SUDO-AI-3D / zero123plus

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

SUDO-AI-3D/zero123plus Issues

How to align the coordinate system of zero123 in threestudio?
Updated 10 days ago1
Depth map size ratios for depth ControlNet
Updated 10 days ago1
About dataset
Closed 10 days ago1
The difference between v1.2 and v1.1 in the network architecture
Closed 10 days ago1
CUDA out of memory. Tried to allocate error
Updated 10 days ago2
would you release the training code in the future?
Updated 21 days ago
Some questions regarding the input and output latent scaling
Closed 5 months ago3
img_to_mv.py without cuda
Closed 23 days ago1
Training details
Closed 5 months ago5
How to change Camera Parameters of output view?
Updated a month ago
Can I get train code?
Updated a month ago
scaling about reference attention
Closed 3 months ago2
Would it be feasible to provide more than one view angle as input to better the quality of the outputs.
Updated 2 months ago
About the object normalization in v1.2
Closed 2 months ago2
camera pose
Closed 3 months ago1
How can I change the camera pose and the size of the image?
Closed 3 months ago2
camera FOV
Closed 3 months ago1
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'
Closed 3 months ago1
training resolution 320^2 instead of 512^2?
Closed 3 months ago2
something about trainning detail..
Closed 3 months ago2
depth control for v1.2 ?
Updated 3 months ago1
getting normals/depth
Closed 4 months ago3
Is there an approach to remove the gray background purely?
Closed 3 months ago4
training data
Closed 4 months ago1
Depth conditioning is not working
Updated 4 months ago5
v-prediction
Closed 4 months ago3
Question about ReferenceOnlyAttnProc
Closed 4 months ago1
Is the training based on LoRA or just tune the original model parameters!
Closed 6 months ago3
question about forward_cond
Closed 5 months ago2
data of depth ControlNet
Closed 5 months ago6
About the scheduler
Closed 6 months ago1
Increasing the image size in the diffuser pipeline causes the output image to collapse
Closed 6 months ago1
Reference Only Local Conditioning Clarification
Closed 6 months ago1
Questions of camera settings when rendering the Objaverse dataset
Closed 6 months ago2
Objaverse Dataloader: Seeking Input/Output Details for Fine-tuning
Updated 6 months ago1
Not generating input image's colors when depth maps passed
Closed 6 months ago2
Discussion/question: What to do with the generated images ? (texturing 3d models)
Updated 6 months ago1
Adding License section in Readme
Closed 7 months ago
Adding Contributors section to the readme.md
Closed 7 months ago1
Adding code-of-conduct to the repo !
Closed 7 months ago3
Reference attention
Closed 7 months ago1
How to get the textured mesh?
Closed 7 months ago4
What dataset was used?
Updated 7 months ago2
How to control the output image to be in those six viewpoints without showing the input camera position？
Updated 7 months ago5
Proposal for Collaborative 3D Reconstruction Between Two Projects
Updated 7 months ago2
could camera parameters be changed?
Updated 7 months ago3
Lens distortion
Closed 7 months ago2
about FOV for rendering dataset
Closed 7 months ago1
What is the "scaled-linear noise scheduler"?
Closed 7 months ago1
How do camera viewpoints work at training and inference?
Updated 7 months ago2