Load Diffusion Model

LoraLoaderModelOnly

Load VAE

Load CLIP

Save Image

KSampler

ModelSamplingSD3

VAE Decode

CLIP Text Encode (Prompt)

cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open placing a fancy black forest cake with candles on top of a dinner table of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere there are paintings on the walls

EmptySD3LatentImage

FluxGuidance

DualCLIPLoader

一个穿着华丽的红色汉服的中年女人在雪山之巅的半身照，戴着华丽的黄金头饰，温暖的阳光照耀在她身上，她的表情十分宁静，美丽的汉服和她的发梢随风飘荡，她面色红润，对着镜头羞涩地微笑，手里拿着一枝桃花，

VAE Encode

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

Clean VRAM Used

LayerUtility: Image Reel

LayerUtility: Image Reel Composit

Preview Image

WanVideoNAG

Flux采样出图

Wan图生图

pixels

LATENT

model

MODEL

CLIP

clip

CONDITIONING

conditioning

positive

negative

latent_image

samples

IMAGE

anything

output

wan2.1_t2v_1.3B_fp16.safetensors

wan_2.1_vae.safetensors

umt5_xxl_fp8_e4m3fn_scaled.safetensors

image1

image2

image3

image4

reel

reel_1

reel_2

reel_3

reel_4

images

git+https://github.com/WASasquatch/img2texture.git@d6159abea44a0b2cf77454d3d46962c8b21eb9d3

leeguandong

Wan2.1 flux image+wan image lightx2v+fusionx lora  Improved image quality

OpenArt

Workflows

Active Sessions

Wan2.1 flux image+wan image lightx2v+fusionx lora Improved image quality

Description

Discussion

Loading...