Új hozzászólás Aktív témák

• #43563 MasterDeeJay veterán Raymond #43561

  Új Válasz 2024-03-29 12:49:38 #43563

  Új hozzászólás

  Összes hozzászólása itt Válaszok az összes hozzászólására itt Válaszok erre a hozzászólásra

  Privát üzenet küldése

  

  MasterDeeJay

  veterán

  LOGOUT blog

  válasz Raymond #43561 üzenetére

  Felraktam a fooocust.

  Total VRAM 16384 MB, total RAM 130776 MB
  Set vram state to: NORMAL_VRAM
  Always offload VRAM
  Device: cuda:0 Tesla V100-PCIE-12GB : native
  VAE dtype: torch.float32
  Using pytorch cross attention
  Refiner unloaded.
  Running on local URL: http://127.0.0.1:7865
  model_type EPS
  UNet ADM Dimension 2816

  1024x1024-en elég lassú.

  [Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] proharver test image video cards, dramatic color, intricate, elegant, highly detailed, extremely scientific, shining, sharp focus, innocent, fine detail, beautiful, inspired, illustrious, complex, epic, amazing composition, fancy, elite, designed, clear, crisp, polished, artistic, symmetry, rich deep colors, cinematic, light, striking, marvelous, moving, very
[Fooocus] Preparing Fooocus text #2 ...
[Prompt Expansion] proharver test image video cards, mystical surreal, highly detailed, very beautiful, dramatic light, cinematic composition, clear artistic balance, inspired color, intricate, elegant, perfect background, professional fine detail, extremely nice colors, stunning, cute, futuristic, best, creative, positive, thoughtful, vibrant, successful, pure, hopeful, whole, romantic, iconic, shiny
[Fooocus] Encoding positive #1 ...
[Fooocus Model Management] Moving model(s) has taken 1.27 seconds
[Fooocus] Encoding positive #2 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Encoding negative #2 ...
[Parameters] Denoising Strength = 1.0
[Parameters] Initial Latent shape: Image Space (1024, 1024)
Preparation time: 3.55 seconds
[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 34.70 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [01:05<00:00, 2.19s/it]
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.89 seconds
Image generated with private log at: T:\AI\Fooocus\Fooocus\outputs\2024-03-29\log.html
Generating and saving time: 103.38 seconds
[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 27.48 seconds
33%|███████████████████████████▎ | 10/30 [00:21<00:43, 2.18s/it]

  Annyi hogy a kártyát átraktam WDDM módba nvidia-smi-vel.
  Így már Aida is látja rendesen meg a hwinfó is.
  
  Játékra is alkalmas lenne de a pcie1x miatt nincs értelme.

  FP16-ot kellene tudnia pedig. Még annyi hogy alig melegszik 60 fok felett alig látom pedig nem is megy rá rendesen levegő csak ilyen 2 cm hézagba fujatok bele blowerrel. Az előző Tesla M40 már ennyinél megfőtt volna.

  [ Szerkesztve ]

  Vintage Story PH szervere újra fut!

• #43570 lenox veterán Raymond #43561

  Új Válasz 2024-03-29 15:22:35 #43570

  Új hozzászólás

  Összes hozzászólása itt Válaszok az összes hozzászólására itt Válaszok erre a hozzászólásra

  Privát üzenet küldése

  

  lenox

  veterán

  válasz Raymond #43561 üzenetére

  Nekem ilyen:

  Total VRAM 49140 MB, total RAM 130834 MB
  Set vram state to: NORMAL_VRAM
  Always offload VRAM
  Device: cuda:0 NVIDIA RTX 6000 Ada Generation : native
  VAE dtype: torch.bfloat16

  [Fooocus] Encoding positive #1 ...
  [Fooocus Model Management] Moving model(s) has taken 0.14 seconds
  [Fooocus] Encoding positive #2 ...
  [Fooocus] Encoding negative #1 ...
  [Fooocus] Encoding negative #2 ...
  [Parameters] Denoising Strength = 1.0
  [Parameters] Initial Latent shape: Image Space (1024, 1024)
  Preparation time: 1.98 seconds
  [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 2.62 seconds
  100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [00:04<00:00, 6.36it/s]
  Requested to load AutoencoderKL
  Loading 1 new model
  [Fooocus Model Management] Moving model(s) has taken 0.14 seconds
  Image generated with private log at: S:\fooocus\Fooocus\outputs\2024-03-29\log.html
  Generating and saving time: 8.16 seconds
  [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 1.23 seconds
  100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [00:04<00:00, 6.29it/s]
  Requested to load AutoencoderKL
  Loading 1 new model
  [Fooocus Model Management] Moving model(s) has taken 0.13 seconds
  Image generated with private log at: S:\fooocus\Fooocus\outputs\2024-03-29\log.html
  Generating and saving time: 6.73 seconds
  Requested to load SDXLClipModel
  Requested to load GPT2LMHeadModel
  Loading 2 new models
  Total time: 16.93 seconds
  [Fooocus Model Management] Moving model(s) has taken 0.57 seconds

• #43577 MasterDeeJay veterán Raymond #43561

  Új Válasz 2024-04-01 08:05:00 #43577

  Új hozzászólás

  Összes hozzászólása itt Válaszok az összes hozzászólására itt Válaszok erre a hozzászólásra

  Privát üzenet küldése

  

  MasterDeeJay

  veterán

  LOGOUT blog

  válasz Raymond #43561 üzenetére

  SD-re felraktam a tensorRT kieget bekapcsolva 8 kikapcsolva 3

  Nem tudom hogyan lehetne tesztelni rendesen.

  Loading TensorRT engine: T:\AI\stable-diffusion-webui\models\Unet-trt\v1-5-pruned-emaonly_d7049739_cc70_sample=2x4x64x64-timesteps=2-encoder_hidden_states=2x77x768.trt
Loaded Profile: 0
        sample = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]
        timesteps = [(2,), (2,), (2,)]
        encoder_hidden_states = [(2, 77, 768), (2, 77, 768), (2, 77, 768)]
        latent = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  7.84it/s]
Total progress: 30it [07:30, 15.00s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  7.71it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  6.71it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  7.30it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  6.88it/s]
Dectivating unet: [TRT] v1-5-pruned-emaonly████████████████████████████████████████████| 20/20 [00:02<00:00,  8.02it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:06<00:00,  2.93it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:06<00:00,  2.94it/s]
Activating unet: [TRT] v1-5-pruned-emaonly█████████████████████████████████████████████| 20/20 [00:06<00:00,  3.01it/s]
Loading TensorRT engine: T:\AI\stable-diffusion-webui\models\Unet-trt\v1-5-pruned-emaonly_d7049739_cc70_sample=2x4x64x64-timesteps=2-encoder_hidden_states=2x77x768.trt
Loaded Profile: 0
        sample = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]
        timesteps = [(2,), (2,), (2,)]
        encoder_hidden_states = [(2, 77, 768), (2, 77, 768), (2, 77, 768)]
        latent = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  7.88it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  6.85it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  8.00it/s]

  [ Szerkesztve ]

  Vintage Story PH szervere újra fut!

Új hozzászólás Aktív témák