ComfyUI Flux Kontext Dev 原生工作流示例。
Load Image(from output)
节点来加载需要编辑的图像可以让你更方便地获取到编辑后的图像,从而进行多轮次编辑
Load Diffusion Model
节点中加载 flux1-dev-kontext_fp8_scaled.safetensors
模型DualCLIP Load
节点中确保: clip_l.safetensors
及 t5xxl_fp16.safetensors
或 t5xxl_fp8_e4m3fn_scaled.safetensors
已经加载Load VAE
节点中确保加载 ae.safetensors
模型Load Image(from output)
节点中加载提供的输入图像CLIP Text Encode
节点中修改提示词,仅支持英文Queue
按钮,或者使用快捷键 Ctrl(cmd) + Enter(回车)
来运行工作流Image Stitch
节点将两个图像拼接成一个图像,并使用 Flux.1 Kontext 进行编辑。
Load VAE
节点中加载 ae.safetensors
模型Load Image
节点中加载提供的第一个输入图像Load Image
节点中加载提供的第二个输入图像Queue
按钮,或者使用快捷键 Ctrl(cmd) + Enter(回车)
来运行工作流FLUX.1 Kontext Image Edit
组节点,具体可以查看下面的视频演示,当你选中 Load Image
节点时,就可以在选择工具箱中找到新增的编辑按钮
"Change the car color to red"
"Change to daytime while maintaining the same style of the painting"
"Transform to Bauhaus art style"
"Transform to oil painting with visible brushstrokes, thick paint texture"
"Change to Bauhaus style while maintaining the original composition"
"The woman with short black hair"
而非"she"
"while maintaining the same facial features, hairstyle, and expression"
"Replace 'joy' with 'BFL'"
"Replace text while maintaining the same font style"
"Transform the person into a Viking"
✅ 正确:"Change the clothes to be a viking warrior while preserving facial features"
"Put him on a beach"
✅ 正确:"Change the background to a beach while keeping the person in the exact same position, scale, and pose"
"Make it a sketch"
✅ 正确:"Convert to pencil sketch with natural graphite lines, cross-hatching, and visible paper texture"
"Change [object] to [new state], keep [content to preserve] unchanged"
风格转换:
"Transform to [specific style], while maintaining [composition/character/other] unchanged"
背景替换:
"Change the background to [new background], keep the subject in the exact same position and pose"
文本编辑:
"Replace '[original text]' with '[new text]', maintain the same font style"
记住: 越具体越好,Kontext 擅长理解详细指令并保持一致性。