Works on GUI but fails in the script. something with Image1 kwargs

[blademarketing]

I have a super simple workflow that takes 3 images, feeds them into ip adapter and generates an image, then upsacles it.

Works fine on GUI Here is the original workflow test.json

It succesfully compiled it into a .py script and then when i run it with python i get this:

`model_type EPS adm 0 Using pytorch attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using pytorch attention in VAE clip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight'] clip unexpected: ['clip_l.transformer.text_model.embeddings.position_ids'] Requested to load SD1ClipModel Loading 1 new model Using pytorch attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using pytorch attention in VAE Leftover VAE keys ['model_ema.decay', 'model_ema.num_updates'] INFO: Clip Vision model loaded from C:\ComfyUI\ComfyUI\models\clip_vision\CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors INFO: IPAdapter model loaded from C:\ComfyUI\ComfyUI\models\ipadapter\ip-adapter-faceid-plusv2_sd15.bin INFO: LoRA model loaded from C:\ComfyUI\ComfyUI\models\loras\ip-adapter-faceid-plusv2_sd15_lora.safetensors Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\ComfyUI\ComfyUI\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:\ComfyUI\ComfyUI\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:\ComfyUI\ComfyUI\models\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0 Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\ComfyUI\ComfyUI\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:\ComfyUI\ComfyUI\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5 set det-size: (640, 640) INFO: InsightFace model loaded with CPU provider Traceback (most recent call last): File "C:\ComfyUI\ComfyUI\ComfyUI-to-Python-Extension\workflow_api.py", line 291, in main() File "C:\ComfyUI\ComfyUI\ComfyUI-to-Python-Extension\workflow_api.py", line 210, in main impactmakeimagebatch_32 = impactmakeimagebatch.doit() File "C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\util_nodes.py", line 378, in doit image1 = kwargs['image1'] KeyError: 'image1'

`C:\ComfyUI\ComfyUI\ComfyUI-to-Python-Extension>``

[blademarketing]

Made this video just to give you a clearer insight @pydn https://www.loom.com/share/d5ec93d744c544649847cdaf78f014a8

[atmaranto]

This issue may be fixed on my fork. Kwargs is now sent if requested by the function.

[pydn]

@blademarketing I made a few updates the last couple of days that may fix this issue so feel free to pull the latest version and check the output. If you are still running into issues, feel free to reopen this ticket