Bad VHS
Om denna modell
Jämför
STABLE DIFFUSION 1.5 · LoRA
This lora is supposed to emulate the feeling and effects of a VHS tape, visual artifacts and all. During testing, this lora appeared to give the effect of a VHS tape the strongest. Try combining this with other era related loras. Per the author: This model is designed to give the style of an old, poor-quality VHS tape. The safetensors file should now be possible to use natively in Automatic1111! It should be used with the Stable Diffusion 1.5 base model, and I recommend increasing the strength if you want a stronger effect. Around 1.5 seems to work pretty well.
Skaparens anteckningar
This model is designed to give the style of an old, poor-quality VHS tape.
The safetensors file should now be possible to use natively in Automatic1111!
It should be used with the Stable Diffusion 1.5 base model, and I recommend increasing the strength if you want a stronger effect. Around 1.5 seems to work pretty well.
Triggerord
vhs footage of
vhs
SHA256
5A48FC9B542351F7662C41B561509BF9B2C64F3A644253A621AD341D6BDC2FD9
ModelTrends.ai modell-ID
#638
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Sampler
Euler a
Steg
20
Guidance
7
Seed
3573187890
Storlek
640x512
Prompt
VHS footage, robot mech suit walking around New York, no people, <lora:epiNoiseoffset_v2:1> <lora:badVHS_v101:1>
Negativ prompt
Distorted, deformed, warped, distortion, warp, deformation, people
Inställningar
Sampler
Euler a
Steg
20
Guidance
7
Seed
2094108652
Storlek
640x512
Prompt
VHS footage, subway station, dark, no people, <lora:epiNoiseoffset_v2:1> <lora:badVHS_v101:1>
Negativ prompt
Distorted, deformed, warped, distortion, warp, deformation, people
Inställningar
Sampler
DDIM
Steg
28
Guidance
15
Seed
3942008339
Storlek
512x512
Prompt
VHS footage of full figure nousr robot in the desert, wide angle lens photo, holding a pipe
Negativ prompt
goggles, truck, drawing, gore, badly lit, no face, round, cropped, three legs, selfie, painting, cartoon, flcl
Inställningar
Sampler
Euler a
Steg
20
Guidance
7
Seed
1199959
Storlek
640x512
Prompt
VHS footage, indoor pool, dark, no people, <lora:epiNoiseoffset_v2:1> <lora:badVHS_v101:1>
Negativ prompt
Distorted, deformed, warped, distortion, warp, deformation, people
Inställningar
Sampler
DDIM
Steg
21
Guidance
12.5
Seed
2110660711
Storlek
512x704
Prompt
VHS footage analog style cyberpunk portrait of a cute girl, beautiful
Negativ prompt
blur haze naked weapon
Inställningar
Sampler
Euler a
Steg
50
Guidance
7
Seed
1817729451
Storlek
512x512
Prompt
VHS footage, VHS footage, indoor satan party, man in goat mask, dark, no people, <lora:badVHS_v101:1>
Negativ prompt
deformed, warped, distortion, warp, deformation, people
Inställningar
Sampler
DDIM
Steg
18
Guidance
12
Seed
2728951706
Storlek
576x576
Prompt
VHS footage analog style cyberpunk portrait of a soldier, beautiful
Negativ prompt
goggles, truck, drawing, gore, badly lit, no face, round, cropped, three legs, selfie, painting, cartoon, flcl, missing jaw, no mouth, no chin
Inställningar
Sampler
Euler a
Steg
15
Guidance
9
Seed
3442437272
Storlek
640x512
Prompt
VHS footage analog style Lady as a 1960s
Negativ prompt
ugly misshaped clown kitchen
Liknande modeller
How this score adds up
Every number on this site can be checked. The heat score of Bad VHS is 7,905°, and this is the receipt: the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. Hover over or tap any item for a plain-language explanation; the glossary at the end defines every term.
7,000°
7,905°
7,000°
Floor
Every model with real popularity data starts at 7,000°. Models without any data get a lower stand-in number so the lists are never empty, and a stand-in never ranks above a model with data.
+1,117°
Civitai downloads
5,294 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 five download sources share that one term, split between them in proportion to their counts.
+392°
Likes
407 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
−604°
Age of the weights
−604° 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.
= 7,905°
Heat score
Step by step
- 1Start at the floor.Every model with real popularity data begins at 7,000°.7,000°running total
- 2Add the downloads.5,294 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.+1,117°8,117°running total
- 3Add the likes.407 likes and thumbs up, at half the weight of a download.+392°8,509°running total
- 4Take off the age of the weights.The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.−604°7,905°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.7,905°
The same slices over the last twelve months, or since the model's first day. Downloads, likes and runs follow the model's reconstructed curve, the red band is the age penalty as it stood on each date, and the white line is the score. The split between the download sources is today's; the speed, the bonus and the boost are shown as they are today.
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. Numbers below it are stand-ins for models without data.
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.
Download speed
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.
Graydient runs
How often a model has been run on Graydient, counted like downloads.
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 of the weights
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.
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.
Popularitetstrend
Hur den här modellens popularitet har rört sig jämfört med resten av katalogen: dess tillväxt i nedladdningar, gillningar och användning under varje period, mätt mot en typisk modells tillväxt under samma period, med dess heat-poäng vid den tiden. Över den typiska tillväxten ses som en uppgång, under som en nedgång. Det förflutna rekonstrueras från dagens totalsummor, modellens första dag och dess uppmätta nedladdningshastighet där två mätningar finns; en modell som inte fanns i början av en period visar n/a.
Den här veckan
▼
0.6%
7,907° då, 7,905° nu
Den här månaden
▼
2.4%
7,913° då, 7,905° nu
Senaste året
▼
25.9%
7,995° då, 7,905° nu
Ingen andra mätning av källorna än, så kurvan fördelar dagens totalsummor jämnt över modellens livslängd. Den blir tydligare när dagliga synkroniseringar lägger till mätningar.
Först sedd 1 Jan 2023.
Badges for creators
Gjorde du den här modellen? Visa dess placering på din Civitai-sida, din Hugging Face-kort, din README eller din sida. Varje märke är en liten bild som visar placeringen den dag du kopierar den och ändras aldrig efteråt, oavsett hur rankningarna rör sig senare. Datumet är en del av märket. Varje märke länkar tillbaka till den här sidan.
Märkesform
AI-modeller för bild-, video- och textgenerering
Bad VHS är en LoRA för familjen Stable Diffusion 1.5, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra Stable Diffusion 1.5-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.
Fler Stable Diffusion 1.5-modellerFler Stable Diffusion 1.5 LoRAeffectsretrolow qualitybad quality1980s1990svhs
Bläddra efter modellfamilj
Text / LLM-modeller
415
Anima-modeller
519
Chroma-modeller
17
Flux-modeller
1,498
Flux 2 / Klein-modeller
1,239
MiniMax H3-modeller
330
Hunyuan-modeller
204
Ideogram-modeller
20
Krea2-modeller
676
Qwen-modeller
20
Qwen2-modeller
36
Ltx2-modeller
152
Stable Diffusion 1.5-modeller
7,042
Stable Diffusion XL 1.0-modeller
17,420
Zimage-modeller
815
Wan-modeller
1,067

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Alla rättigheter förbehållna
