flat color wan — WAN AI-modell

Flat Color - Style Trained on images without visible lineart, flat colors, and little to no indication of depth. ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information. This is a small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular. The effect is quite nice and easy to evaluate in training, so I've extended the dataset with videos in following versions for text-to-video models like Wan and Hunyuan, and it is what I am generally using to test LoRA training on new models now. Recommended tags: flat color, no lineart, blending, negative space, {{color}} background

Triggerord

flat color

no lineart

4,099 nedladdningar · 583 gillningar på Civitai

SHA256

E61910EC19FC602D72248C4F3ABD338B614D82394F357D2D67F6E1575B4F4819

ModelTrends.ai modell-ID

#11568

Rapportera innehåll

Exempelrenderingar

Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.

Hämta denna prompt

Rendering av motimalu på Civitai

Rapportera

Inställningar

Sampler

UniPC

Steg

Guidance

Seed

552860142156157

Storlek

480x832

Prompt

slime girl, water dress, absurdly long hair, liquid hair, twintails, blue hair, blue dress, blue skin, ocean, dappled sunlight, strapless dress, blue eyes, bare shoulders, looking up, waves, from side, bare arms, sitting, wind, floating hair, live2d, animation, the camera is steady, camera panning downwards, zooming in, masterpeice, best quality, very aesthetic, absurdres

Negativ prompt

bad quality video,signature,watermark,色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走

Rendering av motimalu på Civitai

Rapportera

Inställningar

Storlek

832x480

Prompt

flat color, no lineart, blending, negative space, artist:[john kafka|ponsuke kaikai|hara id 21|yoneyama mai|fuzichoco], 1girl, hoshimachi suisei, virtual youtuber, blue hair, side ponytail, cowboy shot, black shirt, star print, off shoulder, outdoors, starry sky, wariza, looking up, half-closed eyes, black sky, live2d animation, upper body, high quality cinematic video of a woman sitting under the starry night sky. The Camera is steady, This is a cowboy shot. The animation is smooth and fluid.

Negativ prompt

色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走

Rendering av KalbyEaten på Civitai

Rapportera

Inställningar

Steg

Guidance

Seed

812647272

Storlek

480x480

Använd vikt

Prompt

score_9, score_8_up, score_7_up, score_6_up, Elsa in winter dress, dancing, hands off screen, smooth movements,

Rendering av motimalu på Civitai

Rapportera

Inställningar

Sampler

UniPC

Steg

Guidance

Seed

552860142156000

Storlek

832x480

Prompt

flat color, no lineart, blending, negative space, artist:[john kafka|ponsuke kaikai|hara id 21|yoneyama mai|fuzichoco], fern \(sousou no frieren\), 1girl, purple hair, long hair, winter clothes, snow, from below, purple eyes, mittens, cold, floating hair, blush, sitting, white scarf, live2d animation, upper body, high quality cinematic video of a girl drinking tea from a mug. The Camera is steady, This is an upper body shot. The animation is smooth and fluid.

Negativ prompt

Liknande modeller

AI-modeller för bild-, video- och textgenerering

flat color wan är en LoRA för familjen Wan, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra Wan-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.

Fler Wan-modeller Fler Wan LoRA video anime sci-fi artstyles flat styles wan flat color

Bläddra efter modellfamilj