Om denna modell
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
AI-modeller för bild-, video- och textgenerering
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
411
Anima-modeller
509
Chroma-modeller
14
Flux-modeller
1,071
Flux 2 / Klein-modeller
1,237
MiniMax H3-modeller
331
Hunyuan-modeller
197
Ideogram-modeller
20
Krea2-modeller
674
Qwen-modeller
17
Qwen2-modeller
36
Ltx2-modeller
150
Stable Diffusion 1.5-modeller
6,465
Stable Diffusion XL 1.0-modeller
15,432
Zimage-modeller
804
Wan-modeller
919

Model
Trends
.ai
© ModelTrends.ai
|
Tillverkad i Japan
|
© 2026
