Chạy cục bộ
everclearPNYByZovya_v4.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Tải xuống do Civitai cung cấp. Một số tác giả yêu cầu đăng nhập Civitai trước.
Về mô hình này
STABLE DIFFUSION XL 1.0 · Mô hình cơ sở
Model by Zovya. Guidance should range from 7 to 10, higher than other models. You can experiment with different samplers. I prefer DPM2M /karras .Prompting for quality should use the score system like other PonyXL models. (score_9, score_8_up, score_7_up) in the positive prompt and (score_3_up, score_4_up, score_5_up) in the negative prompt. Otherwise your images will be very plain.
Ghi chú của tác giả
Does everything a PonyXL model can, but "nearly" photorealistic!
V4 update, improved faces and lighting trained in.
Workflow I use to create the preview images
What it does:
If you're familiar with Pony models, they are very specific in their prompting and subject focus. I made this model to work the same way, but get closer to photorealistic. It uses the same prompting and LoRAs that other PonyXL models use.
What it doesn't do:
It's not a general model. Like other PonyXL models, it's more designed to work with booru tags and mostly does images with people in them. If you want to make general images, use a standard SDXL model.
What's coming:
PonyXL is trained on images with "exaggerated" anatomy. So I've purposely kept it from getting too photorealistic for the moment due to uncanny valley issues. As I train it more, I'll bring it closer to photoreal. In the meantime, use prompts such as (realistic photograph, depth of field, bokeh, etc) to help get the photo look.
How to use:
I recommend using the standard SDXL VAE. CFG should range from 7 to 10, higher than other models. You can experiment with different samplers. I prefer DPM++ 2S a Karras for consistency and DPM++ 3M SDE Exponential to get wild. Prompting for quality should use the score system like other PonyXL models. (score_9, score_8_up, score_7_up) in the positive prompt and (score_3_up, score_4_up, score_5_up) in the negative prompt. Otherwise your images will be very plain.
Alternately, you can use the that I created for much easier use.
SHA256
6673BD3A26010D0AB3FC2E765803F6B04E426F5162D2FA7BAF93293623D8D37B
ID mô hình ModelTrends.ai
#10943
Báo cáo nội dung
Ảnh mẫu
Prompt và thiết lập do những người tạo ra các ảnh này trên Civitai chia sẻ. Chọn một ảnh để xem nó được tạo như thế nào.
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
20
Guidance
9
Seed
722727892714678
Kích thước
832x1216
Prompt
(zPDXL3) beautiful girl with vivid (rainbow dye, colored hair:1.3), smile, long hair, very long hair, (wavy hair:0.9), bangs, at a carnival at night, wearing a white sweater, realistic photograph, professional photographer, depth of field, bokeh
Prompt phủ định
child, teeth, brunette, brown, teeth, makeup, (nude, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
20
Guidance
9
Seed
1056272890615462
Kích thước
832x1216
Prompt
(zPDXL3) dappled sunlight, realistic photograph of little red riding hood in a dark forest sitting on the ground, wearing a red hooded cloak, red dress and boots, leather pants
Prompt phủ định
child, from behind
Thiết lập
Sampler
Euler a
Số bước
10
Guidance
6
Seed
1331282704
Kích thước
832x1216
Clip skip
2
Prompt
boneswm
(MANDALA boneswm)
(mandala geometric)
(BONES radiating from a central mandala)
(fractal BONE designs mandala)
(Geometric BONE patterns mandala)
Prompt phủ định
3d, photo, realistic, anime, source_furry, ((bad quality, worst quality)), blurry, black and white photo, nude
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
20
Guidance
9
Seed
612476313497802
Kích thước
832x1216
Prompt
(zPDXL3) photo, ginger woman with red hair, long hair, freckles, in luxurious nightclub, sitting at the bar holding a beer, wearing a sweater and jeans, bokeh
Prompt phủ định
teeth, brunette, brown, teeth, muscular, (nude, large breasts, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Thiết lập
Sampler
Euler a
Số bước
30
Guidance
10
Seed
1886026628
Kích thước
944x1216
Prompt
score_7, score_8, score_9, break, 1girl, solo, beautiful, sexy, alluring , ((freckles)) , body freckles, glossy skin, dramatic lighting, dark eyeshadow, false eyelashes, makeup , lip gloss, winged eyeliner, backlit , sultry, seductive, soft light , photo realistic , detailed skin, sharp focus, , volumetric lighting,
ultrasharp, sharp eyes, sharp facial features, looking lustfully at viewer, backlit,
<lora:Expressive_H:0.5> ,expressiveh,
<lora:g0th1cPXL:0.5> ,g0th1cpxl,
, ,wide angle , Dutch angle,
golden hour, large tree, cherry blossom tree, heart shaped leaves, picturesque , detailed landscape,
legs hanging down ,midriff, navel, high neck high low dress, no cleavage, , legs,
hair blowing in the light breeze,
brown hair, brown eyes, large breasts, 20 year old, gothic,
alone, lonely, loneliness, sad, sadness, darkness, hopeless romantic, perfect shadows, imagination, dark fantasy, passion,
<lora:Crystal_Heart_Style:.7>, heart shaped crystals falling from the tree, flower hearts, leaf hearts, crstheart, crystal, flower, light particles, light rays,
Prompt phủ định
score_6, score_5, score_4, ugly face, low res, blurry face, black and white, muscular female , aidxlv05_neg, negative_v2, negativeXL_D, censored, greyscale, sketch, bad hands, ugly, bad feet , watermark , tan lines , large belly , large stomach , watermark, text, extra arms, extra legs, shoes, heels,
multi arms, multi legs, bad hand anatomy, bad finger anatomy, unclear architectural outline, non-linear background,
Thiết lập
Sampler
Euler a
Số bước
40
Guidance
3.5
Seed
236735465
Kích thước
832x1216
Clip skip
2
Prompt
a skeleton clock sitting in the middle of a street, 3d rendered steampunk, muscular eldritch clockwork, cyberpunk skeleton, clockpunk, robot skeleton, steampunk automaton, high quality steampunk art, clockwork steampunk, skelleton, clockwork mechanical, titanium skeleton, tall skeletal figure, clockwork automaton, clockwork horror, mechanical clock, inter dimensional clockwork, 4 k human detailed!!! (starry night) starry_morph
Thiết lập
Sampler
DPM++ 2M
Số bước
20
Guidance
7
Seed
1544044352
Kích thước
832x1216
Prompt
zPDXL3 zPDXLpg zPDXLrl beautiful girl with vivid (rainbow dye, colored hair:1.3), smile, long hair, very long hair, (wavy hair:0.9), bangs, at a carnival at night, wearing a white sweater, realistic photograph, professional photographer, depth of field, bokeh
Prompt phủ định
zPDXLpg-neg zPDXLrl-neg teeth, brunette, brown, teeth, muscular, (nude, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
20
Guidance
9
Seed
769582106865883
Kích thước
832x1216
Prompt
(zPDXL3) 2girls, beautiful, colorful hair, cyberpunk nightclub, sofa, chairs, bodysuit, robes, coffee table, low light, dark, (hugging:0.5), lounge, night, cityscape in the background
Prompt phủ định
from behind, teeth, cybernetics, (nude, child, rating_explicit, large breasts, cleavage, nsfw, source_anime, source_cartoon, covered nipples, blurry)
Mô hình tương tự
Mô hình AI để tạo hình ảnh, video & văn bản
everclear4 xl là một mô hình cơ sở thuộc họ Stable Diffusion XL 1.0 được liệt kê trên ModelTrends.ai, danh mục chỉ đọc về các mô hình AI hình ảnh, video và văn bản mã nguồn mở. So sánh nó với các mô hình Stable Diffusion XL 1.0 khác, xem điểm độ hot để biết xu hướng và mở trên PirateDiffusion hoặc BitVector để dùng thử.
Thêm mô hình Stable Diffusion XL 1.0Thêm Mô hình cơ sở Stable Diffusion XL 1.0ponytyperealisticsemi-realeffectsbasephotorealisicponyxlbase model
Duyệt theo họ mô hình
Mô hình Text / LLM
411
Mô hình Anima
509
Mô hình Chroma
14
Mô hình Flux
1,071
Mô hình Flux 2 / Klein
1,237
Mô hình MiniMax H3
331
Mô hình Hunyuan
197
Mô hình Ideogram
20
Mô hình Krea2
674
Mô hình Qwen
17
Mô hình Qwen2
36
Mô hình Ltx2
150
Mô hình Stable Diffusion 1.5
6,465
Mô hình Stable Diffusion XL 1.0
15,432
Mô hình Zimage
804
Mô hình Wan
919
Model
Trends
.ai
© ModelTrends.ai
|
Làm tại Nhật Bản
|
© 2026