Model
.ai
tracking open ai models

Fake documentary

7793°
Fake documentary
Created by
vjleoliu
on Civitai
Creator notes
If you enjoy my work, please give me a "like" rating; it means a lot to me! I don't speak English, but I wrote the explanation very carefully. It won't take more than two minutes to read. The following translation is from ChatGPT. 《fake documentary》 At first, I just wanted to create a Lora that could generate old photos. Gradually, I found that old photos have a unique sense of reality and history, so I tried to add some interesting elements to it. This is why I trained dozens of versions until this version emerged, as you can see now, it can create some huge content that does not exist in reality, but still looks real! Of course, it can also create a lot of interesting content, which depends on your imagination. Now I can't wait to see your works! 一开始我只是想创造一个能够生成老照片的lora,渐渐的,我发现老照片具有一种独特的真实感和历史感,所以我尝试为它增加一些有趣的元素,这也就是为什么我训练了数十个版本,直到这个版本的出现,正如你现在所见,它可以创造一些巨大的现实中不存在的内容,但看起来依旧真实!当然,它也可以创作很多有趣的内容,这取决于你的想象力,现在我等不及要看到你们的作品啦! How to do it ? Firstly, during the collection of materials, I found that the color of old photos can be divided into several types, which are: Sepia Old Photo / Yellowed Old Photo / Grayscale Old Photo / Old Photo. As long as you choose any one of them as a trigger word, it will present a picture with different colors (note, do not mix and use them). 首先,在收集资料的时候,我发现老照片的成色可以分成几种,它们分别是:sepia Old Photo / Yellowed Old Photo / grayscale Old Photo / Old Photo,只要你选用任意一种作为触发词,都会呈现出不同成色的画面(注意,不可混用) Secondly, as time goes by, old photos are subject to varying degrees of damage, which I have categorized as: damaged / Light Leaks / Scratches / dust. These can serve as trigger words, and of course, you can include all of them in your prompt. However, to be honest, I did not train it in this way, so the final effect may differ from what you might imagine. 其次,随着时光的流逝,老照片会受到不同程度的破坏,我将它分类为:damaged / Light Leaks / Scratches / dust,作为触发词,你当然可以将它们全部加到提示词中,但坦白讲,我并没有这样训练它,所以最终呈现的效果,可能和你的想象会有些不同。 Finally, as a simulation of old photos, the classification of the era seems to be important as well (though this is not mandatory). Photography was invented by the French in 1839, and taking this as the starting point, I have set up multiple time points as the third category of trigger words. They are as follows: Early 19th Century / in 19th Century / Early 20th Century / 1960s / 1970s / 1980s / 1990s. From the examples above, you can see that as the era gets closer to the present, the colors in the images also become more vivid, which is exactly what I want. 最后,作为模拟老照片,年代划分似乎也很重要(这不是必须的)摄影术是由法国玉1839年发明,以此为起点,我为它设置了多个时间点作为第三类触发词,它们分别是:Early 19th Century / in 19th Century / Early 20th Century / 1960s / 1970s / 1980s / 1990s 从上面的示例中你可以看出,随着年代越来越近,图像的颜色也会越来越鲜活,这就是我想要的。 Alright! Now we have three sets of trigger words that you can combine in any way to test the effect you want to achieve. For example, "sepia old photo," "damaged," "early 19th century," is a good combination. 好啦!现在我们有三组触发词,你可以任意组合它们,来测试你想实现的效果,比如:sepia old photo,damaged,early 19th century,就是一组不错的组合。 How to do it Sampler:DPM++ 2M Karras Steps:39 CFG Scale:6 lora weight:0.3~0.9 Hires.fix:4x_NMKD-Siax_200k Steps:9 Denoising:0.39 Additional notes In addition to these amazing features, you will also find that it still works very well even without using prompt words. It just has a slightly different effect, to be precise, it enhances the film texture of the image, and you don't have to worry about overexposure or being too dark. 除了这些神奇的功能,你还会发现,即使不使用提示词,它仍然能很好的工作,只是功效会有些许不同,准确的说是为画面增强胶片质感,不用担心曝光过度或者黑成一团 I hope you have fun!Peace!
Trigger words
sepia old photo
damaged
early 19th century
2,423 downloads · 376 likes on Civitai
SHA256
8C461B4D282CC7A62C2DCF86BBBFB3AB0F2DE1D979664F136633B42BBA0F2AA1
Ranking badge
Updated Oct 22, 2026
fake documentary on ModelTrends.ai: Up 0.2% this week
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
fake documentary Popularity Trend
Heat score, last 12 months
Heat score
7,793°
This week
▲
0.2%
7,794° then, 7,793° now
This month
▲
0.8%
7,799° then, 7,793° now
Past year
▲
17.2%
7,842° then, 7,793° now
fake documentary: Heat score, last 12 months7,000°7,393°7,785°8,178°8,570°Oct 2025Dec 2025Mar 2026May 2026Aug 2026Oct 20267,793°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.
+1,016°
Civitai downloads
2,423 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.
+386°
Likes
376 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 7,793°, 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.
    2,423 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.
    +1,016°
    8,016°
    running total
  3. 3
    Add the likes.
    376 likes and thumbs up, at half the weight of a download.
    +386°
    8,402°
    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°
    7,793°
    running total
  5. =
    The heat score.
    Where this model stands on every list of this site. Nothing else adjusts it.
    7,793°
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.
Settings
Sampler
DPM++ 2M Karras
Steps
39
Guidance
6
Seed
1275871187
Size
520x960
Clip skip
2
Prompt
sepia old photo, damaged, scratches, dust, light leaks, early 19th century, fantasy, surreal, hyperrealistic, detailed, photo of familly with very giant cat, wearing hanfu, cheongsam, traditional chinese gown, patterned fabric, outdoors, village, <lora:oldPhotoV1:0.9>,
Negative prompt
NSFW, logo, text, sketches, signature, watermark, bad anatomy, bad proportions, out of focus, username,
Render by vjleoliu on
Civitai
·
Prompt on BunchaPrompts
Flag
Settings
Sampler
DPM++ 2M Karras
Steps
39
Guidance
6
Seed
1015044639
Size
520x960
Clip skip
2
Prompt
masterpiece, best quality, highres, hyper detailed, faded old photo, damaged, 1840s, Ancient asian cultural, fantasy, surreal, a real 8 foot tall cow Head Warrior stands with the local villagers, giant, beard, traditional dress, armor, costume, smile, crowd, children, outdoor, village scene, depth of field, <lora:oldPhotoV1:1>,
Settings
Sampler
DPM++ 2M Karras
Steps
39
Guidance
6
Seed
4174894037
Size
520x960
Clip skip
2
Prompt
yellowed old photo, early 19th century, tall giant in the piazza, steel robot frame inside, in the style of fine attention to anatomy, chrome-plated, steel robot frame inside, farm security administration photography, <lora:oldPhotoV1:0.9>,
Negative prompt
NSFW, logo, text, blurry, low quality, sketches, lowres, normal quality, monochrome, grayscale, worstquality, signature, watermark, bad anatomy, cropped, bad proportions, out of focus, username, stubble,
Render by celticwolf72 on
Civitai
·
Prompt on BunchaPrompts
Flag
Settings
Sampler
Euler a
Steps
25
Guidance
3.5
Seed
383090442
Size
512x768
Clip skip
2
Weight used
1
Prompt
solo, anthro female red fox, long black hair with detailed green eyes, victorian eyeglasses, silk black victorian dress, sad, crying, BREAK, mourning her dead lover, in a victorian graveyard, graveyard, holding a letter with tear stains, BREAK, outside, dreary lighting, rain, dark clouds, sepia tone
Negative prompt
watermark, signature, patreon, subscribestar, ribcage, featureless, multiple anus, sketch, worst quality, low quality, simple background, bad anatomy, bad hands, malformed hands, deformed limbs, blurry, cross-eyed, glowing eyes, extra arms, speech bubble, extra legs, extra limbs, bad proportions, missing fingers, missing legs, poorly drawn hands, signature, text, bad feet, watermark, flat background, ugly, bad legs, bara, big belly, muscular, abdominal muscles, hyper penis, hyper, large breasts, (human: 1.4, humans, loli, shota), bad anatomy, futa, ((skin)),
Run Locally
oldPhoto_v1.0.safetensors
144 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.