Run Locally
L_IR01z3.safetensors
288 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION 1.5 · LoRAs
__html__InstantRealizerInstantRealizer is a Lora group for turning illustration models into realistic models. If I used Lora alone, the adjustment range would be too small, so I divided it into three parts.InstantRealizerは,イラスト系モデルをリアル系モデルにするためのLora群です。単体Loraにすると調整幅が少なくなりすぎるので3つにまとめました。IR01: Re-BuilderIR02: DetailerIR03: FinisherIR01: Re-Builder(counterfeit V3)IR01 is a very powerful Lora. This is to change a flat anime painted model to a live-action model, and not only change the painting method, but also adjust the balance of the body and face at the same time. If you use a large value for 2.5D or gradient illustrations, it will have a big impact on the body structure. The original picture will easily collapse, so please try starting from around 0.3.Also, the pattern may change significantly. Please decide the value based on how much you want to maintain the atmosphere of the original picture.IR01は非常に強い作用を持ったLoraです。フラットなアニメ塗りのモデルを実写系のモデルに変えるためのものであり,単に塗りの方式を変えるだけでなく,身体や顔のバランスの調整も同時に行っています。2.5Dやグラデ塗りのイラストなどで大きな値で使うと身体構造などに大きな影響を与えます。簡単に元絵が崩壊しますので,最初は0.3くらいから試してみてください。また,絵柄を大きく変える可能性があります。元の絵の雰囲気をどの程度保つかで値を決めてください。IR02: Detailer(facebombmix)IR02 is Lora that affects skin texture etc. Normally, I think you can see a change in the texture of your skin at around 0.4 or 0.5.IR02は肌の質感などに影響を与えるLoraです。通常,0.4か0.5くらいで肌の質感に変化が確認できると思います。IR03: Finisher(meinaV11)IR03 is Lora for photorealism expression and reality enhancement. If you make it stronger, it will look more like an artistic p
Creator notes
InstantRealizer
InstantRealizer is a Lora group for turning illustration models into realistic models. If I used Lora alone, the adjustment range would be too small, so I divided it into three parts.
InstantRealizerは,イラスト系モデルをリアル系モデルにするためのLora群です。単体Loraにすると調整幅が少なくなりすぎるので3つにまとめました。
IR01: Re-Builder
IR02: Detailer
IR03: Finisher
IR01: Re-Builder
(counterfeit V3)
IR01 is a very powerful Lora. This is to change a flat anime painted model to a live-action model, and not only change the painting method, but also adjust the balance of the body and face at the same time. If you use a large value for 2.5D or gradient illustrations, it will have a big impact on the body structure. The original picture will easily collapse, so please try starting from around 0.3.
Also, the pattern may change significantly. Please decide the value based on how much you want to maintain the atmosphere of the original picture.
IR01は非常に強い作用を持ったLoraです。フラットなアニメ塗りのモデルを実写系のモデルに変えるためのものであり,単に塗りの方式を変えるだけでなく,身体や顔のバランスの調整も同時に行っています。2.5Dやグラデ塗りのイラストなどで大きな値で使うと身体構造などに大きな影響を与えます。簡単に元絵が崩壊しますので,最初は0.3くらいから試してみてください。
また,絵柄を大きく変える可能性があります。元の絵の雰囲気をどの程度保つかで値を決めてください。
IR02: Detailer
(facebombmix)
IR02 is Lora that affects skin texture etc. Normally, I think you can see a change in the texture of your skin at around 0.4 or 0.5.
IR02は肌の質感などに影響を与えるLoraです。通常,0.4か0.5くらいで肌の質感に変化が確認できると思います。
IR03: Finisher
(meinaV11)
IR03 is Lora for photorealism expression and reality enhancement. If you make it stronger, it will look more like an artistic photo. Please use with caution as it may affect the color and composition.
IR03はフォトリアリズム系の表現とリアリティ強化のためのLoraです。強くすると,アート的な写真に近くなります。色味や絵柄に影響を与えることもあるので注意して使ってください。
All of these are enhancements to the drawing of the base model, so there is no uniformly recommended value, and each needs to be adjusted individually. As a starting point,
IR01:0.3
IR02:0.4
IR03:0.5
I think it's a good idea to try it from a certain point.
いずれもベースになるモデルの描画に対しての強化となりますので,一律な推奨値は存在せず,それぞれで調整をしていく必要があります。スタートポイントとしては,
IR01:0.3
IR02:0.4
IR03:0.5
くらいから試すのがよいと思います。
Although it is different from the published version, it shows the application status of Lora in Good Old Days.
公開版とは異なりますが,でのLoraの適用状況を示します。
The base model for that was this illustrated model.
From here, we added conceptual processing using Lora and ESD to create a 1960s American style model. The character Lora is almost not used (there is a slight minus added to prevent her Asian face from appearing).
あれのベースモデルはこんなイラストモデルでした。
ここからLoraとESDでの概念処理などを加えて1960年代アメリカ風のモデルに仕上げています。キャラクターLoraはほぼ使用していません(Asian faceが出ないように軽いマイナスで加えたものはあります)。
Important point
-
If you use too much force, the composition and style of the original painting will be lost. The characters are often completely different.
-
Not everything can be made photorealistic. There are some limits. CuteYukiMix was realy tough.
-
The results of application may not necessarily be favorable. Even if you keep the anime face and make it real, it won't be cute at all. It just gets weirder. Although the balance of the face and body has been adjusted to some extent with IR01, the size of facial parts varies greatly from model to model, so adjustments may not be perfect. Please make additional adjustments individually.
(cuteyukimix)
注意点
・強めに使うと元絵の構図や画風は失われます。キャラも全然違うものになることが多いです。
・どんなものでもフォトリアルにできるわけではありません。ある程度限界があります。CuteYukiMixは強敵でした。
・適用した結果が好ましいものになるとは限りません。アニメ顔のままリアルにしても全然可愛くはなりません。奇怪になるだけです。顔や身体のバランスはIR01である程度調整はしていますが,顔パーツの大きさはモデルごとの差も大きく,調整が行き届かないことがあります。個別で追加調整してください。
For models that are already photorealistic, by using IR01 in the negative direction, you can add anime-like elements, such as enlarged eyes, mainly to the face. You may be able to improve the quality by adding IR03.
Even if you don't go photorealistic, you can create a variety of expressions depending on the weight, such as semi-realistic models and artistic works.
すでにフォトリアルなモデルに対しては,IR01をマイナス方向で使うことで主に顔に対して,目が大きくなるなどのアニメ的な要素を加えることができます。IR03を加えることでクオリティアップできることもあります。
フォトリアルまでいかなくても,セミリアルモデルやアート的な作品など,ウェイト次第でいろいろな表現が可能です。
*All tests and adjustments are performed using the LCM sampler. I believe that other samplers will work without problems, but I have not verified this.
SHA256
A48B4BE74CC9AB85EDF622C1E3D7F54CDB835CF20A57E6FE2F98E487E48E0DD5
ModelTrends.ai Model ID
#8736
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
LCM
Steps
15
Guidance
2
Seed
551474305
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(masterpiece, best quality),1girl with long white hair sitting in a field of green plants and flowers, her hand under her chin, warm lighting, white dress, blurry foreground
<lora:L_IR01z3:.6> <lora:L_IR02x1:.4> <lora:L_IR03x2:0.5>
Negative prompt
easynegativeV2
Settings
Sampler
LCM
Steps
14
Guidance
2.5
Seed
3080399038
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(best quality, masterpiece, colorful, dynamic angle, highest detailed) upper body photo, fashion photography of cute, intense long red hair, \Mary Jane\ in spiderman suit, (ultrahigh resolution textures), in dynamic pose, bokeh, glowing web, (intricate details, hyperdetailed:1.15), detailed, moonlight passing through hair, perfect night, fantasy background, (official art, extreme detailed, highest detailed), HDR+
<lora:L_IR01z3:.7> <lora:L_IR02x2:.4> <lora:L_IR03x2:.4>
Negative prompt
easynegative, ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), moles, freckles,
Settings
Sampler
LCM
Steps
10
Guidance
2
Seed
1381636031
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
light particles, soft lighting, volumetric lighting, intricate details, finely detailed,
1girl, solo,
blonde hair, long hair, high ponytail,
red eyes, long eyelashes, thick eyelashes, looking at viewer,
red dress, ornate dress, backless dress, puffy sleeves, juliet sleeves, (long sleeves:1.2), red bow,
black background, simple background, from behind,
<lora:Add Detail:0.4>
<lora:L_IR01z3:.6> <lora:L_IR02x2:.6> <lora:L_IR03x2:.5>
Negative prompt
(EasyNegative:0.8), (worst quality, low quality:1.2),
tight, skin tight, impossible clothes, off shoulder, bare shoulders, bare arms, nude, naked, black dress, white dress, red background,
Settings
Sampler
LCM
Steps
14
Guidance
2
Seed
1263627724
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(masterpiece, best quality), 1girl, collarbone, wavy hair, looking at viewer, blurry foreground, upper body, necklace, contemporary, plain pants, ((intricate, print, pattern)), ponytail, freckles, red hair, dappled sunlight, smile, happy,
<lora:L_IR01z3:.7> <lora:L_IR02x2:.6> <lora:L_IR03x2:.5>
Negative prompt
(worst quality, low quality, letterboxed)
Settings
Sampler
LCM
Steps
14
Guidance
2.5
Seed
3080399038
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(best quality, masterpiece, colorful, dynamic angle, highest detailed) upper body photo, fashion photography of cute, intense long red hair, \Mary Jane\ in spiderman suit, (ultrahigh resolution textures), in dynamic pose, bokeh, glowing web, (intricate details, hyperdetailed:1.15), detailed, moonlight passing through hair, perfect night, fantasy background, (official art, extreme detailed, highest detailed), HDR+
Negative prompt
easynegative, ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), moles, freckles,
Settings
Sampler
LCM
Steps
13
Guidance
2
Seed
529716396
Size
680x900
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
([balloons:Small planets:0.5]:1.4), (Small_planets inside of balloons:1.4), (lots of colorful Small_planets:1.35)
(colorful planets, earth, floating petals, big balloons:1.22),
1 girl, cute face,
Full body, sitting, detailed beautiful eyes, bare legs, costume combination, Goddess, perfect body, [nsfw:0.88]
(sitting on ice_planet:1.22)
(lots of [floting blue Butterflies:floting ice:0.4]:1.22)
(detailed light), (an extremely delicate and beautiful), volume light, best shadow,cinematic lighting, Depth of field, dynamic angle, Oily skin,
<lora:L_IR01z3:.7> <lora:L_IR02x2:.7> <lora:L_IR03x2:.3>
Negative prompt
(worst quality, low quality, blurry:1.66), (bad hand:1.4), watermark, (greyscale:0.88), multiple limbs, (deformed fingers, bad fingers:1.2), (ugly:1.3), monochrome, horror, geometry, bad anatomy, bad limbs, (Blurry pupil), (bad shading), error, bad composition, Extra fingers, strange fingers, Extra ears, extra leg, bad leg, disability, Blurry eyes, bad eyes, Twisted body, confusion, (bad legs:1.3)
Settings
Sampler
LCM
Steps
14
Guidance
2
Seed
1502709202
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(masterpiece, best quality), dark-skinned female, ((intricate)), traditional clothes, desert, bracelet, town, hair ornament, jewelry, leaning back, looking at viewer, upper body, plateau, sandstorm,
<lora:L_IR01z3:.9> <lora:L_IR02x2:.8> <lora:L_IR03x2:.8>
Negative prompt
(worst quality, low quality, letterboxed)
Settings
Sampler
LCM
Steps
18
Guidance
2
Seed
3080399038
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1>
(best quality, masterpiece, colorful, dynamic angle, highest detailed) upper body photo, fashion photography of cute, intense long red hair, \Mary Jane\ in spiderman suit, (ultrahigh resolution textures), in dynamic pose, bokeh, glowing web, (intricate details, hyperdetailed:1.15), detailed, moonlight passing through hair, perfect night, fantasy background, (official art, extreme detailed, highest detailed), HDR+
<lora:L_IR01z3:.4> <lora:L_IR02x2:.5> <lora:L_IR03x2:.3>
Negative prompt
easynegative, ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), moles, freckles,
Similar Models
AI Models for Image, Video & Text Generation
instantrealizer rebuilder is a LoRA 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.
More Stable Diffusion 1.5 modelsMore Stable Diffusion 1.5 LoRAsrealisticanimeexpressionseffectsgraphic-designartstylesstylestools
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
332
Hunyuan Models
198
Ideogram Models
20
Krea2 Models
675
Qwen Models
17
Qwen2 Models
37
Ltx2 Models
151
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
920

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved
