Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
Model Description by Creator
现在来到了200w steps loss曲线仍在降低虽然很慢,同时我的偏置噪声似乎设定的有些高了.初始Noise offset 0.05.从画面图像来看有部分颜色有些失真或溢出..比如绿色（。也许有人能用lora合并来修复画面问题。
(在sd2.1的fintune模型上lora好像泛用性较低,也许需要在该模型上训练的才会有效果）我尝试了一个sd2.1的lora发现对画面没有起效，不知道原因在哪
Now we have reached 200w steps. The curve loss is still decreasing, though very slowly. Meanwhile, my bias noise seems to have been set too high. Initial Noise offset 0.05. Judging from the image, some colors are distorted or overflow.. For example, green (. Maybe someone can fix the graphics with lora merge.
(lora seems to be less general on sd2.1 fintune model, maybe it needs to be trained on that model to be effective) I tried an sd2.1 lora and found it didn't work on the screen, I don't know why
这个模型在3.1w张niji图像训练了200个gpu小时合计120w steps。但是loss任未收敛至合适范围.同时由于训练文本倾向原因导致模型短语理解能力失调.可能需要重新调整.也就是说这个模型不能通过简单的1girl出图.有兴趣的人可以在上面继续做微调，亦或是能给我提供补充数据集也欢迎联系我
This model was trained on 3.1w niji images for 200 gpu hours totaling 120k steps. However, the loss does not converge to the appropriate range. At the same time, the training text tendency causes the dyscomprehension of model phrases. May need to readjust. That is to say, this model cannot be mapped by a simple 1girl. If you are interested, please feel free to contact me for further fine-tuning, or if you can provide me with supplementary data sets
Images Generated With This Model
N/A
Hidden For Public Users
Fantastic flying castle, Ghibli style, scenery, outdoors, fantasy, clothesline, cloud, sky, day, floating island
N/A
Hidden For Public Users
A home office livingroom with bookshelf and plants, picture frame above the couch, plant, indoors, no humans, couch, potted plant, pillow, clock, book, scenery, picture (object), wooden floor, window, shelf, signature, table, rug, picture frame, cushion, photo (object), leaf
N/A
Hidden For Public Users
masterpiece, best quality, 8k, perfect lighting, cinematic lighting, dark skin, light brown hair, 1girl, yellow eyes, solo, full body, standing,
N/A
Hidden For Public Users
Fantastic flying castle, Ghibli style, scenery, outdoors, fantasy, clothesline, cloud, sky, day, floating island
N/A
Hidden For Public Users
the queen of assassins, beautiful elegant portrait, 1girl, solo, jewelry, long hair, crown, earrings, looking at viewer, blonde hair, upper body, blue eyes, closed mouth, signature, veil, own hands together, gem, bangs, grey eyes, long sleeves, simple background, dress, fingernails, parted bangs, bridal gauntlets
N/A
Hidden For Public Users
a girl wearing black fantasy clothing with black hair, beautiful blue eyes, art by Jeremy Chong, Gu art by Zheng Wei, art by Z.W Gu, artstation, semi-realistic art, fantasy art, dark and mysterious, surreal environment, detailed painting, Anime girl, anime style, digital art, anime waifu( 17 - years - old) - hot - babe - flirty, fit - thick - build, gorgeous face - perfect with perfect anime eyes - symmetric, anatomically correct, enchanting eyes, beautiful pupils, glowing eyes, beautiful eyes, pupils and iris looking at viewer, looking at viewer, stunning bright eyes, Her chiseled face boasts a high forehead, friendly looking, pronounced cheekbones, piercing eyes with long lashes, a straight narrow nose, full red lips, juicy lips, blush face, clean face, long eyelashes, high contrast, ultra detailed, cinematic lighting, highly detailed, sharp focus, photorealistic painting, Beautiful Lighting, volumetric, 8K, dramatic light, high quality, smooth light, delicate, perfect shading, global illumination, smooth light, delicate, pixiv, High quality, backlight, complex image, 8k, 4k, ( ( masterpiece) ), ( ( ( best quality) ) ), ( ( ultra - detailed) ), best quality illustration, ultra - detailed, rtx[shading( focal/ hardlight - diffused/ ambientlight) defined, best quality illustration, ultra - detailed, rtx[shading( focal/ hardlight - diffused/ ambientlight), aftereffects, highly detailed, face focus, global illumination, stable - diffusion, trending on artstation Artgerm + Tsuaii, Krenz Cushart + Ilya Kuvshinov + Rossdraws + Adam Hughes + Alfons Mucha + Greg Tocchini + Krenz Cushart + Ross Tran, Pixiv masterpiece by ufotable, by Kyoto Animation, anime produced by ufotable, anime produced by madhouse studio, anime produced by studio trigger, concept art, 1girl, jewelry, blue eyes, gloves, shirt, looking at viewer, skirt, long hair, solo, black skirt, black gloves, earrings, long sleeves, black shirt, bangs, belt, hand in pocket, jacket, fingerless gloves, open clothes, cowboy shot, black hair
N/A
Hidden For Public Users
(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl:1.3), extremely detailed,(fractal art:1.1),(colorful:1.1)(flowers:1.3),highest detailed,(zentangle:1.2), (dynamic pose), (abstract background:1.3), (shiny skin), (many colors:1.4), ,(earrings), (feathers:1.5)
N/A
Hidden For Public Users
a girl wearing black fantasy clothing with black hair, beautiful blue eyes, art by Jeremy Chong, Gu art by Zheng Wei, art by Z.W Gu, artstation, semi-realistic art, fantasy art, dark and mysterious, surreal environment, detailed painting, Anime girl, anime style, digital art, anime waifu( 17 - years - old) - hot - babe - flirty, fit - thick - build, gorgeous face - perfect with perfect anime eyes - symmetric, anatomically correct, enchanting eyes, beautiful pupils, glowing eyes, beautiful eyes, pupils and iris looking at viewer, looking at viewer, stunning bright eyes, Her chiseled face boasts a high forehead, friendly looking, pronounced cheekbones, piercing eyes with long lashes, a straight narrow nose, full red lips, juicy lips, blush face, clean face, long eyelashes, high contrast, ultra detailed, cinematic lighting, highly detailed, sharp focus, photorealistic painting, Beautiful Lighting, volumetric, 8K, dramatic light, high quality, smooth light, delicate, perfect shading, global illumination, smooth light, delicate, pixiv, High quality, backlight, complex image, 8k, 4k, ( ( masterpiece) ), ( ( ( best quality) ) ), ( ( ultra - detailed) ), best quality illustration, ultra - detailed, rtx[shading( focal/ hardlight - diffused/ ambientlight) defined, best quality illustration, ultra - detailed, rtx[shading( focal/ hardlight - diffused/ ambientlight), aftereffects, highly detailed, face focus, global illumination, stable - diffusion, trending on artstation Artgerm + Tsuaii, Krenz Cushart + Ilya Kuvshinov + Rossdraws + Adam Hughes + Alfons Mucha + Greg Tocchini + Krenz Cushart + Ross Tran, Pixiv masterpiece by ufotable, by Kyoto Animation, anime produced by ufotable, anime produced by madhouse studio, anime produced by studio trigger, concept art, 1girl, jewelry, blue eyes, gloves, shirt, looking at viewer, skirt, long hair, solo, black skirt, black gloves, earrings, long sleeves, black shirt, bangs, belt, hand in pocket, jacket, fingerless gloves, open clothes, cowboy shot, black hair
N/A
Hidden For Public Users
re-l from ergo proxy, black hair, pale skin, blue eys, blue eye shadow, gothic cyberpunk, looking straight, looking at camera, adult woman, 1girl, solo, blue eyes, black hair, looking at viewer, freckles, long hair, piercing, glowing, parted lips, jewelry, jacket, letterboxed, glowing eyes
N/A
Hidden For Public Users
80s anime movie poster depicting the goddess of love, long hair, jewelry, blue eyes, white hair, looking at viewer, earrings, gloves, crown, holding, bangs, solo focus, parted bangs, multiple girls, straight-on, collarbone
N/A
Hidden For Public Users
a fairy by naoko takeuchi, 1girl, solo, flower, hair ornament, long hair, hair flower, looking at viewer, wings, blush, upper body, bangs, smile, blue flower, hair between eyes, long sleeves, white background, white hair, closed mouth, butterfly wings
Similar Models
Train Models
Train AI Models On Your Own Pictures
You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model
Generate AI Images. Simple and Easy
AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.