zoezhu

For who want the rendered face is as the same postion as input image, the folowing code may be help. ops_detail = self.render(verts, trans_verts, opdict['uv_texture'], codedict['light']) visdict = { 'inputs':...

I met the same error too, I found this can be resolved by installing **TensorFlowTTS** from this repo given. ```shell cd TensorFlowTTS python setup.py install ```

I encountered the same error too, I solved this by chaning **def rasterize** as following: ```python # Deep3DFaceReconstruction/tf_mesh_renderer/mesh_renderer/rasterize_triangles.py _MINIMUM_PERSPECTIVE_DIVIDE_THRESHOLD = 1e-6 def rasterize(world_space_vertices, attributes, triangles, camera_matrices, image_width, image_height, background_value): clip_space_vertices...

It's 2022 now, code is still on the way ...

I met this issue too, in my case, I pull new code and lauch webui, and new launch.py install xformer again, which version is xformers==0.0.16rc425 and not compiled with my...

@konioyxgq I haven't compared them yet, but that's a good suggestion to do that. I will update the result once I do that experiment. Thank you!

您好，我的邮箱是**[email protected]**，期待交流和指导！

I met several errors when run "web_demo.py" too, and I change it as following, then I can run it now. Please make sure your weight file is in right path...

> How do you set the ckpt_path?  , if you set the ckpt of InternVideo2_Stage2 to `vision_ckpt_path`, it shouldn't meet size mismatch of `text_proj.weight`. Can you explain this with...

看样例是支持了Qwen3的MOE结构，但Qwen3VL的MOE还是没有