Model
Trends
.ai
Model
Trends
.ai
cele mai bune modele AI open source
Rulează local
BACUN style.safetensors
164 MB · SafeTensor · fp16 · full
Descărcările sunt servite de Civitai. Unii creatori cer mai întâi autentificarea pe Civitai.
AD
<bacunstyle>
Despre acest model
STABLE DIFFUSION 1.5 · LoRA
Creat de
SomeAIGuy
pe Civitai
Notele creatorului
FLUX UPDATE !!! I decided to update my Lora for Flux, at 4k steps and 3k steps. The preview images were the outputs I got when training at 512 x 512 on 29 images. I do believe the 2000 and 2500 step models were also pretty good, should I upload them as well ? I hope you enjoy :) Introduction This is the first LORA I've ever made, so it's far from perfect. I trained it on 85 images of Bacun's art using Anything v4.5 at 512x512. In hindsight, I realise some of the images I included in the training set messed with the results, as they have multiple characters or wrong anatomy. Five of them didn't even get picked up by the Kohya SS gui. I guess that proves quantity doesn't always equate to quality. Also, sometimes it can get pretty close to the referenced illutrations. Usage: For now, the LORA needs heavy handholding. I'd say put the strength at 0.6 - 0.8 (over those values, impurities and other characters will often pop up). If you enable highres, put the Upscale at 1.5 and Denoise at 0.5 This combines quite well with other character and style LORAs, you can also try using ControlNET. What's next: I'll try to improve this LORA some more by polishing the training set, then the next LORAs I'll make will be one focused on a specific Niji Journey cartoon style, and one about the character Arezu from Pokemon Legends Arceus. As for why I made this, it was because I wanted to learn this artstyle, so I thought making a LORA based on his art could be a huge help with learning the anatomy. I was gonna keep it private, but changed my mind in the spirit of open source. Also, it would only take a few weeks or months for someone else to do it instead sooo yeah. Final points: Please, if you make something with this model, credit the original artist (Bacun), as he's a very talented individual. Feel free to polish it, use it in mixes or whatever. Feel free to use it locally or on Google Colab. Please, do not use it on your generation service without my agreement first (although I obviously can't enforce it). I hope I don't end up regretting posting this, but hey, it was interesting to discover the inner workings of LORA-making. This shows that literally anyone can do this after a couple of hours though. Edit: Removed early access, thought it wasn't necessary in the end.
2,477 descărcări · 584 aprecieri pe Civitai
SHA256
2A0B3662F6A52A9E38266D625B2034D42866443B0F2311CCA5ECD93092A752A3
ID model ModelTrends.ai
#2511
Semnalează conținutul
Exemple de randări
Prompturi și setări partajate de cei care au făcut aceste randări pe Civitai. Alege o randare pentru a vedea cum a fost făcută.
Setări
Sampler
Euler a
Pași
25
Guidance
7
Seed
2374336831
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, dynamic angle, dynamic pose, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), 1girl, outdoor, bright colors, sitting, knees together feet apart, barefoot, happy face, holding a pumpkin, halloween pumpkin, from below, (feet focus:1.2), smile, curvy, night, dynamic action, dynamic shot, (official art, extreme detailed, highest detailed:1.20), (solo), <lora:Incase [MockAi - v1.0]:0.45> <lora:BASUN style:0.2> <lora:slugboxV1:0.3>, <lora:add_saturation:1.5>, <lora:Marnie:1> twintails, asymmetrical bangs, marnie, ribbon, hair ribbon, choker, jewelry, black jacket, pink dress, medium hair, open clothes
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers
Setări
Sampler
Euler a
Pași
10
Guidance
5.5
Seed
2011333830
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), (official art, extreme detailed, highest detailed:1.20), (solo), 1girl, bright colors, close up shot, (smug:1.3), sexy, parted lips, open mouth, teeth, (medium body:1.2), <lora:BASUN style:0.2> <lora:BlushySpicy [MockAi - v1.0]:0.4> <lora:slugboxV1:0.2>, (dynamic angle), <lora:add_saturation:1.3>, <lora:add_detail:1.1>, <lora:dark_magician_girl_offset:1>yugioh, dark magician, blue witch hat, blonde, (blue eyes:1.3), blue gear
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers, watermark
Setări
Sampler
Euler a
Pași
10
Guidance
5.5
Seed
3674552105
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), (official art, extreme detailed, highest detailed:1.20), (solo), 1girl, bright colors, close up shot, (smug:1.3), sexy, parted lips, open mouth, teeth, (medium body:1.2), <lora:BASUN style:0.2> <lora:BlushySpicy [MockAi - v1.0]:0.4> <lora:slugboxV1:0.2>, <lora:add_saturation:1.3>, <lora:add_detail:1.1>, <lora:dark_magician_girl_offset:1>yugioh, dark magician, blue witch hat, blonde, (blue eyes:1.1), blue gear,
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers, watermark
Setări
Sampler
Euler a
Pași
10
Guidance
5
Seed
3695417173
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), (official art, extreme detailed, highest detailed:1.20), (solo), 1girl, bright colors, close up shot, (smug:1.3), sexy, parted lips, (upper body:1.4), <lora:BASUN style:0.2> <lora:BlushySpicy [MockAi - v1.0]:0.4> <lora:slugboxV1:0.2>, <lora:add_saturation:1.3>, <lora:add_detail:1.1>, <lora:dark_magician_girl_offset:1>yugioh, dark magician, blue witch hat, blonde, blue eyes, blue gear,
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers, watermark
Setări
Sampler
Euler a
Pași
30
Guidance
7
Seed
3924734263
Mărime
576x920
Clip skip
2
Prompt
(((upper body))), (((simple background))), character focus, solo, centered subject, 1girl, centered <lora:BASUN style:0.8> autumn_leaves maple_leaf leaf autumn sweater ribbed_sweater bag rating:safe falling_leaves between_breasts 1girl ginkgo_leaf solo holding_leaf waving day strap_between_breasts suzuya_(kancolle) smile handbag hair_ornament tree ponytail breasts blue_sky hairclip long_hair leaf_background sky green_eyes outdoors looking_at_viewer turtleneck shoulder_bag aqua_hair green_hair aqua_eyes denim turtleneck_sweater long_sleeves grin medium_breasts alternate_costume cowboy_shot blush sidelocks large_breasts teeth leaf_on_head pants hair_between_eyes cloud school_bag eyebrows_visible_through_hair sleeves_past_wrists :d upper_body casual jeans orange_sweater bangs holding hand_up nature open_mouth
Prompt negativ
(worst quality:1.6),(low quality:1.6), bad_prompt_version2,makeup, mole under eye, mole, logo, watermark, text, EasyNegative, three hands, three legs, kid, loli, naked, nude, nsfw, multiple characters, braid, skull, hairband, white legwear, brown hair, yellow hair, mask
Setări
Sampler
Euler a
Pași
25
Guidance
7
Seed
289166957
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, dynamic angle, dynamic pose, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), 1girl, outdoor, bright colors, sitting, knees together feet apart, barefoot, holding a pumpkin, halloween pumpkin, from below, (feet focus:1.2), shy, blush, curvy, night, dynamic action, dynamic shot, (official art, extreme detailed, highest detailed:1.20), (solo), <lora:Incase [MockAi - v1.0]:0.45> <lora:BASUN style:0.2> <lora:slugboxV1:0.3>, <lora:add_saturation:1.5>, <lora:Marnie:1> twintails, asymmetrical bangs, marnie, ribbon, hair ribbon, choker, jewelry, black jacket, pink dress, medium hair, open clothes
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers
Setări
Sampler
DPM++ 2M
Pași
25
Guidance
4
Seed
2731265826
Mărime
512x768
Clip skip
2
Prompt
(anime illustration), (best quality, masterpiece, dynamic angle, dynamic pose, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), 1girl, outdoor, bright colors, sitting, knees together feet apart, barefoot, sitting on pumpkin, halloween pumpkin, from below, (feet focus:1.2), sexy, smug face, smile, curvy, night, dynamic action, dynamic shot, (official art, extreme detailed, highest detailed:1.20), (solo), <lora:add_saturation:1.3>, <lora:add_detail:1>, <lora:BASUN style:0.2> <lora:BlushySpicy [MockAi - v1.0]:0.4> <lora:slugboxV1:0.2>, <lora:vex3:0.8> vex1, rnd1, hood, vex \(league of legends\), vex shadow \(league of legends\), 1girl, animal ear fluff, black hoodie, black nails, expressionless, green hair, hair between eyes, hood, looking at viewer, purple eyes, solo, toenails, toes, yordle, (gray skin tone, gray skin, pale skin:1.5)
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers, watermak, text
Setări
Sampler
Euler a
Pași
10
Guidance
4.5
Seed
2709993784
Mărime
512x768
Clip skip
2
Prompt
(best quality, masterpiece, beautiful and aesthetic, 8k, ultradetailed illustration:1.30), (official art, extreme detailed, highest detailed:1.20), (solo), 1girl, bright colors, closeup, (smug:1.2), sexy, parted lips, open mouth, suggestive face, (dynamic angle, dynamic pose, dynamic action, dynamic shot:1.2), portrait, upper body, <lora:BASUN style:0.2> <lora:BlushySpicy [MockAi - v1.0]:0.4> <lora:slugboxV1:0.2>, <lora:add_saturation:1.3>, <lora:add_detail:1.1>, <lora:aqua_(konosuba)_v1:0.85> aaaqua, long hair, blue hair, hair rings, hair ornament, choker, bare shoulders, green bow, blue shirt, detached sleeves, blue skirt, thighhighs
Prompt negativ
(worst quality, low quality:1.4) easynegative, badhandv4, NegfeetV2, (looking at viewer:1.3), text, watermarks, extra limbs, extra fingers, watermark
Modele AI pentru generare de imagini, video și text
bacunstyle este un LoRA pentru familia Stable Diffusion 1.5, listat pe ModelTrends.ai, un catalog doar pentru citire al modelelor AI open source pentru imagini, video și text. Compară-l cu alte modele Stable Diffusion 1.5, verifică-i scorul de căldură pentru a vedea cât este de popular și deschide-l pe PirateDiffusion sau BitVector pentru a-l încerca.
Răsfoiește după familia de modele
Răsfoiește toate modelele