Model
.ai
tracking open ai models

InstantRealizer IR03: Finisher v1.0x2

7171°
InstantRealizer IR03: Finisher v1.0x2
Created by
aueki4g467
on Civitai

__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…__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.
280 downloads · 1 likes on Civitai
SHA256
7C2F76A708CFAB8EDA0BF85F125F2F68A59B68F7148D23226B271D4083B49859
Ranking badge
Updated Oct 22, 2026
InstantRealizer IR03: Finisher v1.0x2 on ModelTrends.ai: Heat 7,171°
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
InstantRealizer IR03: Finisher v1.0x2 Popularity Trend
Heat score, last 12 months
Heat score
7,171°
This week
n/a
Wasn't released/tracked
This month
n/a
Wasn't released/tracked
Past year
n/a
Wasn't released/tracked
InstantRealizer IR03: Finisher v1.0x2: Heat score, last 12 months7,000°7,218°7,437°7,655°7,874°Oct 2025Dec 2025Mar 2026May 2026Aug 2026Oct 20267,171°ModelTrends.ai
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+735°
Civitai downloads
280 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.
+45°
Likes
1 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
−609°
Age
−609° because the SD15 weights came out in 2022. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 7,171°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
  1. 1
    Start at the floor.
    Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
    7,000°
    running total
  2. 2
    Add the downloads.
    280 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
    +735°
    7,735°
    running total
  3. 3
    Add the likes.
    1 likes and thumbs up, at half the weight of a download.
    +45°
    7,780°
    running total
  4. 4
    Take off the age.
    The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
    −609°
    7,171°
    running total
  5. =
    The heat score.
    Where this model stands on every list of this site. Nothing else adjusts it.
    7,171°
Glossary: the terms used here
Heat score
One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor
The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents
Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale
Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes
Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate
How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated
Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder
Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde
A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites
Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens
A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint)
The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding
Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights
The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age
Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost
A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score
A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period)
A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend
How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model
The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Render by aueki4g467 on
Civitai
·
Prompt on BunchaPrompts
Flag
Settings
Sampler
LCM
Steps
10
Guidance
2
Seed
690789066
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1> (((5 beautiful women))), Alexandra, Rosalind,Rosemary,Karin,Katherine <lora:L_IR01z1:0> <lora:L_IR02x1:0> <lora:L_IR03x1:0.8>
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
690789066
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1> (((5 beautiful women))), Alexandra, Rosalind,Rosemary,Karin,Katherine <lora:L_IR01z1:0> <lora:L_IR02x1:0> <lora:L_IR03x1:0.4>
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
690789066
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1> (((5 beautiful women))), Alexandra, Rosalind,Rosemary,Karin,Katherine <lora:L_IR01z1:0> <lora:L_IR02x1:0> <lora:L_IR03x1:0>
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
690789066
Size
512x768
Clip skip
2
Prompt
<lora:LCM_LoRA_Weights_SD15:1> (((5 beautiful women))), Alexandra, Rosalind,Rosemary,Karin,Katherine <lora:L_IR01z1:0> <lora:L_IR02x1:0> <lora:L_IR03x1:0.6>
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,
Run Locally
L_IR03x2.safetensors
144 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.