Closed KhanhNgoDuy closed 3 months ago
Hi, we fine-tuned SD1.5 using text-normal pairs. The fine-tuning code is based on the text-to-image example in Diffusers. You can find more details in our supplementary material. After fine-tuning SD1.5, we can generate normal maps by providing text prompts.
In Sec. 4.2.1, you " adapt a text-to-image diffusion model into a text-to-normal diffusion model". Can you describe this process?