Faceswap crashes

[sondresorbye]

Describe the problem The program crashes when trying to use an image as prompt and selecting the faceswap advanced option

Full Console Log Requirement already satisfied: pygit2==1.12.2 in /usr/local/lib/python3.10/dist-packages (1.12.2) Requirement already satisfied: cffi>=1.9.1 in /usr/local/lib/python3.10/dist-packages (from pygit2==1.12.2) (1.16.0) Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.9.1->pygit2==1.12.2) (2.21) /content fatal: destination path 'Fooocus' already exists and is not an empty directory. /content/Fooocus Already up-to-date Update succeeded. [System ARGV] ['entry_with_update.py', '--preset', 'realistic', '--share'] Loaded preset: /content/Fooocus/presets/realistic.json Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] Fooocus version: 2.1.824 Running on local URL: http://127.0.0.1:7865/ Running on public URL: https://fb6371be5d9ced0c1d.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) Total VRAM 15102 MB, total RAM 12983 MB 2023-11-29 21:03:50.202601: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2023-11-29 21:03:50.202658: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2023-11-29 21:03:50.202708: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2023-11-29 21:03:52.244376: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Set vram state to: NORMAL_VRAM Disabling smart memory management Device: cuda:0 Tesla T4 : native VAE dtype: torch.float32 Using pytorch cross attention Refiner unloaded. model_type EPS adm 2816 Using pytorch attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using pytorch attention in VAE extra keys {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale'} Base model loaded: /content/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 [/content/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors]. Loaded LoRA [/content/Fooocus/models/loras/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors] for UNet [/content/Fooocus/models/checkpoints/realisticStockPhoto_v10.safetensors] with 788 keys at weight 0.25. Loaded LoRA [/content/Fooocus/models/loras/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors] for CLIP [/content/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 1.30 seconds App started successful. Use the app with http://127.0.0.1:7865/ or 127.0.0.1:7865 or https://fb6371be5d9ced0c1d.gradio.live/ [Parameters] Adaptive CFG = 7 [Parameters] Sharpness = 2 [Parameters] ADM Scale = 1.5 : 0.8 : 0.3 [Parameters] CFG = 3.0 [Parameters] Seed = 604471590939558783 [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] Portrait of a young man on the beach, full light, gorgeous, amazing, elegant, intricate, highly detailed, dynamic, rich deep vivid colors, beautiful, very inspirational, inspiring, thought, fancy, sharp focus, colorful, epic, professional, artistic, new, charismatic, cool, brilliant, awesome, attractive, shiny, fine detail, pretty, focused, creative [Fooocus] Preparing Fooocus text #2 ... [Prompt Expansion] Portrait of a young man on the beach, full pretty, attractive, fine detail, intricate, elegant, luxury, elite, dramatic light, highly detailed, cinematic, complex, sharp focus, illuminated, amazing, marvelous, thought, epic, fabulous, colorful, shiny, brilliant, symmetry, great, excellent composition, ambient, dynamic, vibrant colors, relaxed, beautiful [Fooocus] Encoding positive #1 ... [Fooocus Model Management] Moving model(s) has taken 0.11 seconds [Fooocus] Encoding positive #2 ... [Fooocus] Encoding negative #1 ... [Fooocus] Encoding negative #2 ... [Parameters] Denoising Strength = 1.0 [Parameters] Initial Latent shape: Image Space (1152, 896) Preparation time: 3.60 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 2.40 seconds 100% 60/60 [00:55<00:00, 1.09it/s] Image generated with private log at: /content/Fooocus/outputs/2023-11-29/log.html Generating and saving time: 60.73 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 2.01 seconds 100% 60/60 [00:56<00:00, 1.06it/s] Image generated with private log at: /content/Fooocus/outputs/2023-11-29/log.html Generating and saving time: 61.85 seconds Requested to load SDXLClipModel Requested to load GPT2LMHeadModel Loading 2 new models [Fooocus Model Management] Moving model(s) has taken 1.57 seconds Total time: 131.21 seconds [Parameters] Adaptive CFG = 7 [Parameters] Sharpness = 2 [Parameters] ADM Scale = 1.5 : 0.8 : 0.3 [Parameters] CFG = 3.0 [Parameters] Seed = 7513856776859948774 [Fooocus] Downloading control models ... [Fooocus] Loading control models ... extra keys clip vision: ['vision_model.embeddings.position_ids']

[heypratik]

Same issue on windows. Faceswap crashes the program

[psychonaut97]

any other tools to use faceswap? thanks for any tipp

[itsachrafmansari]

@psychonaut97 : any other tools to use faceswap? thanks for any tipp

I found this replica of Fooocus API that has the FaceSwap feature working without errors (Altough you'll have to login with your GitHub account to use it and it's limited to a certain number of images before you have to pay to continue using it) : https://replicate.com/konieshadow/fooocus-api

Also, since the images produced by the FaceSwap feature may not be highly identical, I suggest making and scaling up the images with Fooocus, then using this face swapping service to get almost identical result of the real faces : https://remaker.ai/face-swap-free

[ccatty25250]

I still have this issue on the Colab workbook when using the Faceswap function. I don't know why this would happen.

[tbuyle]

Try changing the last line of the colab with :

!python entry_with_update.py --share --preset --always-high-vram --all-in-fp16 See also https://github.com/lllyasviel/Fooocus/issues/1377

[mashb1t]

see https://github.com/lllyasviel/Fooocus/issues/1377#issuecomment-1853958551