixAI、SeaArt和Yodayo。它們的下載量和Civitai一樣,每次生成算一次下載。
OpenRouter 代幣
透過 API 提供的文字模型,如 Claude 或 GPT,沒有權重可下載,因此使用量以代幣計算:過去30天內透過 OpenRouter(許多應用使用的閘道)讀取和生成的文字片段。每 10,000,000 代幣算作一次下載。來源:OpenRouter (openrouter.ai/rankings),CC BY 4.0。
完整模型(檢查點)
權重本身,是能獨立生成的檔案。它會有額外加分,因為其他附加檔案都依賴它。
LoRA和嵌入
小型附加檔案,用來引導別人的權重走向某種風格、角色或概念。它們無法獨立運行。
家族與權重
模型所建立的基礎,例如SD 1.5、SDXL、Flux或Wan。每個模型都繼承其家族權重的發布日期。
年齡
根據家族權重發布時間距今多久,扣除的度數:每年150°,最多750°。它會保留那些有多年累積下載的舊模型,防止它們從排行榜頂端消失。
家族加成
針對本站目前推廣的某個家族的LoRA給予的小幅度限制加成,會在分解中顯示。
替代分數
給尚無來源報告的模型一個穩定的最低分,讓列表保持完整。它永遠不會高於有數據的模型。
全新!(寬限期)
不到 7 天的新模型會顯示「全新!」而非分數,且不列入排名。分數從第一天開始計算,但一天大的模型成長最快,若不等待,週榜首將永遠是昨天剛出的模型,而非持續一週的。
趨勢
模型在某段時間內的成長與典型模型同期成長的比較。比典型快表示上升,比典型慢表示下降。
典型模型
目錄中的中間值:一半模型在該期間成長較快,一半較慢。
這個模型的受歡迎程度跟整個目錄相比的變化:它在每個時期的下載量、喜歡數和使用量的成長,跟同一時期一般模型的成長相比,還有當時的熱度分數。高於一般成長代表上升,低於則是下降。過去的數據是從今天的總數、模型的第一天和有兩次讀數時的下載速度推算出來的;如果模型在某時期開始時不存在,會顯示 n/a。
範例作品
以下提示詞和參數由在 Civitai 上創作這些作品的人分享。選擇一張作品查看它是如何生成的。
參數
取樣器
DPM++ SDE Karras
步數
20
引導強度
7
種子
2716231661
尺寸
832x512
Clip skip
2
提示詞
masterpiece, best quality, ultra-detailed, illustration, 1girl, solo, outdoors, camping, night, mountains, nature, stars, moon, tent, twin ponytails, green eyes, cheerful, happy, backpack, sleeping bag, camping stove, water bottle, mountain boots, gloves, sweater, hat, flashlight, forest, rocks, river, wood, smoke, shadows, contrast, clear sky, constellations, Milky Way, peaceful, serene, quiet, tranquil, remote, secluded, adventurous, exploration, escape, independence, survival, resourcefulness, challenge, perseverance, stamina, endurance, observation, intuition, adaptability, creativity, imagination, artistry, inspiration, beauty, awe, wonder, gratitude, appreciation, relaxation, enjoyment, rejuvenation, mindfulness, awareness, connection, harmony, balance, texture, detail, realism, depth, perspective, composition, color, light, shadow, reflection, refraction, tone, contrast, foreground, middle ground, background, naturalistic, figurative, representational, impressionistic, expressionistic, abstract, innovative, experimental, unique
負面提示詞
(worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (dusty sunbeams:1.0),, (abs, muscular, rib:1.0), (depth of field, bokeh, blurry:1.4), (greyscale, monochrome:1.0), text, title, logo, signature,watermark,
這張作品沒有分享提示詞。
參數
取樣器
DPM++ SDE Karras
步數
20
引導強度
7
種子
3080004317
尺寸
512x832
Clip skip
2
提示詞
masterpiece, best quality, ultra-detailed, illustration, 1girl, solo, fantasy, flying, broom, night sky, outdoors, magic, spells, moon, stars, clouds, wind, hair, cape, hat, boots, broomstick, glowing, mysterious, enchanting, whimsical, playful, adventurous, freedom, wonder, imagination, determination, skill, speed, movement, energy, realism, naturalistic, figurative, representational, beauty, fantasy culture, mythology, fairy tales, folklore, legends, witches, wizards, magical creatures, fantasy worlds, composition, scale, foreground, middle ground, background, perspective, light, color, texture, detail, beauty, wonder.
負面提示詞
nsfw,(worst quality, low quality:1.4), (lip, nose, tooth, rouge, lipstick, eyeshadow:1.4), ( jpeg artifacts:1.4), (depth of field, bokeh, blurry, film grain, chromatic aberration, lens flare:1.0), (1boy, abs, muscular, rib:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, title, logo, signature
參數
取樣器
DPM++ SDE Karras
步數
20
引導強度
7
種子
1418181673
尺寸
1664x1024
Clip skip
2
提示詞
masterpiece, best quality, ultra-detailed, illustration,2girls,fantasy, RPG, heroine, devil, final battle, outdoors, epic, dramatic, intense, powerful, dynamic, magic, spells, sword, shield, armor, wings, horns, tail, fire, smoke, light, shadow, impact, movement, energy, determination, bravery, courage, heroism, villainy, evil, darkness, destruction, victory, defeat, redemption, justice, sacrifice, friendship, companionship, teamwork, perseverance, challenge, obstacle, success, achievement, goal-oriented, progress, improvement, realism, naturalistic, figurative, representational, video game culture, anime, manga, Japanese, RPG tropes, character design, animation, special effects, composition, scale, foreground, middle ground, background, perspective, light, color, texture, detail, beauty, wonder,
負面提示詞
nsfw,(worst quality, low quality:1.4), (lip, nose, tooth, rouge, lipstick, eyeshadow:1.4), ( jpeg artifacts:1.4), (depth of field, bokeh, blurry, film grain, chromatic aberration, lens flare:1.0), (1boy, abs, muscular, rib:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, title, logo, signature
這張作品沒有分享提示詞。
參數
取樣器
DDIM
步數
20
引導強度
7
種子
1276181096
尺寸
512x768
Clip skip
2
提示詞
(masterpiece, 4k ,ultra detailed:1.2),(beautiful face:1.2),(anime:1.2),illustration,(realistic:1), (1girl facing each other:1.4),(multiple views:1.4),(from side:1.4), (facing away,looking away:1.4), (teasing smile:1.2), (standing:1.2),(supermodel:1.4), (simple background,white background:1.2), (schoolgirl_uniform,long sleeve dress shirt,black pleated skirt,black thighhigh:1.2), (black_hair),(medium length hair),(flat chest:1),(wide_hips,curvy:1.2), (mature,milf,35yo:1.2), <lora:hipoly3DModelLora_v10:0.2>, <lora:japanesedolllikenessV1_v15:0.4>, <lora:breastExpansionLora_v10:0.6>,(breast expansion:1.4)
負面提示詞
EasyNegative,(badhandv4),verybadimagenegative_v1.3,By bad artist -neg, (worst quality:1.4), (low quality:1.4) ,( jpeg artifacts, signature,logo,watermark,text:1.3), (string,abs,elf,loli,child,petite,heterochromia:1.1),(nsfw,nipple:1.4),(undress:1.8),(looking at viewer:1.4)
這張作品沒有分享提示詞。
參數
取樣器
Euler
步數
36
引導強度
7
種子
1186590781
尺寸
512x512
Clip skip
2
提示詞
best quality, ultra high res,(extreme furry short hair sparrow,extreme furry short hair bird), [32k|16k|best-quality], professional photo, <lora:tangbohu-detailer_1.0:1>, <lora:add_saturation:1.0>, <lora:tangbohu-detailmaker_v2.5:1.0>, many sparrow, group of sparrow, (groups of sparrow lines up as a ring),(japanese living room),(bird),(sparrow head, bird head:1.5),(large bird:1.5),(brown bird ),(short fur),(fluff, fine hair:1.5) , <lora:cute_sparrow:0.6>, sparrow
負面提示詞
bad_prompt_version2, By bad artist -neg ,DreamArtistBADHAND, EasyNegative ,ng_deepnegative_v1_75t, verybadimagenegative_v1.3,(pubic hair),(extra fingers, deformed hands, polydactyl:1.5), badhandv4,(text)
本機執行
abyssorangemix3AOM3_aom3a1b.safetensors
1.99 GB · SafeTensor · fp16 · full
下載由 Civitai 提供。部分建立者要求先登入 Civitai。