Autouppspelning
Kör lokalt
淹没-high.safetensors
293 MB · SafeTensor
Nedladdningar sköts av Civitai. Vissa skapare kräver att du först loggar in på Civitai.
Om denna modell
WAN · LoRA
by hxxwoq2222 - wan2.2-i2v-high-Screen Flood
Skaparens anteckningar
Get the latest global workflows on my RunningHub homepage and run them free on RTX4090.
-
Sign Up with my invite link for 1000 bonus points + 100 daily:
-
-
Run Directly:
-
-
Please credit and link to my homepage if reprinting.
The model only needs to load high noise lora, recommended weights: 0.8-1, to get better water quality, you need to turn off light acceleration at low noise, increase the number of steps, and improve the CFG value (3.5).
Example prompt word:
yanmo567, masterpiece, best quality, photorealistic, full shot, a woman in a grey dress and black thighhighs bending over towards a small kitten on a newspaper, then water suddenly rushes up from the bottom and submerges the entire screen.
yanmo567, a woman in a green sweater and a cap takes a selfie in an elevator, and as the doors open, a huge splash of water erupts from the bottom and submerges the entire screen.
SHA256
FFFC73E51A967A51F40BD4ED8661D1BD42C5E5F32ADCA4F8FBBF638CE88C0CEA
ModelTrends.ai modell-ID
#22272
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Sampler
Euler a
Steg
20
Guidance
1
Storlek
576x1024
Prompt
then water suddenly rushes up from the bottom and submerges the entire screen.
Inställningar
Storlek
1440x2560
Prompt
A young Korean woman casually walking down the alleyway. As she passes a street art mural, a massive, powerful wave of clean, crystal-clear water rushes up from the bottom of the screen, completely submerging her and the alley scene in a matter of seconds.
Inställningar
Sampler
Euler
Steg
4
Guidance
1
Storlek
1248x1792
Prompt
yanmo567, masterpiece, best quality, photorealistic, ultra-detailed cinematic scene. A witch stands at a table reading her spellbook, deep concentration on her face, soft candlelight flickering. Suddenly, a massive splash of water erupts from below, rising dynamically and submerging the scene. The water flows around her body, clothing swept away, elegant motion, realistic water physics, bubbles and reflections, gentle ripples, wet hair and skin, cinematic camera slowly zooming out and rotating, masterpiece, fantasy-horror, hyper-realistic, dramatic lighting and volumetric fog, 8K.
Inställningar
Storlek
1440x2560
Prompt
A young Korean woman is shown from a low angle, her head bowed as she flips through a book. Suddenly, a massive, powerful wave of clean, crystal-clear water rushes up from the bottom of the screen, completely submerging her and the bookstore scene in a matter of seconds.
Inställningar
Sampler
Euler a
Steg
20
Guidance
1
Storlek
576x1024
Prompt
then water suddenly rushes up from the bottom and submerges the entire screen.
Inställningar
Steg
4
Storlek
640x320
Prompt
An1meStyl3, AnimeStyle, anime coloring. yanmo567, a group of anime characters reading a piece of paper, then water suddenly rushes up from the bottom and submerges the entire screen causing the everyone's hair to float and swirl around in the water.
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,裸露,(child),(teen),(youth), (extra limbs), (extra fingers), (3d), (((realistic))), ((photograph))
Inställningar
Sampler
Euler a
Steg
20
Guidance
1
Storlek
576x1024
Prompt
backward dive into the deep, starting from portrait of serene woman, legs transforming into glowing mermaid tail, camera descending with her, character’s inspired underwater world unfolding below — surreal, emotional, vast, sunbeams, caustic light, floating particles, 16fps, slow motion, Unreal Engine 5, volumetric lighting, teal and gold palette.
Liknande modeller
AI-modeller för bild-, video- och textgenerering
high screen flood 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.
Bläddra efter modellfamilj
Text / LLM-modeller
411
Anima-modeller
509
Chroma-modeller
14
Flux-modeller
1,071
Flux 2 / Klein-modeller
1,237
MiniMax H3-modeller
331
Hunyuan-modeller
197
Ideogram-modeller
20
Krea2-modeller
674
Qwen-modeller
17
Qwen2-modeller
36
Ltx2-modeller
150
Stable Diffusion 1.5-modeller
6,465
Stable Diffusion XL 1.0-modeller
15,432
Zimage-modeller
804
Wan-modeller
919

Model
Trends
.ai
© ModelTrends.ai
|
Tillverkad i Japan
|
© 2026
