Object-removal feature not working
The model card states “support inpaint (image-fill), outpaint (image-extend), eraser (object-removal),” but in my testing it can’t perform object removal. Could you tell me what might be going wrong?
Prompt: remove fox ears, "onereward" written on the whiteboard.
The base model flux fill have undergone heavy SFT for object generation, so the improvement on removal is not obvious. We will release a lora for object removal separately. And it will be better
BTW, the prompt for object removal should be "remove", not extra text append.
lora updated , see the end of README
Note that it is not an instruction-based model like FLUX kontext, it requires descriptive text.
lora updated , see the end of README
Nice!!
Sorry for bumping old thread. I've tried with the removal lora, but not even once able to remove an object/text. Here's the sample I use for the text one
Tried multiple prompt:
prompt1: remove
prompt2: background
prompt3: blurry background
Here's the image
(masking one of the year, not including the comma)
Using workflow from ComfyUI browser
and tried change some settings like:
cfg to 4.0 (before at 1.0) (both doesn't work)
Can you help me? Thanks!
thanks! Looking forward for your observation