Patakbuhin nang lokal
public_v3.0-locon.safetensors
19 MB · SafeTensor
Ang mga download ay mula sa Civitai. May mga gumawa na humihingi muna ng Civitai login.
AD
I-install / Patakbuhin sa Graydient
Nangangailangan ng membership
<public-photo>
Tungkol sa model na ito
STABLE DIFFUSION 1.5 · Mga LoRA
LoRA trained to generate a person in public surrounded by people, such as photographers. Works with other LoRas and various anime and semi-real models. Try it out with , , and . If you want more people in the background, use a wider size, like 832x640, or reverse it for better focus on the character. Keep weight at around 0.8-0.9. The main trigger word ‘public’ is already included as a token. Other helpful prompts are listed in triggers. Example: /render /size:832x640 1girl, photographer, denim shorts, crop top, full body, foreground, camera, cosplay, crowds, ((masterpiece, best quality, highly detailed, intricate, empty hands)), [[lowres, worst_quality, blurry, monochrome]]
Mga tala ng gumawa
Support my work on and and get access to tutorials and exclusive models.
Rate and leave a like if you enjoyed it, and follow for new models!
LoRA trained to generate a person in public surrounded by people, such as photographers. Works with other LoRAs and various models.
UPDATE - new training and small improvements
Updated training: used LyCORIS instead of LoRA, trained on larger dataset with more realistic images, cleaned up tags.
Updated output: less likely to have a camera on character's hands, more detailed crowd, a bit more consistent, you can better increase the crowd or photographers by increasing the trigger tag's weight.
Main tags (use one or both for different effect): public, photographers
// OLD VERSION (1.0) //
Main trigger word: public Other tags used photographer,phone screen,camera,foreground
You can use your usual CFG and weight 1.0
See weight comparison 0.0 vs 1.0, minimal effect on style and composition:
Mga trigger word
public
photographers
SHA256
6C5787BE76348BB00676259FA1076B926D634E306DBFE9260458494D66C39F5B
ModelTrends.ai Model ID
#122
I-flag ang nilalaman
Mga halimbawang render
Mga prompt at setting na ibinahagi ng mga gumawa ng mga render na ito sa Civitai. Pumili ng render para makita kung paano ito ginawa.
Mga setting
Sampler
Euler a
Steps
20
Guidance
7
Seed
2168466583
Laki
512x768
Clip skip
2
Prompt
<lora:public_v3.0-locon:1.0>
public, (photographers:1.2), <lora:koreanDollLikeness_v15:0.4>, 1girl, street, shorts,, masterpiece, best quality, highly detailed
Negative prompt
(worst quality, low quality:1.4)
Mga setting
Sampler
DPM++ 2M Karras
Steps
20
Guidance
7
Seed
2774614232
Laki
512x768
Clip skip
2
Prompt
<lora:public_v3.0-locon:1.0>
public, (photographers:1.0), 1girl, street, shorts, depth of field, foreground,, masterpiece, best quality, highly detailed
Negative prompt
(worst quality, low quality:1.4)
Mga setting
Sampler
DPM++ 2M Karras
Steps
20
Guidance
7
Seed
2774614239
Laki
512x768
Clip skip
2
Prompt
<lora:public_v3.0-locon:1.0>
public, (photographers:1.0), 1girl, face,, masterpiece, best quality, highly detailed
Negative prompt
(worst quality, low quality:1.4)
Mga setting
Sampler
Euler a
Steps
20
Guidance
7
Seed
2774614224
Laki
512x768
Clip skip
2
Prompt
<lora:public_v3.0-locon:1.0>
public, (photographers:1.2), <lora:koreanDollLikeness_v15:0.4>, 1girl, street, shorts,, masterpiece, best quality, highly detailed
Negative prompt
(worst quality, low quality:1.4)
Mga setting
Sampler
Euler a
Steps
20
Guidance
7
Seed
2774614226
Laki
512x768
Clip skip
2
Prompt
<lora:public_v3.0-locon:1.0>
public, (photographers:1.2), <lora:koreanDollLikeness_v15:0.4>, 1girl, street, shorts,, masterpiece, best quality, highly detailed
Negative prompt
(worst quality, low quality:1.4)
Mga setting
Sampler
Euler a
Steps
20
Guidance
7
Seed
1506477162
Laki
512x768
Clip skip
2
Prompt
(masterpiece, best quality), intricate details,
1girl, <lora:katarina-nvwls-v2:0.8>academiaKat, white shirt, necktie, bare shoulders, black jacket, black skirt, thighhighs, high heels, scar over eye,
<lora:public_v3.0-locon:0.8> public, photographers,
Negative prompt
(worst quality:1.4), (low quality:1.4), (monochrome:1.1), easynegative, bad-artist-anime, bad-image-v2-39000, bad_prompt_version2, bad_quality, ng_deepnegative_v1_75t, verybadimagenegative_v1.1-6400, vile_prompt3, bad-hands-5,watermark, font, text, negative_hand-neg, zombie, watermark, username, patreon username, patreon logo, censored, bar censor,
Mga katulad na model
Mga AI model para sa paggawa ng larawan, video at teksto
Ang public photo ay isang LoRA para sa pamilyang Stable Diffusion 1.5 na nakalista sa ModelTrends.ai, isang read-only na catalog ng mga open source AI model para sa larawan, video at teksto. Ikumpara ito sa ibang Stable Diffusion 1.5 model, tingnan ang heat score nito para makita kung gaano ito kasikat, at buksan ito sa PirateDiffusion o BitVector para subukan.
Higit pang Stable Diffusion 1.5 modelHigit pang Stable Diffusion 1.5 Mga LoRAeffectsrealisticanime3dbackgroundsphotographybackground
Mag-browse ayon sa pamilya ng model
Mga Text / LLM model
411
Mga Anima model
509
Mga Chroma model
14
Mga Flux model
1,071
Mga Flux 2 / Klein model
1,237
Mga MiniMax H3 model
331
Mga Hunyuan model
197
Mga Ideogram model
20
Mga Krea2 model
674
Mga Qwen model
17
Mga Qwen2 model
36
Mga Ltx2 model
150
Mga Stable Diffusion 1.5 model
6,465
Mga Stable Diffusion XL 1.0 model
15,432
Mga Zimage model
804
Mga Wan model
919
Model
Trends
.ai
© ModelTrends.ai
|
Gawa sa Japan
|
© 2026