Lokaal uitvoeren
BG2_dpep4+silicon29dim64.safetensors
72 MB · SafeTensor
Downloads worden geleverd door Civitai. Sommige makers vragen eerst om in te loggen op Civitai.
AD
Installeren / Uitvoeren op Graydient
Lidmaatschap vereist
<background-tweak>
Over dit model
STABLE DIFFUSION 1.5 · LoRA's
Background Complexity Additive by Jemnite This LoRA helps to increase the complexity and prominence of your backgrounds. This reduces the style, coloring, clothing, anatomy or facial details. Play around with positive and negative weights.
Notities van de maker
This model is meant to enhanced the complexity and prominence of your backgrounds. It's made by combining background-focused loras and then target isolating blocks to reduce the effect on things like style, clothing, coloring, anatomy, or facial details.
In practice it's a bit finicky. The primary observed effect it that without any tags for shot distance, it will make your background take up more space. It won't necessarily make your background better, persay, but will increase the number of visible background elements, their density, and their prominence. In the case of images where you want one extremely prominent backdrop or you want your character to be silhouetted against the backdrop it actually might be better not to prompt it or prompt it negative, as prompting it negative will creat the opposite effect. Because of the way it's block isolated, you can prompt it at strong weights without it making your picture look like a complete mess. I recommend toying with both positive and negative weights if you decide to use it, as both create interesting outcomes.
If you prompt for an image that only has landscape/scenery, prompting it will increase coherency. Likewise, negative prompting it will make the landscape make less sense. Both have their own uses.
SHA256
D688ED2D2AB851959FCCFC0F49D1034EA74DB2F23466034AF88349FDAC131676
ModelTrends.ai model-ID
#6022
Inhoud melden
Voorbeeldrenders
Prompts en instellingen gedeeld door de mensen die deze renders op Civitai maakten. Kies een render om te zien hoe hij is gemaakt.
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
4240270297
Formaat
832x1216
Clip skip
2
Prompt
<lora:PM_WalkingWake_a1_4_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big:0.8>,score_9,score_8_up,score_7_up,source_furry,walkingwake,feral,by zackary911,by syuro,by dagasi,by hanuvo,solo,hi res,detailed background,forest,
looking at viewer,extreme detail,dynamic lighting,cinematic lighting,side view,eyes closed,sleeping,on front,curled tail,
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
4209706688
Formaat
832x1216
Clip skip
2
Prompt
<lora:MC_EnderDragon_a1_3_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big>,score_9,score_8_up,score_7_up,source_furry,enderdragon,anthro,female,by zackary911,by syuro,by hanuvo,solo,hi res,detailed background,forest,
looking at viewer,purple eyes,no sclera,white pupils,raised tail,open smile,cargo shorts,crop top,hand on hip,black wings,purple tongue,
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
3743064068
Formaat
832x1216
Clip skip
2
Prompt
<lora:MC_EnderDragon_a1_3_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big>,score_9,score_8_up,score_7_up,source_furry,enderdragon,feral,by zackary911,by syuro,by hanuvo,solo,hi res,detailed background,forest,sky,
looking at viewer,purple eyes,no sclera,white pupils,open mouth,black wings,purple tongue,low-angle view,flying,action pose,
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
814377768
Formaat
832x1216
Clip skip
2
Prompt
<lora:LoL_Kindred_a1_12_PonyXL_spnckpt1_th-1.4>,<lora:TOTO_Inaxtoto__bebebebe_Style_Lora:0.7>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:XDetail_light:1.1>,score_9,score_8_up,score_7_up,kindlamb,anthro,female,solo,hi res,detailed background,forest,
leaning back,blue eyes,mask,crop top,cargo shorts,hand on hip,
Negatieve prompt
deviantart,source_pony,source_3d,(source_cartoon:0.5),score_5,score_4,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
2660742945
Formaat
832x1216
Clip skip
2
Prompt
<lora:MC_EnderDragon_a1_3_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big>,score_9,score_8_up,score_7_up,source_furry,enderdragon,feral,by zackary911,by syuro,by hanuvo,solo,hi res,detailed background,forest,
looking at viewer,purple eyes,no sclera,white pupils,hand on ground,side view,open mouth,black wings,purple tongue,
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
2473654860
Formaat
832x1216
Clip skip
2
Prompt
<lora:SM_Yoshi_a1_2_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big>,score_9,score_8_up,score_7_up,source_furry,smyoshi,feral,by zackary911,by syuro,by dagasi,by hanuvo,solo,hi res,detailed background,forest,
looking at viewer,extreme detail,dynamic lighting,cinematic lighting,black eyes,shoes,red shell,side view,smirk,orange scales,(leaning forward),
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,spiked shell,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
1746100117
Formaat
832x1216
Clip skip
2
Prompt
<lora:MH_PukeiPukei_a1_10_PonyXL_spnckpt1_th-1.4>,<lora:TOTO_Inaxtoto__bebebebe_Style_Lora:0.7>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:XDetail_light:1.2>,score_9,score_8_up,score_7_up,pukeipukei,anthro,female,solo,hi res,detailed background,forest,
yellow eyes,(slit pupils:0.7),tongue out,blep,forked tongue,clawed fingers,winged arms,half-length portrait,(raised tail),crop top,cargo shorts,detailed eyes,
Negatieve prompt
deviantart,source_pony,source_3d,(source_cartoon:0.5),score_5,score_4,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Instellingen
Sampler
DPM++ 2M Karras
Stappen
30
Guidance
7
Seed
2869343124
Formaat
832x1216
Clip skip
2
Prompt
<lora:MH_TobiKadachi_a1_7_PonyXL>,<lora:BG2_dpep4+silicon29dim64:1>,<lora:PDXL_artist_tags_v2_big>,score_9,score_8_up,score_7_up,source_furry,tobi-kadachi,feral,by zackary911,by syuro,by dagasi,by hanuvo,solo,hi res,detailed background,forest,
looking at viewer,extreme detail,dynamic lighting,cinematic lighting,red eyes,no sclera,slit pupils,hand on ground,action pose,open mouth,low-angle view,running towards viewer,raised tail,dutch angle,speed lines,blue scales,dark blue scales,
Negatieve prompt
deviantart,source_anime,source_3d,source_cartoon,url,border,artist signature,patreon,low detail,sketch,text,speech bubble,vignette,
Vergelijkbare modellen
AI-modellen voor het genereren van afbeeldingen, video en tekst
background tweak is een LoRA voor de Stable Diffusion 1.5-familie, vermeld op ModelTrends.ai, een alleen-lezen catalogus van open source AI-modellen voor afbeeldingen, video en tekst. Vergelijk het met andere Stable Diffusion 1.5-modellen, bekijk de populariteitsscore om de trend te zien en open het op PirateDiffusion of BitVector om het te proberen.
Meer Stable Diffusion 1.5-modellenMeer Stable Diffusion 1.5 LoRA'sclothingbackgroundspositivesscenerylightingbackground
Bladeren op modelfamilie
Text / LLM-modellen
411
Anima-modellen
509
Chroma-modellen
14
Flux-modellen
1,071
Flux 2 / Klein-modellen
1,237
MiniMax H3-modellen
331
Hunyuan-modellen
197
Ideogram-modellen
20
Krea2-modellen
674
Qwen-modellen
17
Qwen2-modellen
36
Ltx2-modellen
150
Stable Diffusion 1.5-modellen
6,465
Stable Diffusion XL 1.0-modellen
15,432
Zimage-modellen
804
Wan-modellen
919

Model
Trends
.ai
© ModelTrends.ai
|
Gemaakt in Japan
|
© 2026
