Spustit lokálně
cinematic_anime_scenery_v1.safetensors
218 MB · SafeTensor
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
O tomto modelu
STABLE DIFFUSION XL 1.0 · LoRA
Poznámky autora
EDIT: it seems some people are happy with that concept! I'm currently training a V2 with a lot more images. It will probably include some customization features like color tone and will be able to handle low-light scenes!
-
-
📊
-
🙏
This LoRA is designed to elevate your scene by enhancing the scenery quality and seamlessly integrating your anime characters into the scene. It emphasizes the background and adds more information and details to your composition. The lighting is also natural and volumetric, creating an "epic" or "cinematic" feel. Moreover, depth is more obvious, enabling you to explore the "foreground, middle ground, background" concept more effectively.
This model has been trained on cherry picked pics and specific AI generated images.
HQ:
HQ:
The higher the strength, the more the cinematic color tone is accentuated and certain details appear, such as dust particles illuminated by light, depth of field, etc. The background is also more prominent.
Recommended parameters (universal):
Base model:
-
Pony Diffusion XL v6: best style expression. You may have to use other LoRAs to get the style you want. Best contrast and light.
-
AutismMix: easiest setup, works out of the box. No other LoRAs needed. Several LoRAs may produce unexpected results though.
-
Other models based on Pony XL.
Sampler: Euler a.
CFG Scale: ~6.0.
Steps: > 30.
LoRA strength: technically 0.0 - 1.0 but 0.5 - 0.8 is a good range. While 1.0 is possible in some cases, don't go too high or you will screw up your image.
I recommend using hires fix or other upscaler to enhance details after raw generation.
Alternative parameters:
DPM++ 2M SDE Karras or DPM++ 2S a
Those settings produce consistent and detailed pictures, even at lower resolutions without upscaling. Better backgrounds than Euler a. On the other hand, the images may look a little more like oil paintings.
Sampler: DPM++ 2M SDE Karras or DPM++ 2S a.
CFG Scale: ~6.0.
Steps: 25 - 30.
LoRA strength: 0.0 - 0.9 (0.5 - 0.7 is good)
Example matrix:
LCM
The first tests I did with the LCM sampler gave very good results, sometimes better, but they were very irregular. It seems to depend very much on the prompt.
I'm still trying to find the right formula. Recommendations to come...
Known issues:
-
Night or low-light scenes are difficult to achieve. Although the background is correct with the right keywords (night, dark background), the characters tend to be too bright. This will be addressed in the version 2.
-
"I don't want to have light or dust particles" / "There are too much particles": just put "particles" in negative prompt.
SHA256
6C4C6E4F0C4D1D51833E07B362DD798C5505D0448335CAEC876B19B99C9BA4E6
ID modelu ModelTrends.ai
#2883
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
dpmpp_2m_karras
Kroky
30
Guidance
6.5
Seed
525166294035766
Velikost
1024x1024
Prompt
embedding:zPDXL2, Expressiveh, rating_explicit, score_9, score_8_up, score_7_up, BREAK source_anime,best quality, masterpiece,(anime screencap:0.5), hi res, best quality, very aesthetic, absurdres, 8k, Rkbn, solo, 1other, humanoid robot,no humans, other focus,robot joints,
smile,happy,open_mouth, :d, black eyes,
rushpunch,punching,multiple hands,fists,clenched fists,
Negativní prompt
score_6, score_5,embedding:negativeXL_D, embedding:unaestheticXL_Sky3.1, embedding:zPDXL2-neg,, censored, mosaic censoring, bar censor ,border, worst quality,low quality , bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealcensored, mosaic censoring, bar censor ,border, worst quality,low quality , bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealistic,source_furry, source_pony, source_cartoon, still life,greyscale, censored, monochrome,mosaic_censoring, text,speech_bubble,3d,blush, comic,abs,ripped,
Nastavení
Sampler
DPM++ 2M SDE Exponential
Kroky
45
Guidance
2.5
Seed
1781279821
Velikost
832x1216
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, score_6_up, rating_safe, (from below,:1.1) 1girl, long ash braided hair, almond eyes,knight armor, skintight armor, large pauldrons, vambraces, armored boots, leg armor, (muscular:0.6), princess crown, (looking down at viewer:1.2), microwaist, (abs:1.1)
<lora:Fant5yP0ny:0.7>
<lora:microwaist_pony-adam-cosine-16x8-4x1-cs1:0.4>
<lora:age_slider_v4:3>
<lora:epic_anime_scenery_v0_1:0.35>
<lora:Pony_DetailV2.0:0.25>
Negativní prompt
score_6, score_5, score_4, source_furry, source_pony, source_cartoon, sketch, artist name, monochrome, rating_explicit, rating_questionable,
Nastavení
Sampler
DPM++ 2M Karras
Kroky
30
Guidance
7
Seed
2134325801
Velikost
1216x1216
Clip skip
2
Prompt
score_9, score_8_up, score_8, score_9, photo, RAW, (beautiful fairy, colorful magical wings, holding glowing sword:1.2), blue eyes, magical forest in background, concept art, digital art, realistic, hkstyle
<lora:Pony_Fantasy_Knights_-_By_HailoKnight:0.6>
<lora:epic_anime_scenery_v0_1:0.4>
<lora:V2_Pony_Fantasy_Knights_-_By_HailoKnight:0.5>
Negativní prompt
(watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), SDXL-Negative-Semireal-unaestheticXL_v3.1
Nastavení
Sampler
DPM++ 2M
Kroky
40
Guidance
7
Seed
39476396
Velikost
832x1216
Clip skip
2
Použitá váha
0.7
Prompt
score_9, score_8_up, score_7_up, Ryuuguu Rena from Higurashi no naku koro ni, beautiful face, thick thighs, medium chest, blue eyes, orange hair, medium hair, bob cut, parted bangs, cute smile, falling petals, beautifully backlit, anime coloring, beret, black thighhighs, bow, bowtie, dress, hat, puffy short sleeves, puffy sleeves, purple bow, purple bowtie, short sleeves, thighhighs, white dress, zettai ryouiki, brown knee boots,
Negativní prompt
score_1, score_2, score_3, score_4, score_5, score_6, simple background
Nastavení
Sampler
dpmpp_2m_karras
Kroky
30
Guidance
6.5
Seed
404528895146146
Velikost
1024x1024
Prompt
embedding:zPDXL2, Expressiveh, rating_explicit, score_9, score_8_up, score_7_up, BREAK source_anime,best quality, masterpiece,(anime screencap:0.5), hi res, best quality, very aesthetic, absurdres, 8k, Rkbn, solo, 1other, humanoid robot,no humans, other focus,robot joints,
smile,happy,open_mouth,
rushpunch,punching,multiple hands,fists,clenched fists,
Negativní prompt
score_6, score_5,embedding:negativeXL_D, embedding:unaestheticXL_Sky3.1, embedding:zPDXL2-neg,, censored, mosaic censoring, bar censor ,border, worst quality,low quality , bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealcensored, mosaic censoring, bar censor ,border, worst quality,low quality , bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealistic,source_furry, source_pony, source_cartoon, still life,greyscale, censored, monochrome,mosaic_censoring, text,speech_bubble,3d,blush, comic,abs,ripped,
Nastavení
Sampler
Euler a
Kroky
33
Guidance
6
Seed
536027850526613
Velikost
1480x1952
Prompt
score_9,score_8_up,score_7_up,score_6_up,source anime,1girl,standing,solo,black hair,long hair,purple eyes,large breasts,cardigan,outdoors,from above,cowboy shot,light smile,sweat,pantyhose, looking at viewer, wind, hands in pocket
Negativní prompt
score_6,score_5,score_4, text, watermark, source cartoon,
Nastavení
Sampler
Euler a
Kroky
30
Guidance
7
Seed
279998006
Velikost
1280x1856
Použitá váha
0.55
Prompt
score_9, score_6_up, score_8_up, score_7_up, hero_wolf, 1boy, furry male, male focus, solo, bara, yaoi, muscular, brown fur, warrior, armor, shoulder armor, pants, outdoors, sitting on stone, looking at sky, night time, starry night, close up shot, face close up
Negativní prompt
censored, bar, score_6, score_5, score_4, watermark, signature, missing eye, text, watermark, logo, low-quality, signature, distortion, twisted, exaggerated pose, symmetrical, duplicate, error, pattern, low quality, worst quality, black and white, comic, multiple frame, english text, nude, nipples, abs, exposed
Nastavení
Sampler
Euler a
Kroky
33
Guidance
6
Seed
477246087294468
Velikost
1480x1952
Prompt
score_9,score_8_up,score_7_up,score_6_up,source anime,
1girl,solo,cockpit,spaceship,space,science fiction,dark background,piloting,cyberpunk,serious,(spacesuit:0.4),(military uniform:0.5),long sleeves,gloves,dress,sitting,side ponytail,red_hair,amber eyes,hair ribbon,tie,straight-on,from below,particles
Negativní prompt
score_6,score_5,score_4, text, watermark, source cartoon
Podobné modely
AI modely pro generování obrázků, videa a textu
cinematicanime xl je LoRA pro rodinu Stable Diffusion XL 1.0 uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Stable Diffusion XL 1.0, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Další modely Stable Diffusion XL 1.0Další LoRA Stable Diffusion XL 1.0animeeffectspositivesstylescenerysceneponyxlcinematic
Procházet podle rodiny modelů
Modely Text / LLM
411
Modely Anima
509
Modely Chroma
14
Modely Flux
1,071
Modely Flux 2 / Klein
1,237
Modely MiniMax H3
331
Modely Hunyuan
197
Modely Ideogram
20
Modely Krea2
674
Modely Qwen
17
Modely Qwen2
36
Modely Ltx2
150
Modely Stable Diffusion 1.5
6,465
Modely Stable Diffusion XL 1.0
15,432
Modely Zimage
804
Modely Wan
919
Model
Trends
.ai
© ModelTrends.ai
|
Vyrobeno v Japonsku
|
© 2026