Closed Laidawang closed 11 months ago
Hi @Laidawang. Thanks to our community, many img2img demos can be found now, e.g., https://huggingface.co/spaces/radames/Enhance-This-DemoFusion-SDXL.
DemoFusion is proposed for high-resolution generation, and as a tuning-free method, its capability for img2img is strongly correlated with the SDXL's training data distribution and will show a significant bias. Pleaseregard this "upscaling" as a side application of text+image based generation and have fun!
Please tell me how to input the image as described in the paper to make it super resolution? At the same time, is there a parameter similar to strength to control the change? In your project, I feel that the change seems too big for works like SR.