
Simple Workflow that uses the new Florence Nodes to "replace" older detection techniques that requires many specific models, (Ultralytics YOLO's)
Now you can just have one single model to detect pretty much anything with more details and accuracy, (face, eye, mouth, hairs, watermark removing, inpainting tools to change colors or shapes) Alot of usages possible,
DINO is a also a good alternative but I think Florence is better, have to do some tests
Here you can see how it works
I recommend using an Inpaint model for strong changes, (above 0.4 denoise value)
You can use a classic SDXL model for "details" (under 0.4 denoise value)
描述:
训练词语:
名称: florenceDetailerWorkflow_v101.zip
大小 (KB): 4
类型: Archive
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success