MIDI 3D
MIDI is a 3D generative model for single image to compositional 3D scene generation. It was introduced in the paper MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation.
Model source
- Kind
- Other
- File size
- 463 MB–3.13 GB
- Version
- vRevision 3b98498
- Updated
- Nov 4, 2026
- Downloads
- 5
- Source
- Hugging Face
Source description
MIDI-3D
MIDI is a 3D generative model for single image to compositional 3D scene generation. It was introduced in the paper MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation.
Project page: https://huanngzh.github.io/MIDI-Page/
Sources
1 source
Sources
1 sourceVerified Nov 4
Download files
Repository files
File inventory only; completeness is unverified.
- feature_extractor_1/preprocessor_config.json
- feature_extractor_2/preprocessor_config.json
- image_encoder_1/config.json
- image_encoder_1/model.safetensors
- image_encoder_2/config.json
- image_encoder_2/model.safetensors
- model_index.json
- scheduler/scheduler_config.json
- transformer/config.json
- transformer/diffusion_pytorch_model.safetensors
- vae/config.json
- vae/diffusion_pytorch_model.safetensors
Model artifacts
4 artifacts
Model artifacts
4 artifactsimage_encoder_1/model.safetensors
safetensors · BF16 (tensor header) · 580 MB · SHA-256 e4b33d864f89…8da8 · Hugging Face
Download fileimage_encoder_2/model.safetensors
safetensors · BF16 (tensor header) · 582 MB · SHA-256 a354885ca460…65ba · Hugging Face
Download filetransformer/diffusion_pytorch_model.safetensors
safetensors · BF16 (tensor header) · 3.13 GB · SHA-256 92c7177fa8f3…3b1b · Hugging Face
Download filevae/diffusion_pytorch_model.safetensors
safetensors · BF16 (tensor header) · 463 MB · SHA-256 826352fb8e5d…e56d · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: apache-2.0 pipeline_tag: image-to-3d --- # MIDI-3D <!-- Provide a quick summary of what the model is/does. --> MIDI is a 3D generative model for single image to compositional 3D scene generation. It was introduced in the paper [MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation](https://huggingface.co/papers/2412.03558). Project page: https://huanngzh.github.io/MIDI-Page/ Code: https://github.com/VAST-AI-Research/MIDI-3D
Source context: 5 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo ameerazam08/MIDI-3D
Source context: 1 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo ameerazam08/MIDI-3D
