Issue with clip_vision model

[lipsumar]

Hi,

I can't wait to try your workflow but i'm getting an error that doesn't make sense to me:

Error occurred when executing BatchCreativeInterpolation:

Missing CLIPVision model.

File "/workspace/comfyui_launcher_projects/steerable-motion/comfyui/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/workspace/comfyui_launcher_projects/steerable-motion/comfyui/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/workspace/comfyui_launcher_projects/steerable-motion/comfyui/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/workspace/comfyui_launcher_projects/steerable-motion/comfyui/custom_nodes/steerable-motion/SteerableMotion.py", line 449, in combined_function
model, = ipadapter_application.apply_ipadapter(model=model, ipadapter=ipadapter, image=prepped_image, weight=base_ipa_advanced_settings["ipa_weight"], weight_type=base_ipa_advanced_settings["ipa_weight_type"], start_at=base_ipa_advanced_settings["ipa_starts_at"], end_at=base_ipa_advanced_settings["ipa_ends_at"], clip_vision=clip_vision, attn_mask=mask,image_negative=negative_noise,embeds_scaling=base_ipa_advanced_settings["ipa_embeds_scaling"])
File "/workspace/comfyui_launcher_projects/steerable-motion/comfyui/custom_nodes/steerable-motion/imports/ComfyUI_IPAdapter_plus/IPAdapterPlus.py", line 396, in apply_ipadapter
raise Exception("Missing CLIPVision model.")

According to this error, and looking at the code, it seems clip_vision is None here. It is suppose to be passed down by this line, which is getting it straight from the node input in combined_function.

Looking at the code, there's no reason it would be None. I'm using your creative_interpolation_example.json unmodified, so i do have a "Load clip vision" node connected to the clip_vision input - and that loader executes fine.

Do you have an idea what the problem could be ? I would greatly appreciate any pointer!

The only thing that's not exactly as your workflow is the model 100_motion_director_lora_r64_temporal_unet.safetensors that I can't find anywhere. I'm not sure it's related, but I'd also appreciate a link to it!

Thanks again for your work, steerable-motion seems stunning!

[peteromallet]

Could you update your IP-Adapter node and Comfy and let me know if this is still happening?

[lipsumar]

nevermind, I'm the model was literally not loaded 🤦 I expected the "load CLIP Vision" node to fail in that case, but it just happily loaded nothing. I apologize for wasting your time on such a spectacularly stupid issue, the workflow is working perfectly! 👌

[peteromallet]

haha no problem it happens, glad you're sorted!