[Bug]: Inpaint: Improve Detial - Not always work

[kobylls]

Checklist

• [X] 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?

Since version 2.5 when selecting the "Improve detail" option in the inpainter tab, it works like the default "inapaint or Outpaint" method. The workaround (sometimes) is generate a change with the "modify content" method and then move to the "improve detail" method.

Steps to reproduce the problem

1. Geneart an image
2. Move it to the inpaint outpaint tab
3. Mask and choose the "Improve detail" method.
4. Look how the image is re-generated instead of improving the masked area.

What should have happened?

The masked area needs to be improved, instead, it changed to a new generated image.

What browsers do you use to access Fooocus?

Google Chrome

Where are you running Fooocus?

Locally

What operating system are you using?

Windows 11

Console logs

F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0>.\python_embeded\python.exe -s Fooocus\entry_with_update.py --preset realistic
Already up-to-date
Update succeeded.
[System ARGV] ['Fooocus\\entry_with_update.py', '--preset', 'realistic']
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Fooocus version: 2.5.2
Loaded preset: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\presets\realistic.json
[Cleanup] Attempting to delete content of temp dir C:\Users\cobij\AppData\Local\Temp\fooocus
[Cleanup] Cleanup successful
Total VRAM 16376 MB, total RAM 65428 MB
Set vram state to: NORMAL_VRAM
Always offload VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : native
VAE dtype: torch.bfloat16
Using pytorch cross attention
Refiner unloaded.
Running on local URL:  http://127.0.0.1:7865

To create a public link, set `share=True` in `launch()`.
model_type EPS
UNet ADM Dimension 2816
IMPORTANT: You are using gradio version 3.41.2, however version 4.29.0 is available, please upgrade.
--------
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['cond_stage_model.clip_l.transformer.text_model.embeddings.position_ids'])
Base model loaded: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realisticStockPhoto_v20.safetensors
VAE loaded: None
Request to load LoRAs [('SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors', 0.25)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realisticStockPhoto_v20.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realisticStockPhoto_v20.safetensors] with 722 keys at weight 0.25.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realisticStockPhoto_v20.safetensors] with 264 keys at weight 0.25.
Fooocus V2 Expansion: Vocab with 642 words.
F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\python_embeded\lib\site-packages\torch\_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
  return self.fget.__get__(instance, owner)()
Fooocus Expansion engine loaded for cuda:0, use_fp16 = True.
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
[Fooocus Model Management] Moving model(s) has taken 0.62 seconds
Started worker with PID 1796
App started successful. Use the app with http://127.0.0.1:7865/ or 127.0.0.1:7865
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 5653733400558689131
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
model_type EPS
UNet ADM Dimension 2816
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['cond_stage_model.clip_l.transformer.text_model.embeddings.position_ids'])
Base model loaded: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors
VAE loaded: None
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.56 seconds
[Fooocus] Processing prompts ...
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (785, 785, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.26 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.39 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.47 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.49 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.28 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.21 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 22.88 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.40 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:20<00:00,  2.95it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.40 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 22.76 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 22.76 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 45.68 seconds
[Fooocus Model Management] Moving model(s) has taken 0.71 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 6507501043343510886
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] denim jacket, futuristic, glowing light atmosphere, detailed, intricate, full, cinematic, extremely, highly saturated colors, theatrical, dramatic, beautiful composition, elegant, sharp focus, professional, winning, fair quality, epic, stunning, color, perfect, artistic, innocent, strong background, aesthetic, whole coherent, cute, best, creative, passionate, positive, vibrant
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (769, 769, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.26 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.36 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.32 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.17 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.36 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 13.02 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.22 seconds
 17%|█████████████▋                                                                    | 10/60 [00:03<00:16,  3.09it/s]
User stopped
[Enhance] Skipping, preconditions aren't met
Processing time (total): 4.46 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 17.54 seconds
[Fooocus Model Management] Moving model(s) has taken 0.85 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 471836179906917013
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Fooocus] Downloading inpainter ...
[Inpaint] Current inpaint model is F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 48
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Synthetic Refiner Activated
Synthetic Refiner Activated
Request to load LoRAs [('add-detail-xl.safetensors', 1.0), ('F:\\stable-diffusion\\Fooocus\\Fooocus_win64_2-5-0\\Fooocus\\models\\inpaint\\inpaint_v26.fooocus.patch', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 960 keys at weight 1.0.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.48 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] denim jacket, light, cool, shiny, intricate, elegant, sharp focus, highly detailed, symmetry, fine detail, cinematic, colorful, joyful, beautiful, epic composition, background, professional, dramatic ambient, dynamic, full color, magic, atmosphere, marvelous, thought, iconic, best, creative, winning, perfect, thoughtful, pretty, attractive, smart, lucky
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (769, 769, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.35 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
[Parameters] Denoising Strength = 1
[Parameters] Initial Latent shape: Image Space (1024, 1024)
Preparation time: 14.83 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 2.74 seconds
 13%|███████████                                                                        | 8/60 [00:02<00:17,  3.03it/s]
User stopped
[Enhance] Skipping, preconditions aren't met
Processing time (total): 5.39 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 20.26 seconds
[Fooocus Model Management] Moving model(s) has taken 0.66 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 4645070933587384573
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.49 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] denim jacket, cinematic, dynamic composition, dramatic light, aesthetic, very inspirational, bright colors, clear, perfect, detailed, epic, fine detail, winning color, enhanced, intricate, colorful, coherent, sharp focus, professional, ambient background, joyful, taking full creative, positive, unique, attractive, elegant, thoughtful, cute, pretty, confident, passionate, best
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (769, 769, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.28 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 12.84 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.14 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:15<00:00,  3.96it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 17.10 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 17.10 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 29.98 seconds
[Fooocus Model Management] Moving model(s) has taken 0.67 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 1639654057274566701
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Fooocus] Downloading inpainter ...
[Inpaint] Current inpaint model is F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 48
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Synthetic Refiner Activated
Synthetic Refiner Activated
Request to load LoRAs [('add-detail-xl.safetensors', 1.0), ('F:\\stable-diffusion\\Fooocus\\Fooocus_win64_2-5-0\\Fooocus\\models\\inpaint\\inpaint_v26.fooocus.patch', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 960 keys at weight 1.0.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.54 seconds
[Fooocus] Processing prompts ...
[Fooocus] Encoding positive #1 ...
[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 0.21 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.34 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
[Parameters] Denoising Strength = 1
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 12.10 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 2.83 seconds
 57%|██████████████████████████████████████████████▍                                   | 34/60 [00:14<00:11,  2.36it/s]
User stopped
[Enhance] Skipping, preconditions aren't met
Processing time (total): 17.27 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 29.40 seconds
[Fooocus Model Management] Moving model(s) has taken 0.60 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 6262325304059888142
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Fooocus] Downloading inpainter ...
[Inpaint] Current inpaint model is F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 48
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Synthetic Refiner Activated
Synthetic Refiner Activated
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] nude, light, gorgeous, intricate, cinematic, elegant, highly detailed, intense, beautiful, sharp focus, strong detail, artistic, fine composition, cool colors, amazing, full color, awesome, perfect, colorful, surreal, pretty, trendy, creative, positive, attractive, best, successful, unique, loving, cute, pure, iconic, very inspirational, vibrant
[Fooocus] Encoding positive #1 ...
[Fooocus Model Management] Moving model(s) has taken 0.11 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 0.22 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.27 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.22 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
[Parameters] Denoising Strength = 1
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 12.12 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 2.79 seconds
 80%|█████████████████████████████████████████████████████████████████▌                | 48/60 [00:13<00:02,  4.08it/s]Requested to load SDXL
Loading 1 new model
unload clone 0
[Fooocus Model Management] Moving model(s) has taken 1.18 seconds
Refiner Swapped
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:17<00:00,  3.41it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.26 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 21.23 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 21.23 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 33.38 seconds
[Fooocus Model Management] Moving model(s) has taken 0.65 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 6948835188936682803
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.47 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] nude, light, sharp focus, intricate, elegant, highly detailed, dynamic, vibrant, beautiful, designed, rich deep colors, winning, color, epic, best, dramatic, contemporary, vivid, attractive, cinematic, modern, surreal, iconic, fine detail, full background, professional, creative, cool, awesome, colorful, symmetry, magic, atmosphere, gorgeous
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (743, 743, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.34 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 13.11 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.22 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:15<00:00,  3.92it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.28 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 17.34 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 17.34 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 30.49 seconds
[Fooocus Model Management] Moving model(s) has taken 0.60 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 3333697581128150927
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Fooocus] Downloading inpainter ...
[Inpaint] Current inpaint model is F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 48
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Synthetic Refiner Activated
Synthetic Refiner Activated
Request to load LoRAs [('add-detail-xl.safetensors', 1.0), ('F:\\stable-diffusion\\Fooocus\\Fooocus_win64_2-5-0\\Fooocus\\models\\inpaint\\inpaint_v26.fooocus.patch', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\inpaint\inpaint_v26.fooocus.patch] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 960 keys at weight 1.0.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.54 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] nude, very strong, intricate, highly detailed, dramatic light, sharp focus, surreal beautiful, dynamic background, illuminated glowing cinematic fine composition, elegant, great detail, professional, winning, perfect, innocent, artistic, pure, color, inspired, still, pretty, attractive, futuristic, marvelous, thought, creative, positive, atmosphere, new, shiny, amazing, brilliant
[Fooocus] Encoding positive #1 ...
[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 0.22 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
[Parameters] Denoising Strength = 1
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 13.59 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 2.66 seconds
 80%|█████████████████████████████████████████████████████████████████▌                | 48/60 [00:13<00:02,  4.11it/s]Requested to load SDXL
Loading 1 new model
unload clone 0
[Fooocus Model Management] Moving model(s) has taken 1.23 seconds
Refiner Swapped
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:17<00:00,  3.38it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 21.22 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 21.22 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 34.85 seconds
[Fooocus Model Management] Moving model(s) has taken 0.63 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 2661125294241091642
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
Request to load LoRAs [('add-detail-xl.safetensors', 1.0)] for model [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors].
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for UNet [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 722 keys at weight 1.0.
Loaded LoRA [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\loras\add-detail-xl.safetensors] for CLIP [F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\models\checkpoints\realismEngineSDXL_v30VAE.safetensors] with 264 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 0.47 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] very long hair, highly detailed wavy (redhead hair:1.3), very bright colorful, glowing, attractive, intricate, cinematic, stunning, sharp focus, great composition, thought, best depicted, dramatic light, enhanced quality, artistic, innocent, fabulous, epic, dazzling, rich deep colors, winning scenic background, professional, appealing, cute, beautiful, marvelous
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (921, 985, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 960).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.29 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.35 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 120, 128])
Preparation time: 14.58 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.23 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:19<00:00,  3.04it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.44 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 21.96 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 21.96 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 36.58 seconds
[Fooocus Model Management] Moving model(s) has taken 0.63 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 83156600178157169
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] very long hair, highly detailed wavy (redhead hair:1.3), extremely lush colorful deep aesthetic, intricate, very beautiful, dramatic light, cinematic composition, inspirational, vibrant colors, winning fine detail, open dynamic color, enhanced quality, professional, emotional, glorious, iconic, rich vivid, complex artistic background, incredible creative, wonderful atmosphere, striking, epic
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (461, 463, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.32 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.34 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 10.94 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.20 seconds
  0%|                                                                                           | 0/60 [00:00<?, ?it/s]
User stopped
[Enhance] Skipping, preconditions aren't met
Processing time (total): 1.58 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 12.57 seconds
[Fooocus Model Management] Moving model(s) has taken 0.85 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 4706597671403432048
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] beautiful eyes, realistic eyes, highly detailed eyes blue-green, highly detailed face, extremely delicate, perfect, dramatic, intricate, elegant, real, sharp focus, beautiful, cute, great composition, professional, amazing, symmetry, clear, ambient, warm colors, artistic, vibrant, complex, iconic, fine detail, pretty, enhanced, background, illuminated, light
[Fooocus] Encoding positive #1 ...
[Fooocus Model Management] Moving model(s) has taken 0.10 seconds
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (461, 463, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.24 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.14 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.35 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.23 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 10.87 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.15 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:19<00:00,  3.14it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.26 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 21.02 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 21.02 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 31.93 seconds
[Fooocus Model Management] Moving model(s) has taken 0.59 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] Seed = 2993013745996793740
[Parameters] CFG = 3
[Fooocus] Downloading upscale models ...
[Inpaint] Parameterized inpaint is disabled.
[Fooocus] Downloading control models ...
[Fooocus] Loading control models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] beautiful eyes, realistic eyes, highly detailed eyes blue-green, highly detailed face, sharp focus, dramatic, intricate, elegant, dynamic, vibrant, rich deep colors, amazing, surreal, inspiring, thought, cinematic, complex, cool, artistic, background, creative, awesome, illuminating, attractive, full color, perfect, fine detail, clear, relaxed, extremely aesthetic
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Image processing ...
Upscaling image with shape (187, 187, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.20 seconds
[Fooocus] VAE encoding ...
Final resolution is (1792, 2176), latent is (1024, 1024).
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.33 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.28 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.16 seconds
Detected 1 faces
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.35 seconds
Requested to load Resampler
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
Requested to load To_KV
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.15 seconds
[Parameters] Denoising Strength = 0.5
[Parameters] Initial Latent shape: torch.Size([1, 4, 128, 128])
Preparation time: 10.42 seconds
Using karras scheduler.
[Fooocus] Preparing task 1/1 ...
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 1.2431749105453491
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.27 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 60/60 [00:19<00:00,  3.12it/s]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.25 seconds
[Fooocus] Saving image 1/1 to system ...
Image generated with private log at: F:\stable-diffusion\Fooocus\Fooocus_win64_2-5-0\Fooocus\outputs\2024-08-03\log.html
Generating and saving time: 21.28 seconds
[Enhance] Skipping, preconditions aren't met
Processing time (total): 21.28 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
Total time: 31.74 seconds
[Fooocus Model Management] Moving model(s) has taken 0.61 seconds

Additional information

No response

[mashb1t]

Works for me in both Windows and MacOS as well as Colab. Can you consistently reproduce the issue? Does this only occur in a specific image format (png, jpeg, webp)?

[kobylls]

Hey, Yes I'm able to reproduce this every time now. I don't know why it's happening, to be honest, it's happening also when I clean start it.

Added a video for reference: https://github.com/user-attachments/assets/0baebcc9-e87d-4f1c-a31e-87dfadd11ffb

BTW, same for PNG and JPG.

[mashb1t]

As far as i can see there is no bug. "Improve detail" and "inpaint or Outpaint" both zoom in as their respective field setting is 0, but the former uses no inpaint engine and 0.5 denoising strwngth compared to the latter with an inpaint engine and 1 as denoising strength. Zooming in on the masked area, then upscaling this one to 1024x1024 and improving the quality by rendering in higher resolution, then inserting this 1024x1024 latent into the original image again is the expected behavior. This does not happen when the inpaint respective field is > 0, as it's the case on the default option.

Maxbe you can rephrase what does not work for you as i might not understand your initial request correctly.

[mashb1t]

Closing as stale, please reply to open this issue again.