Wonder3D

xxlong0/Wonder3D is ranked 19,285 among these 8 peers; zai-org/GLM-130B is ranked 19,277.

Wonder3D first generates consistent multi-view normal maps with corresponding color images via a cross-domain diffusion model, and then leverages a novel normal fusion method to achieve fast and high-quality reconstruction. 22 We have extent the [Wonder3D] to a more advanced version, Wonder3D++! 29 ** Fixed an issue in '/mvdiffusion/pipelines/pipeline_mvdiffusion_image' where cross-domain attention did not work correctly during classifier-free guidance (CFG) inference, causing misalignment between the RGB and normal generation results. ** To address

this issue, we need to place the RGB and normal domain inputs in the first and second halves of the batch, respectively, before feeding them into the model. This approach differs from the typical CFG method, which separates unconditional and conditional inputs into the first and second halves of the batch. The results before and after the bug fix are shown below: Fixed a severe training bug. The "zero_init_camera_projection" in 'configs/train/stage1-mix-6views-lvis. Otherwise

, the domain control and pose control will be invalid in the training. 19 Checkout our new model GeoWizard that jointly produces depth and normal with high fidelity from single images. 24 We release a large 3D native diffusion model CraftsMan3D that is directly trained on 3D representation and therefore is capable of producing complex structures. 29 We release a more powerful MV cross-domain diffusion model Era3D that jointly produces 512x512 color images and normal maps, but more importantly Era3D

could automatically figure out the focal length and elevation degree of the input image so that avoid geometry distortions. Usage Collaborations Our overarching mission is to enhance the speed, affordability, and quality of 3D AIGC, making the creation of 3D content accessible to all. While significant progress has been achieved in the recent years, we acknowledge there is still a substantial journey ahead. We enthusiastically invite you to engage in discussions and explore potential collaborations in any capacity. **If you're

interested in connecting or partnering with us, please don't hesitate to reach out via email (xxlong@connect. Welcome to train wonder3D on your personal data. 10 We release the inference model and codes. Preparation for inference Linux System Setup. Please switch to branch to see details of windows setup. MD Training Here we provide two training scripts and . The training has two stages: 1) first train multi-view attentions by randomly taking normal or color flag; 2) add cross-domain

attention modules into the SD model, and only optimize the newly added parameters. You need to modify that contain the data of the config files and accordingly. Prepare the training data see render_codes/README. If you have troubles to connect to huggingface. Make sure you have downloaded the following models. Download the checkpoints and into the root folder. If you are in mainland China, you may download via aliyun. /configs/mvdiffusion-joint-ortho-6views. Predict foreground mask as the

alpha channel. We use Clipdrop to segment the foreground object interactively. You may also use to remove the backgrounds. Run