Replies: 4 comments 1 reply
-
|
https://colab.research.google.com/drive/1xwBjrCWtZvh-XlTIk2lyQ5sFjDxkcsqW#scrollTo=2QjwpvNpFrRJ |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
-
|
What's the point if you can generate much faster on a GPU? |
Beta Was this translation helpful? Give feedback.
-
|
iam use tpu for big ram amd run focuse on cpu |
Beta Was this translation helpful? Give feedback.
-
|
Already up-to-date |
Beta Was this translation helpful? Give feedback.
-
fooocus run with me on cpu
!pip install tensorflow-cpu
!pip install pygit2==1.15.1
%cd /content
!git clone https://github.com/lllyasviel/Fooocus.git
%cd /content/Fooocus
!python /content/Fooocus/entry_with_update.py --share --always-cpu
Already up-to-date Update succeeded. [System ARGV] ['/content/Fooocus/entry_with_update.py', '--share', '--always-cpu'] Python 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] Fooocus version: 2.5.5 [Cleanup] Attempting to delete content of temp dir /tmp/fooocus [Cleanup] Cleanup successful Running on 48 CPU threads Total VRAM 342591 MB, total RAM 342591 MB Set vram state to: DISABLED Always offload VRAM Device: cpu VAE dtype: torch.float32 /usr/local/lib/python3.10/dist-packages/numba/np/ufunc/parallel.py:371: NumbaWarning: The TBB threading layer requires TBB version 2021 update 6 or later i.e., TBB_INTERFACE_VERSION >= 12060. Found TBB_INTERFACE_VERSION = 12050. The TBB threading layer is disabled. warnings.warn(problem) Using sub quadratic optimization for cross attention, if you have memory or speed issues try using: --attention-split Refiner unloaded. Running on local URL: http://127.0.0.1:7865
IMPORTANT: You are using gradio version 3.41.2, however version 4.29.0 is available, please upgrade.
model_type EPS UNet ADM Dimension 2816 Running on public URL: https://1b6636ec14a73f6262.gradio.live
This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run gradio deploy from Terminal to deploy to Spaces (https://huggingface.co/spaces) 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_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: /content/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors VAE loaded: None Request to load LoRAs [('sd_xl_offset_example-lora_1.0.safetensors', 0.1)] for model [/content/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors]. Loaded LoRA [/content/Fooocus/models/loras/sd_xl_offset_example-lora_1.0.safetensors] for UNet [/content/Fooocus/models/checkpoints/juggernautXL_v8Rundiffusion.safetensors] with 788 keys at weight 0.1. Fooocus V2 Expansion: Vocab with 642 words. Fooocus Expansion engine loaded for cpu, use_fp16 = False. Requested to load SDXLClipModel Requested to load GPT2LMHeadModel Loading 2 new models Started worker with PID 8748 App started successful. Use the app with http://127.0.0.1:7865/ or 127.0.0.1:7865 or https://1b6636ec14a73f6262.gradio.live [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 = 6137604482871942681 [Parameters] CFG = 4 [Fooocus] Loading control models ... [Parameters] Sampler = dpmpp_2m_sde_gpu - karras [Parameters] Steps = 30 - 15 [Fooocus] Initializing ... [Fooocus] Loading models ... Refiner unloaded. [Fooocus] Processing prompts ... [Fooocus] Preparing Fooocus text #1 ... [Prompt Expansion] dog, dramatic, bright colors, sharp focus, intricate, elegant, highly detailed, beautiful, attractive, depicted, rich, meticulous, creative, light novel, fancy, cute, cheerful, glowing, artistic, fine detail, colorful, winning, complex, elaborate, enhanced, color, clear, fair, perfect, pretty, radiant, loving, delicate, friendly, quiet [Fooocus] Preparing Fooocus text #2 ... [Prompt Expansion] dog, cinematic, epic, dynamic light, ambient, crisp quality, highly detailed, professional, fair, clear, color, artistic, winning, complex, imposing, contemporary, rich, vivid, beautiful, infinite, symmetry, great, perfect, atmosphere, amazing, elegant, sharp focus, creative, fantastic, expressive, awesome, full, fabulous, marvelous, glowing, wonderful [Fooocus] Encoding positive #1 ... [Fooocus] Encoding positive #2 ... [Fooocus] Encoding negative #1 ... [Fooocus] Encoding negative #2 ... [Parameters] Denoising Strength = 1.0 [Parameters] Initial Latent shape: Image Space (896, 1152) Preparation time: 6.08 seconds Using karras scheduler. [Fooocus] Preparing task 1/2 ... [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 5.08 seconds 100% 30/30 [10:53<00:00, 21.79s/it] Requested to load AutoencoderKL Loading 1 new model [Fooocus] Saving image 1/2 to system ... Image generated with private log at: /content/Fooocus/outputs/2024-10-03/log.html Generating and saving time: 669.16 seconds [Fooocus] Preparing task 2/2 ... [Sampler] refiner_swap_method = joint [Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828 100% 30/30 [09:35<00:00, 19.20s/it] [Fooocus] Saving image 2/2 to system ... Image generated with private log at: /content/Fooocus/outputs/2024-10-03/log.html Generating and saving time: 585.94 seconds [Enhance] Skipping, preconditions aren't met Processing time (total): 1255.10 seconds Total time: 1261.22 seconds
Beta Was this translation helpful? Give feedback.
All reactions