Combine ImagePrompt and FaceSwap crash Fooocus

[JulienFiant]

Read Troubleshoot

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

Describe the problem
A clear and concise description of what the bug is.

Full Console Log
Paste full console log here. You will make our job easier if you give a full log.

Hello All

I have an issue, i'm on Fooocus 2.1.862 working on a colab
When i tried to do an generation with an input imageprompt + an input faceswap, Fooocus stop to work with a Ctrl+C exit "^C"
I don't use any args with the python launcher and i tried with "Speed", "Quality" and "Extreme Speed", same result for all

Log :
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], ('sdxl_lcm_lora.safetensors', 1.0)] for model [/content/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors].
Loaded LoRA [/content/Fooocus/models/loras/sd_xl_offset_example-lora_1.0.safetensors] for UNet [/content/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors] with 788 keys at weight 0.1.
Loaded LoRA [/content/Fooocus/models/loras/sdxl_lcm_lora.safetensors] for UNet [/content/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors] with 788 keys at weight 1.0.
Requested to load SDXLClipModel
Loading 1 new model
unload clone 1
[Fooocus Model Management] Moving model(s) has taken 2.19 seconds
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Fooocus] Encoding positive #1 ...
[Fooocus Model Management] Moving model(s) has taken 0.12 seconds
[Fooocus] Image processing ...
Requested to load CLIPVisionModelWithProjection
Loading 1 new model
^C

Thanks you for your help

[mashb1t]

Closing as duplicate of #1709, #1574, etc.
Please check if #1710 works for you.