Home Creators Posts Import Register Favorites Logout

Downloads

Content

Generate projection mapping content for any object. Using comfyUI with some mask segmentation and controlnets, you can auto-generate unlimited content with this workflow. You just need a mask of your projection surface and some style references.

IG: https://www.instagram.com/reflekkt_/

Overview of the Workflow:

Capture a photo from the projector's perspective.

Make a mask of your projection surface from that photo. Use different colors to assign different style references to these areas.

Select style references for your content.

Use comfyUI to generate content. (Set auto-queue to iterate through your style reference folder).

Interpolate the content with Flowframes and finalize the mapping in TouchDesigner or any other mapping software.

Links:

comfyUI installation: https://www.youtube.com/watch?v=E_D7y0YjE88&t=40s&ab_channel=MDMZ

Absolute Reality 1.8.1 model: https://civitai.com/models/81458?modelVersionId=132760

lcm-lora-sd15 https://huggingface.co/latent-consistency/lcm-lora-sdv1-5/tree/main

Flowframes Interpolation: https://nmkd.itch.io/flowframes

Pixel Upscaler Model: https://civitai.com/models/147817/realesrganx4plus

Files

Comments

Loya Ni

Hi! Tell me please what I am doing wrong - Error occurred when executing ImageDirIterator: No valid image files found in directory 'C:\Users\User\Desktop\ni\ref' with patterns '0'. I copied files from styleReferencesExamples for this folder

Zam Taranto

Hi mate, thanks for the tutorial and files! I'm trying to both learn ComfyUI and get this method working for a live projection job asap 🥵 I got loads of errors initially trying to use your json, so I recreated all nodes manually step by step to see where the issues were. It seems to be the AnimateDiff section thats causing me issues. Wondering if you came across this at all when you were building it. Any insights you might have are much appreciated 🙏🏽 Error Error while deserializing header: HeaderTooLarge Details { "error": { "node_id": "81", "executed": [ "57", "32", "30", "84", "82", "43", "77", "83", "78", "65", "35", "67", "15", "16", "68", "28", "42" ], "node_type": "ADE_AnimateDiffLoaderWithContext", "prompt_id": "U6e073he0wbuSlNp-lmLe", "timestamp": 1723775687212, "traceback": [ " File \"/app/execution.py\", line 152, in recursive_execute\n output_data, output_ui = get_output_data(obj, input_data_all)\n", " File \"/app/execution.py\", line 82, in get_output_data\n return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)\n", " File \"/app/execution.py\", line 75, in map_node_over_list\n results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))\n", " File \"/app/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/nodes_gen1.py\", line 138, in load_mm_and_inject_params\n motion_model = load_motion_module_gen1(model_name, model, motion_lora=motion_lora, motion_model_settings=motion_model_settings)\n", " File \"/app/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_injection.py\", line 1224, in load_motion_module_gen1\n load_motion_lora_as_patches(motion_model, lora)\n", " File \"/app/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_injection.py\", line 1153, in load_motion_lora_as_patches\n state_dict = comfy.utils.load_torch_file(lora_path)\n", " File \"/app/custom_nodes/ComfyUI-PhotoMaker-Plus/.patches.py\", line 5, in load_torch_file\n sd = safetensors.torch.load_file(ckpt, device=device.type)\n", " File \"/usr/local/lib/python3.10/dist-packages/safetensors/torch.py\", line 311, in load_file\n with safe_open(filename, framework=\"pt\", device=device) as f:\n" ], "exception_type": "safetensors_rust.SafetensorError", "exception_message": "Error while deserializing header: HeaderTooLarge" } }

B. Adam Bagolyszkij

Hey mate, many thanks for this tutorial and workflow its amazing! However there is something wrong here. I installed Fooocus Ksampler but it says IMPORT FAILED. Which Fooocus Ksampler are you using which is working correctly, or is there any trick about it? Many thanks! :)

Wesley Messina

Error occurred when executing ImageDirIterator: No valid image files found in directory 'C:\PM\styleReferencesExamples' with patterns '0'. File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 317, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 192, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_cspnodes\cspnodes.py", line 72, in get_images_by_index raise FileNotFoundError(f"No valid image files found in directory '{directory_path}' with patterns '{glob_patterns}'.")

reflekkt

Hi Wesley, if you right click on the image/video dir iterator and click reset/fix node, then put your path to the files, it should work. For some reason the pattern parameter is not correct when it is launched the first time. So yeah, a reset should fix it. Let me know if that helped.

Wesley Messina

Error occurred when executing IPAdapterUnifiedLoader: IPAdapter model not found. File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 317, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 192, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 573, in load_models raise Exception("IPAdapter model not found.")

Don Burroni

I get an error with the HighRes-Fix Script, i have to turn off use the same seed to get it working, any ideas? i made a new node and plugged it in but get the same

menybliss

Thanks for sharing this great workflow!! one issue that i encounter is about the Node : aio aux preprocessor. the preprocessor are missing, like MiDaS- DepthMap from annotator folder( \ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts\lllyasviel\Annotators) . where they can be downloaded from? any link ?

Fiona Elena

Where can I get the Fooocus_KSamplerEfficient node from? It's the only one I couldn't find with the node manager and also no fitting github repo

fei chen

hi, I hvae some troubleshoot about "ProjectionMapping_comfyUI_Workflow.json". Run the workflow in comfyUI the fooocus--KsamplerEfficet can not be found. I have installed ComfyUI-fooocuse-ksamplerEddicet, but the troubleshoot still.