Open pkuliyi2015 opened 1 year ago
Thank you for implementing MultiDiffusion with the WebUI -- looks great!
Regarding larger images -- in the simplest setting of having the same prompt for all views, then almost by definition it may be unsuitable for certain prompts/resolutions (e.g., when generating a single object that should not appear in each view). I think that a coarse-to-fine generation approach can help with this.
Dear authors,
I have implemented your algorithm to Automatic1111's WebUI with the following optimization:
Some WebUI related stuffs:
Here is the link:
Great thanks to your fantastic work especially in img2img and panorama generation! We are working on text prompt now.
But the uncontrolled large image generation is not ideal at all, as repeated patterns always appears and the image is mostly unusable.
Would you please give us some insights, if we can generate large images without a user-specified prompt mask?
For example, I have an idea (without proof): we may generate a small reference image first, obtain the prompt attention map, scale it to a larger resolution, and finally we automatically locate the prompt to its correct views during multi-diffusion.
Thank you very much!