Model
.ai
tracking open ai models

Replace Subject [Klein 4B & 9B]

8244°
Replace Subject [Klein 4B & 9B]
Created by
ReltivlyObjectv
on Civitai
by ReltivlyObjectv - Replace Subject [Klein 4B & 9B]
Creator notes
Allows you to replace a subject in the first control image with a subject in the second control image. The model will skew towards preserving existing details if the secondary control image does not include the relevant details and the prompt leaves them unspecified. For example, if you are using a head/torso image as the new subject, but the original image was zoomed out more and the person being replaced has jeans, the new person will also be wearing jeans unless you specify otherwise. For best results, try to have comparable framing, camera angle, and number of subjects in both images. replace the person in Image 1 with the person in Image 2 replace the man in Image 1 with the man in Image 2 replace the woman in Image 1 with the woman in Image 2 Model Comparisons: - will preserve the subject and background in Control 1, while bringing the framing/pose of Control 2 - will preserve the framing/pose and background in Control 1, while bringing the subject of Control 2 - will preserve the subject and pose in Control 1, while bringing the background scene of Control 2 California AB 2013 Training Data Disclosure - This LoRA was fine-tuned using visual data consisting entirely of synthetic still images. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution. - The dataset consists of over 100 image sets (over 300 images total). This is the total used for training after low quality sets were culled. Dataset was created in 2026. - Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset. - This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.
Trigger words
replace the person in Image 1 with the person in Image 2
replace the man in Image 1 with the man in Image 2
replace the woman in Image 1 with the woman in Image 2
2,271 downloads · 150 likes on Civitai
SHA256
0FD02736097F1570DA1EA0C0D8E5E584E77E2B0202EB7A8880629D3373850080
Ranking badge
Updated Oct 22, 2026
Replace Subject [Klein 4B & 9B] on ModelTrends.ai: #12 Hottest Flux 2 / Klein LoRA
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #408 Hottest AI model · #14 Hottest Flux 2 / Klein model
Not this creator?
Replace Subject [Klein 4B & 9B] Popularity Trend
Heat score since 31 Mar 2026
Heat score
8,244°
This week
▲
0.2%
8,245° then, 8,244° now
This month
▲
1.2%
8,248° then, 8,244° now
Past year
n/a
Wasn't released/tracked
Replace Subject [Klein 4B & 9B]: Heat score since 31 Mar 20267,000°7,389°7,778°8,168°8,557°Apr 2026May 2026Jun 2026Jul 2026Sep 2026Oct 20268,244°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.
+1,021°
Civitai downloads
2,271 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.
+327°
Likes
150 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+42°
Adoption rate
About 3 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
−146°
Age
−146° because the Flux2 weights came out in 2025. 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 8,244°, 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.
    2,271 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.
    +1,021°
    8,021°
    running total
  3. 3
    Add the likes.
    150 likes and thumbs up, at half the weight of a download.
    +327°
    8,348°
    running total
  4. 4
    Add the adoption rate.
    About 3 downloads a day right now, measured between two readings, at a quarter of the weight.
    +42°
    8,390°
    running total
  5. 5
    Take off the age.
    The Flux2 weights came out in 2025: 150° a year, up to 750°, growing until then.
    −146°
    8,244°
    running total
  6. =
    The heat score.
    Where this model stands on every list of this site. Nothing else adjusts it.
    8,244°
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.
Example render 1
Example render 2
Example render 3
Example render 4
Example render 5
Example render 6
Example render 7
Example render 8
NSFW render, blurred. Turn NSFW on to see it.
Settings
Sampler
Euler a
Seed
1054502373254237
Size
928x1120
Prompt
replace the man on the right in Image 1 with creature in Image 2. preserve the pitchfork, the creature is holding the pitchfork.
Settings
Sampler
Euler
Seed
19467227133499
Size
832x1264
Prompt
replace the woman in Image 1 with creature in Image 2.
Render by ReltivlyObjectv on
Civitai
·
Prompt on BunchaPrompts
Flag
Settings
Sampler
Euler
Size
1844x2868
Prompt
replace the woman in Image 1 with the woman in Image 2
No prompt was shared with this render.
Settings
Sampler
Euler
Size
2148x3172
Prompt
replace the woman in Image 1 with the woman in Image 2
Settings
Sampler
Euler
Size
1852x2876
Prompt
replace the woman in Image 1 with the woman in Image 2
Settings
Sampler
Euler
Size
1049x1988
Prompt
replace the woman in Image 1 with the woman in Image 2
Settings
Sampler
Euler
Size
982x1902
Prompt
replace the woman in Image 1 with the woman in Image 2, long bard skirt
Run Locally
KleinBase9B_ReplaceSubject.safetensors
79 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.