[Bug]: Controlnet Faceid isn't worked

Checklist

[ ] The issue exists after disabling all extensions
[ ] The issue exists on a clean installation of webui
[ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[ ] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

I try to make a faceid using IpAdapter FaceID Plus V2 with InsightFace+CLIP-H preprocessor but no matter I try, the image never get anything like the reference image not sure it's lora or preprocessor. Here is my settings:

Forge still run normal but have warning like this: Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely (I already pasted my log file to check)

I check all function of controlnet like openpose, depth, canny and so on. It's worked fine so I guess only FaceID lora have problem

Steps to reproduce the problem

1- Write a sample prompt 2- Set up controlnet FaceID V2 3- Execute render

What should have happened?

WebUI should check where FaceID lora is loaded correctly or not

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

sysinfo-2024-03-02-09-50.json

Console logs

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f0.0.17v1.8.0rc-latest-269-gef35383b
Commit hash: ef35383b4a1189cbbaa3dea65bf77787385f62a9
Launching Web UI with arguments: --theme dark
Total VRAM 24575 MB, total RAM 32672 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3090 : native
Hint: your device supports --pin-shared-memory for potential speed improvements.
Hint: your device supports --cuda-malloc for potential speed improvements.
Hint: your device supports --cuda-stream for potential speed improvements.
VAE dtype: torch.bfloat16
CUDA Stream Activated:  False
Using pytorch cross attention
ControlNet preprocessor location: C:\AI\webui_forge_cu121_torch21\webui\models\ControlNetPreprocessor
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
[-] ADetailer initialized. version: 24.1.2, num models: 9
Loading weights [62bb78983a] from C:\AI\webui_forge_cu121_torch21\webui\models\Stable-diffusion\epicphotogasm_lastUnicorn.safetensors
Character Path:
Embedding Model value: None
LORA Model value: None
model_type EPS
UNet ADM Dimension 0
2024-03-02 16:48:47,961 - ControlNet - INFO - ControlNet UI callback registered.
Character Path:
Embedding Model value: None
LORA Model value: None
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 19.6s (prepare environment: 4.1s, import torch: 3.5s, import gradio: 1.0s, setup paths: 0.9s, initialize shared: 0.1s, other imports: 0.7s, load scripts: 7.2s, create ui: 1.6s, gradio launch: 0.4s).
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
Loading VAE weights specified in settings: C:\AI\webui_forge_cu121_torch21\webui\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) =  23303.9716796875
[Memory Management] Model Memory (MB) =  454.2076225280762
[Memory Management] Minimal Inference Memory (MB) =  1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) =  21825.764057159424
Moving model(s) has taken 0.05 seconds
Model loaded in 5.0s (load weights from disk: 0.1s, forge load real models: 2.0s, load VAE: 0.3s, calculate empty prompt: 2.5s).
2024-03-02 16:49:00,868 - ControlNet - INFO - ControlNet Input Mode: InputMode.SIMPLE
2024-03-02 16:49:00,869 - ControlNet - INFO - Using preprocessor: InsightFace+CLIP-H (IPAdapter)
2024-03-02 16:49:00,870 - ControlNet - INFO - preprocessor resolution = 0.5
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\AI\webui_forge_cu121_torch21\webui\models\insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\AI\webui_forge_cu121_torch21\webui\models\insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\AI\webui_forge_cu121_torch21\webui\models\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\AI\webui_forge_cu121_torch21\webui\models\insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\AI\webui_forge_cu121_torch21\webui\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (640, 640)
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
2024-03-02 16:49:03,457 - ControlNet - INFO - Current ControlNet IPAdapterPatcher: C:\AI\webui_forge_cu121_torch21\webui\models\ControlNet\ip-adapter-faceid-plusv2_sd15.bin
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 5 images in a total of 5 batches.
[LORA] Loaded C:\AI\webui_forge_cu121_torch21\webui\models\Lora\ip-adapter-faceid-plusv2_sd15_lora.safetensors for BaseModel-UNet with 128 keys at weight 0.7 (skipped 0 keys)
To load target model BaseModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) =  22903.341796875
[Memory Management] Model Memory (MB) =  1639.4137649536133
[Memory Management] Minimal Inference Memory (MB) =  1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) =  20239.928031921387
Moving model(s) has taken 0.50 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:04<00:00,  7.42it/s]
To load target model AutoencoderKL                                                    | 35/175 [00:04<00:17,  7.89it/s]
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) =  21211.07373046875
[Memory Management] Model Memory (MB) =  159.55708122253418
[Memory Management] Minimal Inference Memory (MB) =  1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) =  20027.516649246216
Moving model(s) has taken 0.10 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:04<00:00,  7.89it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:04<00:00,  7.88it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:04<00:00,  7.87it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:04<00:00,  7.83it/s]
Total progress: 100%|████████████████████████████████████████████████████████████████| 175/175 [00:24<00:00,  7.16it/s]
Total progress: 100%|████████████████████████████████████████████████████████████████| 175/175 [00:24<00:00,  7.84it/s]

Additional information

I updated the latest Forge

lllyasviel / stable-diffusion-webui-forge