[Bug]: mixing_image_prompt_and_inpaint

Windecay commented 1 month ago

Checklist

[ ] The issue has not been resolved by following the troubleshooting guide
[X] The issue exists on a clean installation of Fooocus
[X] The issue exists in the current version of Fooocus
[X] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

When using the 'mixing_image_prompt_and_inpaint' function, the canvas is enlarged but the image prompt (such as PyraCanny, CPDS) are not synchronized, resulting in whole reference image being drawn inside the mask.

Steps to reproduce the problem

1,upload image prompt,use canny or depth,Stop At=1,Weight=2(More obvious) 2,choose Inpaint or Outpaint/Improve Detail (face, hand, eyes, etc.)/Modify Content (add objects, change background, etc.) 4,upload image and draw a mask. 5,using the 'mixing_image_prompt_and_inpaint'. 6,generate

What should have happened?

Synchronize zoom in drawing area and reference area.

What browsers do you use to access Fooocus?

Microsoft Edge

Where are you running Fooocus?

Locally

What operating system are you using?

No response

Console logs

[Fooocus] Processing prompts ...
[Fooocus] Encoding positive #1 ...
[Fooocus Model Management] Moving model(s) has taken 0.12 seconds
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
[Fooocus] VAE encoding ...
Final resolution is (2048, 2048), latent is (1024, 1024).
[Parameters] Denoising Strength = 1
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 2.87 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 2.16 seconds
 80%|███████████████████████████████████████████████████████████████████████████████████████████████████████████▏                          | 24/30 [00:06<00:01,  3.44it/s]Requested to load SDXL
Loading 1 new model
unload clone 0
[Fooocus Model Management] Moving model(s) has taken 1.14 seconds
Refiner Swapped
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:09<00:00,  3.22it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: G:\Fooocus_mashb1t_win64_2-1-864\Fooocus\outputs\2024-08-14\log.html
Generating and saving time: 13.54 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 13.54 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 16.44 seconds
[Fooocus Model Management] Moving model(s) has taken 0.59 seconds

Additional information

No response

IPv6 commented 1 month ago

this is by design, image prompts are intentionally cover current inpainting zone (outpainting is just a form of inpainting)

Windecay commented 1 month ago

this is by design, image prompts are intentionally cover current inpainting zone (outpainting is just a form of inpainting)

thank you !

lllyasviel / Fooocus