Easy and fast text to 3D & image to 3D with TripoSR in ComfyUI AI

In this video I will show you how you can easily and fast create 3D models from a text prompt. We will use TripoSR in ComfyUI.

Please comment below if you have questions or want to tell me your suggestions for future videos.

Get this and many other workflows on Patreon with Base membership:

Get the custom nodes:

Get Blender 3D:

Find the other 3D related tutorials for ComfyUI here:

Buy me a coffee:

Connect with me:

#comfyui #stablediffusion #tutorial #animatediff #automatic1111 #aiart #ai #lama #tutorial #howto

[neuron_ai]

Hey guys, it seems that the TripoSR addon is broken at the moment. I am quite sure that it has to do with the recent ComfyUI updates. You can try the CRM addon instead but the installation is quite difficult. As soon as I have updates on this I will let you know.

[welsonfy]

Thanks. Possible convert to 3d from images multi-view ?

[Lovepeace]

Hi guys,

i need some help too, i meet the issue as below, how can i fix it?

TripoSRSampler
Cannot handle this data type: (1, 1, 5), |u1

# ComfyUI Error Report
## Error Details
- **Node Type:** TripoSRSampler
- **Exception Type:** TypeError
- **Exception Message:** Cannot handle this data type: (1, 1, 5), |u1
## Stack Trace
```
File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb,


File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, 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,


File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)

File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))


File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-TripoSR\__init__.py", line 92, in sample
image = Image.fromarray(np.clip(255. * image, 0, 255).astype(np.uint8))

[FlorinGN]

As a 3D Specialist, I find this scary and useful at the same time

[Rimbo]

Excellent idea my friend ! But is not working for me. I replicate your workflow, with the model TripoSR, but the results are so bad man... in a very poor definition... I tried to modify the parameters, but nothing change... What can i do ?

[giovannigiorgio]

Does anybody know how to solve the problem that the TripoSR viewer says "loading scene" and do nothing? Thanks.