Long time waiting for photo upscale

[daniij]

Read Troubleshoot

[x] I admit that I have read the Troubleshoot before making this issue.

Describe the problem
Long time waiting for photo upscale on AMD RX6800 video card. Photo upscale when Fast 2x is selected is 10 minutes, when 1.5 is selected more than 15 minutes.

Full Console Log
Fast 2x
📦[huerga@focus Fooocus]$ python3 entry_with_update.py --preset realistic
Already up-to-date
Update succeeded.
[System ARGV] ['entry_with_update.py', '--preset', 'realistic']
Loaded preset: /run/media/huerga/ssd/stable/Fooocus/presets/realistic.json
Failed to load config key: {"path_checkpoints": "/run/media/huerga/ssd/Fooocus/models/checkpoints"} is invalid or does not exist; will use {"path_checkpoints": "../models/checkpoints/"} instead.
Failed to load config key: {"path_loras": "/run/media/huerga/ssd/Fooocus/models/loras"} is invalid or does not exist; will use {"path_loras": "../models/loras/"} instead.
Failed to load config key: {"path_embeddings": "/run/media/huerga/ssd/Fooocus/models/embeddings"} is invalid or does not exist; will use {"path_embeddings": "../models/embeddings/"} instead.
Failed to load config key: {"path_vae_approx": "/run/media/huerga/ssd/Fooocus/models/vae_approx"} is invalid or does not exist; will use {"path_vae_approx": "../models/vae_approx/"} instead.
Failed to load config key: {"path_upscale_models": "/run/media/huerga/ssd/Fooocus/models/upscale_models"} is invalid or does not exist; will use {"path_upscale_models": "../models/upscale_models/"} instead.
Failed to load config key: {"path_inpaint": "/run/media/huerga/ssd/Fooocus/models/inpaint"} is invalid or does not exist; will use {"path_inpaint": "../models/inpaint/"} instead.
Failed to load config key: {"path_controlnet": "/run/media/huerga/ssd/Fooocus/models/controlnet"} is invalid or does not exist; will use {"path_controlnet": "../models/controlnet/"} instead.
Failed to load config key: {"path_clip_vision": "/run/media/huerga/ssd/Fooocus/models/clip_vision"} is invalid or does not exist; will use {"path_clip_vision": "../models/clip_vision/"} instead.
Failed to load config key: {"path_fooocus_expansion": "/run/media/huerga/ssd/Fooocus/models/prompt_expansion/fooocus_expansion"} is invalid or does not exist; will use {"path_fooocus_expansion": "../models/prompt_expansion/fooocus_expansion"} instead.
Failed to load config key: {"path_outputs": "/run/media/huerga/ssd/Fooocus/outputs"} is invalid or does not exist; will use {"path_outputs": "../outputs/"} instead.
Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
Fooocus version: 2.1.860
Running on local URL: http://127.0.0.1:7865

To create a public link, set share=True in launch().
[0104/184243.717177:ERROR:file_io_posix.cc(153)] open /home/huerga/.config/BraveSoftware/Brave-Browser/Crash Reports/pending/3c58b5e5-1c60-47da-80b2-cff1ef50626e.lock: File exists (17)
[0104/184243.717227:ERROR:file_io_posix.cc(153)] open /home/huerga/.config/BraveSoftware/Brave-Browser/Crash Reports/pending/c9579c1a-721d-47df-bb43-c0e7d39f7ef8.lock: File exists (17)
Окно или вкладка откроются в текущем сеансе браузера.
Total VRAM 16368 MB, total RAM 32019 MB
Set vram state to: NORMAL_VRAM
Always offload VRAM
Device: cuda:0 AMD Radeon RX 6800 : native
VAE dtype: torch.float32
Using sub quadratic optimization for cross attention, if you have memory or speed issues try using: --attention-split
Refiner unloaded.
model_type EPS
UNet ADM Dimension 2816
Using split attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using split attention in VAE
extra {'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
Base model loaded: /run/media/huerga/ssd/stable/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors
Request to load LoRAs [['SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors', 0.25], ['None', 1.0], ['None', 1.0], ['None', 1.0], ['None', 1.0]] for model [/run/media/huerga/ssd/stable/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors].
Loaded LoRA [/run/media/huerga/ssd/stable/Fooocus/models/loras/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors] for UNet [/run/media/huerga/ssd/stable/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors] with 788 keys at weight 0.25.
Loaded LoRA [/run/media/huerga/ssd/stable/Fooocus/models/loras/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors] for CLIP [/run/media/huerga/ssd/stable/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors] with 264 keys at weight 0.25.
Fooocus V2 Expansion: Vocab with 642 words.
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 0.64 seconds
App started successful. Use the app with http://127.0.0.1:7865/ or 127.0.0.1:7865
[Parameters] Adaptive CFG = 7
[Parameters] Sharpness = 2
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 3.0
[Parameters] Seed = 6979671936792233199
[Fooocus] Downloading upscale models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 30 - 15
[Fooocus] Initializing ...
[Fooocus] Image processing ...
[Fooocus] Upscaling image from (1152, 896) ...
Upscaling image with shape (1152, 896, 3) ...
Image upscaled.
Image generated with private log at: /run/media/huerga/ssd/stable/Fooocus/outputs/2024-01-04/log.html
Total time: 589.37 seconds

Upscale 1.5x
[Parameters] Adaptive CFG = 7
[Parameters] Sharpness = 2
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 3.0
[Parameters] Seed = 5461728074585361171
[Fooocus] Downloading upscale models ...
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 18 - 9
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding positive #2 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Encoding negative #2 ...
[Fooocus] Image processing ...
[Fooocus] Upscaling image from (1152, 896) ...
Upscaling image with shape (1152, 896, 3) ...
Image upscaled.
[Fooocus] VAE encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.19 seconds
Final resolution is (1728, 1344).
[Parameters] Denoising Strength = 0.382
[Parameters] Initial Latent shape: torch.Size([1, 4, 216, 168])
Preparation time: 707.57 seconds
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 0.5689725279808044
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.07 seconds
100%|█████████████████████████████████████████████████████████████████████████| 18/18 [01:11<00:00, 3.98s/it]
Requested to load AutoencoderKL
Loading 1 new model
Image generated with private log at: /run/media/huerga/ssd/stable/Fooocus/outputs/2024-01-04/log.html
Generating and saving time: 141.01 seconds
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 0.5689725279808044
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.62 seconds
100%|█████████████████████████████████████████████████████████████████████████| 18/18 [01:01<00:00, 3.42s/it]
Requested to load AutoencoderKL
Loading 1 new model
Image generated with private log at: /run/media/huerga/ssd/stable/Fooocus/outputs/2024-01-04/log.html
Generating and saving time: 70.25 seconds
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
[Fooocus Model Management] Moving model(s) has taken 0.32 seconds
Total time: 923.97 seconds