Hi! I’m trying to understand the recommended approach for training FLUX.2 Inpainting with ControlNet, specifically for mask-conditioned inpainting.
My goal is to perform inpainting only inside the masked region, while also making the generated content follow an additional mask/control signal provided to ControlNet. In other words, I would like the inpainted region to be structurally guided by the ControlNet conditioning input, not only by the text prompt.
Could you please clarify what is the recommended training setup for this use case?
Any guidance or pointers would be greatly appreciated. Thanks!
Hi! I’m trying to understand the recommended approach for training FLUX.2 Inpainting with ControlNet, specifically for mask-conditioned inpainting.
My goal is to perform inpainting only inside the masked region, while also making the generated content follow an additional mask/control signal provided to ControlNet. In other words, I would like the inpainted region to be structurally guided by the ControlNet conditioning input, not only by the text prompt.
Could you please clarify what is the recommended training setup for this use case?
Any guidance or pointers would be greatly appreciated. Thanks!