Stopped without error

[sebastien247]

Hi, Fooocus api suddenly stopped without error. I can found some logs else where ?

[System ARGV] ['main.py']
Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
Fooocus-API version: 0.3.30
Fooocus exists and URL is correct.
Fooocus checkout finished for 624f74a1ed78ea09467c856cef35aeee0af863f6.
[Fooocus-API] Task queue size: 100, queue history size: 0, webhook url: None
Preload pipeline
Total VRAM 5938 MB, total RAM 31814 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 Laptop GPU : native
VAE dtype: torch.bfloat16
Using pytorch cross attention
INFO:     Started server process [29902]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://127.0.0.1:8888 (Press CTRL+C to quit)
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_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
Base model loaded: /home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors
Request to load LoRAs [['sd_xl_offset_example-lora_1.0.safetensors', 0.1], ['None', 1.0], ['None', 1.0], ['None', 1.0], ['None', 1.0]] for model [/home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors].
Loaded LoRA [/home/sebastien/Studio/Fooocus/models/loras/sd_xl_offset_example-lora_1.0.safetensors] for UNet [/home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors] with 788 keys at weight 0.1.
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 0.25 seconds
[Task Queue] Waiting for task finished, job_id=5c9a9980-6465-44ad-a2f4-7d8b5c37454f
[Task Queue] Task queue start task, job_id=5c9a9980-6465-44ad-a2f4-7d8b5c37454f
[Parameters] Adaptive CFG = 7.0
[Parameters] Sharpness = 2.0
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 4.0
[Parameters] Seed = 1148032191865396475
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 30 - 15
[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_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
Base model loaded: /home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors
Request to load LoRAs [('sd_xl_offset_example-lora_1.0.safetensors', 0.1)] for model [/home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors].
Loaded LoRA [/home/sebastien/Studio/Fooocus/models/loras/sd_xl_offset_example-lora_1.0.safetensors] for UNet [/home/sebastien/Studio/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors] with 788 keys at weight 0.1.
Requested to load SDXLClipModel
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.98 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] ram zodiac portrait human representation with celestial glow, by Ewelina T Julian, ethereal atmosphere, Dreamlike colors, delicate strokes, a hint of movement, outer space background, nebula, shimmering gases, V4 quality, high detail, enchanted realism, vivid color, cinematic, epic, symmetry, magical, very inspirational, beautiful, elegant, complex
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Parameters] Denoising Strength = 1.0
[Parameters] Initial Latent shape: Image Space (1344, 768)
Preparation time: 9.48 seconds
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828
Requested to load SDXL
Loading 1 new model
[Task Queue] Already waiting for 10.2 seconds, job_id=5c9a9980-6465-44ad-a2f4-7d8b5c37454f
Processus arrêté```

[mrhan1993]

Is it gone? This looks like everything is normal

[sebastien247]

Excepted for "Processus arrêté"

[Mutai-Gilbert]

The app is running locally on http://127.0.0.1:8888. You need to navigate to that port in your browser to test the various endpoints. The error you're experiencing might be due to issues with your storage or RAM.

My understanding of stable diffusion is that it requires a lot of space, especially when using low-end GPUs.