Model
Trends
.ai
Model
Trends
.ai
model AI open source terbaik
Jalankan secara lokal
figma.safetensors
148 MB · SafeTensor · fp16 · full
Unduhan disediakan oleh Civitai. Beberapa kreator meminta login Civitai terlebih dahulu.
AD
Pasang / Jalankan di Graydient
Memerlukan keanggotaan
<toy-figmas>
Tentang Model Ini
STABLE DIFFUSION 1.5 · LoRA
Dibuat oleh
robowaifudev
di Civitai
A LoRA inspired by the Figma figure series of highly poseable collectible toys, by model creator STMA. A base of or similar with a weight of 0.6 is recommended, though as high as 1.15 can also work well. Recommended prompts: Positives: realistic, 3d, 3dcg, ((octane render)), fisheye Negatives: [[simple background, grey background]]
Catatan pembuat
Note: I did not train these LoRA models myself. Original source: Recommended settings Quick start - Model: - LoRA weight: 0.6 (UNet: 0.6, TEnc: 0.25) - [realistic], [3d], (3dcg), ((octane render)), [fisheye] in positive prompt for realism - simple background, grey background in negative prompt - CLIP skip: 2 - Sampler: DPM++ SDE Karras (Euler a recommended for other models) - in negative prompt Usable - LoRA weight range: 0.2 - 1.15 (UNet: 0.35 - 1.15 TEnc: 0.2 - 1.0) UNet is required for the style. UNet over 0.65 will look like an anime figure product. Too high UNet weight will melt details. Lower TEnc weight will improve generalization. High TEnc will affect composition to look more like an anime figure product photo. Too high will fry the details. Start with lower weight and increase as necessary. Requires more weight when mixed with TI embeddings and other LoRAs. Figma Trained on 5,746 images scraped from GoodSmile's international catalogue, including the discontinued products. All images were tagged with figma first and the product name with figma stripped out second, so an image from a product named "figma Hatsune Miku" would be tagged figma, hatsune miku. All other tags came from the WD1.4 tagger. 3d and realistic tags seem to work well with it. The alpha16 version is better at generalizing, while the 7e-5 version is better at capturing the figure-with-transparent-stand look. Example images Model - (TODO: update example images to ) Textual inversion - (character) roxy-migurdia - (character) megumin_1000 - (composition) chartuner - EasyNegative - bad_prompt Additional LoRA - (charater) yelan \(genshin impact\) - (style) torino aqua
Kata pemicu
figma
31,512 unduhan · 2,270 suka di Civitai
SHA256
6F6D687FE041FCDC0FE55B9CD90AE7634DC50EBC9DA849DC869B232A8DF60F9D
ID Model ModelTrends.ai
#81
Laporkan konten
Contoh render
Prompt dan pengaturan yang dibagikan oleh orang-orang yang membuat render ini di Civitai. Pilih sebuah render untuk melihat cara membuatnya.
Pengaturan
Sampler
DPM++ 2M Karras
Langkah
30
Guidance
6
Seed
3190895564
Ukuran
512x512
Prompt
Deer human hybrid, figma <lora:figma1:1> ((photograph)), highly detailed, sharp focus, 8k, 4k, (hyperrealism),(micro details), colorful, Beautiful environment, Portfolio piece, Fantastic location, beautiful artwork
Prompt negatif
naked, nude,
Pengaturan
Sampler
DPM++ SDE Karras
Langkah
24
Guidance
7
Seed
3792106495
Ukuran
344x512
Clip skip
2
Prompt
(masterpiece, best quality, absurdres, foreshortening, from_above, fisheye:1.2), photo of a highly detailed (figma) of (hastune miku:1.2), 1girl, solo, [realistic], rendered in blender
Prompt negatif
EasyNegative, bad-prompt, worst quality, bad quality, simple background, lineart, flat colors, lowres
Pengaturan
Sampler
Euler a
Langkah
30
Guidance
7
Seed
2859361378
Ukuran
512x768
Clip skip
2
Prompt
looking at viewer, (braixen, pokemon, holding stick, fur), <lora:figmaAnimeFigures_figma:0.6>, ((figma)), (standing), <lora:braixenLora_v1:0.8>
Prompt negatif
Easynegative
Pengaturan
Sampler
Euler a
Langkah
20
Guidance
7
Seed
1744601637
Ukuran
800x1000
Clip skip
2
Prompt
<lora:figmaAnimeFigures_figma:1.1>,muscular, cute (chihuahua:1.2), dog, bodybuilder_pose,dog collar, muscular male, abs, clenched hands, between babel, standing, no humans, navel, animal,arm joint , realistic, dog ears, veins,furry <lora:bulkedupAI_bulkedupAIR15:0.37> ,gym,detail texture,
Pengaturan
Sampler
Euler a
Langkah
20
Guidance
7
Seed
3961300275
Ukuran
536x536
Clip skip
2
Prompt
masterpiece, best quality <lora:kana_kashiwazaki-000008:0.55> 1girl ,(solo), kanakashiwazaki, aqua eyes, yellow ribbon kanakashiwazaki, yellow ribbon, aqua eyes,(geisterjaeger uniform), thighhighs, black jacket, fingerless gloves, belt, cleavage, medium breasts, long sleeves, (standing), upper body, { <lora:animemix_16:0.8> |<lora:animemix_v3_offset:0.8> |<lora:animeoutlineV4_16:0.8> (lineart, monochrome) |<lora:animetarotV51:0.8> |<lora:anmnr01AOM3A1:1> ANMNR |<lora:Crayon drawing:1> HAU_FNEG |<lora:figma:0.8> figma |<lora:Hyohon:0.8> hyohon |<lora:IrisCompietStyle:0.9> ( watercolor \(medium\), IrisCompiet:1.2), painting of |<lora:marvin:0.66> MANGA, GREYSCALE, MONOCHROME |<lora:Necronomicon-10:0.8> (Necronomicon Sketch) |<lora:pixel-portrait-v1:0.8> |<lora:pixel_f2:0.6> pixel |<lora:pixelartV3:0.8> pixelart |<lora:pk_trainer768_V1:0.8> |<lora:SketchStyle:0.75> WHITE BACKGROUND, SKETCH BY NTY, |<lora:add_detail:-2> |<lora:add_detail:-1.5> |<lora:add_detail:-1> |<lora:add_detail:-0.5> |<lora:add_detail:0> |<lora:add_detail:0.5> |<lora:add_detail:1> |<lora:add_detail:1.5> |<lora:add_detail:2> [(anime screencap:1):0.34] [(anime screencap:1.1):0.34] [(anime screencap:1.2):0.34] [(anime screencap:1.3):0.34] [(anime screencap:1.4):0.34] |<lora:80sv1:0.5> 1980S \(STYLE\) |<lora:90s_steel:0.6> (1990s, 90s), |<lora:90sv1.6R:0.6> 1980S \(STYLE\), retro artstyle |<lora:90sv2.0R:0.6> 1980S (STYLE), RETRO ARTSTYLE |<lora:1990's_PC_v2:0.6> 1990's_PC |<lora:Akabur:0.65> |<lora:akebi:1> akebi |<lora:ARTbyJCM2_MMM:0.8> |<lora:as109_128_dim128_dp0.95:1> |<lora:avatar_wan_offset:1> AVATAR WAN |<lora:bb-style:0.6> |<lora:bocchi_style_offset:1> bocchi style |<lora:comiclo:1> |<lora:COOLKIDS_MERGE_V2.5:1> |<lora:DarkestDungeonV2:0.6> DDSTYLE,darkest dungeon, |<lora:dithering2:1> DITHERING,PIXEL ART,HALFTONE,PATTERN, |<lora:elf-pc-98:1> retro artstyle |<lora:evangelion_anime_style_offset:1> EVANGELION ANIME STYLE, anime screencap, 1990s_\(style\) |<lora:flowergirl:0.9> shukezouma,(illustration:1.1),(best quality),(masterpiece:1.1), (solo:1.2),highres, (ink splashing),(watercolor), |<lora:gbaportrait:0.7> gbaportrait |<lora:ghibli_style_offset:0.8> ghibli style |<lora:Haruhiko Mikimoto_v30:0.7> 1980s (style) |<lora:junji_ito:0.75> junji_ito style |<lora:koe_no_katachi_offset:1> KOE NO KATACHI |<lora:lego_v2.0:0.8> LEGO MiniFig, |<lora:LONA09:0.8> |<lora:lucky_star_offset:1> |<lora:lwa_offset:1> LWA |<lora:MoXinV1:0.8> SHUIMOBYSIM, WUCHANGSHUO, BONIAN, ZHENBANQIAO, BADASHANREN |<lora:persona5_anime_style_offset:1> PERSONA5 ANIME STYLE |<lora:LONA06:0.8> |<lora:Pmini_v3.5.18:0.8> PMINI STYLE, MINIATURE, on a base |<lora:Retro-V1:1> 1980S (STYLE), RETRO STYLE, |<lora:Retro_ANIME_V1:1> Retro_ANIME_V1 |<lora:shanzhagao128dim-epoch-000010:1> HANFU, RED LIPS, LIGHT RAYS, EAST ASIAN ARCHITECTURE |<lora:sakura_wars_v1:0.8> |<lora:shinkai_makoto_offset:1> SHINKAI MAKOTO, KIMI NO NA WA, TENKI NO KO, KOTONOHA NO NIWA |<lora:smv1-10:0.8> |<lora:soejima_shigenori:0.8> SOEJIMA SHIGENORI |<lora:StyleTD:1> |<lora:sxz-2dicon:0.8> 2dicon of, 2dicon portrait of |<lora:takada_akemi_offset:1> TAKADA AKEMI, 1980S \(STYLE\), RETRO ARTSTYLE |<lora:the_legend_of_korra_v2_offset:0.8> the legend of korra |<lora:western_animation_style:0.8> |<lora:xrs2.0:0.8> |<lora:yukiyoshi_mamizu:0.7> YUKIYOSHI MAMIZU |<lora:FE13 Style v2:0.7> FE13, FE13-STYLE, FIRE EMBLEM, FIRE EMBLEM AWAKENING |<lora:FE15 Style NAI:0.7> FE15, FE15-Style, Fire Emblem, Fire Emblem Shadows of Valentia |<lora:FE14 Style:0.7> FE14 Style,FE14,FE14-STYLE,FIRE EMBLEM,FIRE EMBLEM FATES |<lora:FE16 Style LoCon:1> fire emblem,FE16, FE16-STYLE,FIRE EMBLEM THREE HOUSES, |<lora:FE16-Style LoCon v2:1> fire emblem,FE16, FE16-STYLE,FIRE EMBLEM THREE HOUSES, |<lora:kyoto animation_artstyle_LoCon:0.5> |<lora:Ufussy:0.6> UFOTABLE STYLE, ANIME COLORING, ANIME SCREENCAP |<lora:surprised_v200:0.8> surprised }
Prompt negatif
badhandv4 EasyNegative, piercing, child,young,nsfw,naked,nude, Watermark, Text, censored, deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, cropped, worst quality, low quality, mutation, poorly drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, Abnormal hands, abnormal legs, abnormal feet, abnormal fingers
Pengaturan
Sampler
Euler
Langkah
8
Guidance
1
Seed
2277126973
Ukuran
1024x1024
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, source_anime, white background, figure style,photorealistic,photo \(medium\), doro, creature, chibi, :3, no humans, solid circle eyes, no pupils, white skin, four legs, hakurei reimu
Prompt negatif
3d, censored, monochrome
Pengaturan
Sampler
Euler a
Langkah
20
Guidance
7
Seed
2785563550
Ukuran
480x640
Clip skip
2
Prompt
masterpiece, best quality, 1girl, (solo), ({__age__}) {__hair_colors__}, {__eye_colors__}, {__hair_styles__}, ({__clothes__}:1.2) {__background__}, {__setting__} { <lora:animemix_16:0.8> |<lora:animemix_v3_offset:0.8> |<lora:animeoutlineV4_16:0.8> (lineart, monochrome) |<lora:animetarotV51:0.8> |<lora:anmnr01AOM3A1:1> ANMNR |<lora:Crayon drawing:1> HAU_FNEG |<lora:figma:0.8> figma |<lora:Hyohon:0.8> hyohon |<lora:IrisCompietStyle:0.9> ( watercolor \(medium\), IrisCompiet:1.2), painting of |<lora:marvin:0.66> MANGA, GREYSCALE, MONOCHROME |<lora:Necronomicon-10:0.8> (Necronomicon Sketch) |<lora:pixel-portrait-v1:0.8> |<lora:pixel_f2:0.6> pixel |<lora:pixelartV3:0.8> pixelart |<lora:pk_trainer768_V1:0.8> |<lora:SketchStyle:0.75> WHITE BACKGROUND, SKETCH BY NTY, |<lora:add_detail:-2> |<lora:add_detail:-1.5> |<lora:add_detail:-1> |<lora:add_detail:-0.5> |<lora:add_detail:0> |<lora:add_detail:0.5> |<lora:add_detail:1> |<lora:add_detail:1.5> |<lora:add_detail:2> [(anime screencap:1):0.34] [(anime screencap:1.1):0.34] [(anime screencap:1.2):0.34] [(anime screencap:1.3):0.34] [(anime screencap:1.4):0.34] |<lora:80sv1:0.5> 1980S \(STYLE\) |<lora:90s_steel:0.6> (1990s, 90s), |<lora:90sv1.6R:0.6> 1980S \(STYLE\), retro artstyle |<lora:90sv2.0R:0.6> 1980S (STYLE), RETRO ARTSTYLE |<lora:1990's_PC_v2:0.6> 1990's_PC |<lora:Akabur:0.65> |<lora:akebi:1> akebi |<lora:ARTbyJCM2_MMM:0.8> |<lora:as109_128_dim128_dp0.95:1> |<lora:avatar_wan_offset:1> AVATAR WAN |<lora:bb-style:0.6> |<lora:bocchi_style_offset:1> bocchi style |<lora:comiclo:1> |<lora:COOLKIDS_MERGE_V2.5:1> |<lora:DarkestDungeonV2:0.6> DDSTYLE,darkest dungeon, |<lora:dithering2:1> DITHERING,PIXEL ART,HALFTONE,PATTERN, |<lora:elf-pc-98:1> retro artstyle |<lora:evangelion_anime_style_offset:1> EVANGELION ANIME STYLE, anime screencap, 1990s_\(style\) |<lora:flowergirl:0.9> shukezouma,(illustration:1.1),(best quality),(masterpiece:1.1), (solo:1.2),highres, (ink splashing),(watercolor), |<lora:gbaportrait:0.7> gbaportrait |<lora:ghibli_style_offset:0.8> ghibli style |<lora:Haruhiko Mikimoto_v30:0.7> 1980s (style) |<lora:junji_ito:0.75> junji_ito style |<lora:koe_no_katachi_offset:1> KOE NO KATACHI |<lora:lego_v2.0:0.8> LEGO MiniFig, |<lora:LONA09:0.8> |<lora:lucky_star_offset:1> |<lora:lwa_offset:1> LWA |<lora:MoXinV1:0.8> SHUIMOBYSIM, WUCHANGSHUO, BONIAN, ZHENBANQIAO, BADASHANREN |<lora:persona5_anime_style_offset:1> PERSONA5 ANIME STYLE |<lora:LONA06:0.8> |<lora:Pmini_v3.5.18:0.8> PMINI STYLE, MINIATURE, on a base |<lora:Retro-V1:1> 1980S (STYLE), RETRO STYLE, |<lora:Retro_ANIME_V1:1> Retro_ANIME_V1 |<lora:shanzhagao128dim-epoch-000010:1> HANFU, RED LIPS, LIGHT RAYS, EAST ASIAN ARCHITECTURE |<lora:sakura_wars_v1:0.8> |<lora:shinkai_makoto_offset:1> SHINKAI MAKOTO, KIMI NO NA WA, TENKI NO KO, KOTONOHA NO NIWA |<lora:smv1-10:0.8> |<lora:soejima_shigenori:0.8> SOEJIMA SHIGENORI |<lora:StyleTD:1> |<lora:sxz-2dicon:0.8> 2dicon of, 2dicon portrait of |<lora:takada_akemi_offset:1> TAKADA AKEMI, 1980S \(STYLE\), RETRO ARTSTYLE |<lora:the_legend_of_korra_v2_offset:0.8> the legend of korra |<lora:western_animation_style:0.8> |<lora:xrs2.0:0.8> |<lora:yukiyoshi_mamizu:0.7> YUKIYOSHI MAMIZU |<lora:FE13 Style v2:0.7> FE13, FE13-STYLE, FIRE EMBLEM, FIRE EMBLEM AWAKENING |<lora:FE15 Style NAI:0.7> FE15, FE15-Style, Fire Emblem, Fire Emblem Shadows of Valentia |<lora:FE14 Style:0.7> FE14 Style,FE14,FE14-STYLE,FIRE EMBLEM,FIRE EMBLEM FATES |<lora:FE16 Style LoCon:1> fire emblem,FE16, FE16-STYLE,FIRE EMBLEM THREE HOUSES, |<lora:FE16-Style LoCon v2:1> fire emblem,FE16, FE16-STYLE,FIRE EMBLEM THREE HOUSES, |<lora:kyoto animation_artstyle_LoCon:0.5> |<lora:Ufussy:0.6> UFOTABLE STYLE, ANIME COLORING, ANIME SCREENCAP |<lora:surprised_v200:0.8> surprised }
Prompt negatif
badhandv4 EasyNegative, Watermark, Text, censored, deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, cropped, worst quality, low quality, mutation, poorly drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, Abnormal hands, abnormal legs, abnormal feet, abnormal fingers
Pengaturan
Sampler
Euler a
Langkah
25
Guidance
7
Seed
908245294
Ukuran
512x512
Prompt
Remove Use these settings Save as template(masterpiece, best quality, absurdres, foreshortening, from_above, fisheye:1.2 ), photo of a highly detailed (figma), 1girl, solo, [realistic], rendered in blender, 1girl, solo, (black hair), short hair, gradient hair, gray hair, bangs, blunt bangs, bob cut, hime cut, black hoodie, hoodie, wearing hoodie, ahoge, parted bangs, wavy hair, parted bangs, bags under eyes, short bangs, eyeliner, eyelashes
Prompt negatif
(worst quality, low quality:1.4 ), easynegative, simple background, lineart, flat colors, lowres, badhandv4
Model AI untuk Pembuatan Gambar, Video & Teks
toy figmas adalah LoRA untuk keluarga Stable Diffusion 1.5 yang tercantum di ModelTrends.ai, katalog hanya-baca untuk model AI gambar, video, dan teks open source. Bandingkan dengan model Stable Diffusion 1.5 lainnya, lihat skor popularitasnya untuk mengetahui trennya, dan buka di PirateDiffusion atau BitVector untuk mencobanya.
Jelajahi berdasarkan Keluarga Model
Jelajahi semua model