kontext series double Image reference双图像参考

The kontext series adapts the posture and shape style of the target image based on related images, maintaining the details of the target image very well. However, it has high requirements for prompt words; specific prompt words can be found in the link below： https://www.runninghub.ai/post/1958169865909653506/?inviteCode=rh-v1180. Additionally, if you want to deploy this model and nodes locally, the computer requirements are quite high, as lower-end computers will generate images very slowly. Through the above link, you can experience this quickly online, and by registering through the link, you will receive 1000 points, plus an additional 100 points for logging in daily, which is more than enough for testing images. Come and give it a try!

kontext系列，根据相关图像改编目标图像的姿势、形状风格，对目标图像的细节保存的非常完好，不过对提示词要求较高，具体的提示词可见如下链接：https://www.runninghub.ai/post/1958169865909653506/?inviteCode=rh-v1180，不过该模型及节点如果要本地部署对电脑要求较高，较低的电脑会生成图像会非常慢，通过上述链接，可在线快速体验，并且通过链接注册，送1000点，每天登陆还送100点，对测试图像完全够用，快来试试吧！