sairajk / easi-tex Goto Github PK

As expected, since this texture generation pipeline has no way to ensure consistent texture generation across the different views, and it doesn't try to keep the lighting condition the same across the different views, so the result is rather messy and unusable:

Last year, I tried the similar workflow, but in addition to Canny ControlNet & IP-Adaptor, I used AnimateDiff as a mean to ensure consistent texture generation across the different views, and use Brightness ControlNet to keep the lighting condition the same across the different views.

Result is better but still takes long to generate & same parameters are not always gives good results.

Mathutils is in Blender, right? When I use pip install, it prompts installation failure. May I ask if it is possible
Do I need to configure the blender path separately?

easi-tex/models/ControlNet/ldm/modules/attention.py", line 302, in init
self.attn1 = attn_cls(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout,
TypeError: CrossAttention.init() got an unexpected keyword argument 'ip_adapter_use_tokens'