GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Yw22
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Yw22
Model Tree
black-forest-labs/FLUX.1-Kontext-dev
Input Modalities
Output Modalities
Supported Functionality
| File | Size (bytes) | Component |
|---|---|---|
lora_dit.safetensors | 1,388,016,360 | Diffusion transformer LoRA weights |
view_moe_double.safetensors | 89,694,626 | View-conditioning module for double-stream blocks |
view_moe_single.safetensors | 89,694,626 | View-conditioning module for single-stream blocks |
All three files are required. The FLUX base model and VGGT weights must be downloaded separately. These files require the ViewWeaver custom loader and do not form a standalone Diffusers pipeline.
Run from the ViewWeaver code directory. First obtain access to FLUX.1-Kontext-dev and accept its terms on its model page.
bash
hf auth loginhf download Yw22/ViewWeaver --local-dir checkpoints/viewweaverhf download facebook/VGGT-1B --local-dir checkpoints/vggthf download black-forest-labs/FLUX.1-Kontext-dev --local-dir checkpoints/flux-kontextExpected layout:
text
checkpoints/├── viewweaver/│ ├── lora_dit.safetensors│ ├── view_moe_double.safetensors│ └── view_moe_single.safetensors├── vggt/│ └── model.safetensors└── flux-kontext/ ├── model_index.json ├── transformer/ ├── vae/ ├── text_encoder/ ├── text_encoder_2/ ├── tokenizer/ ├── tokenizer_2/ └── scheduler/Use a CUDA GPU with bfloat16 support. The following installation commands match the ViewWeaver project instructions for CUDA 12.8; choose an appropriate PyTorch build for other CUDA versions.
bash
conda create -n viewweaver python=3.12 -yconda activate viewweaverpython -m pip install torch==2.8.0 torchvision==0.23.0 \ --index-url https://download.pytorch.org/whl/cu128 cd /path/to/ViewWeaverpython -m pip install -e '.[prepare]' \ 'numpy==1.26.4' 'opencv-python==4.11.0.86'export PYTHON="$(command -v python)"After downloading the checkpoints, run the included Mario example from the code directory:
bash
CUDA_VISIBLE_DEVICES=0 bash scripts/run_case.sh --case examples/mario \ --reference-view 0 --azimuth -15 --elevation 15 \ --camera-distance 4.5 --offset-y 0.18 --save-comparisonThe default workflow uses eight reference images with foreground masks, performs VGGT geometry preparation, and generates one target view. Generation defaults are 1024 × 1024 pixels, 32 steps, and guidance scale 3.5. Outputs are written to outputs/<case>/<timestamp>/, including the generated image, reference–target comparison, and result.json.
For your own inputs, provide a case directory with case.json, eight reference images, and matching foreground masks (white foreground, black background). RGBA images can supply foreground masks through their alpha channel. The ViewWeaver code documentation describes the full case format, reusable preparation caches, and camera controls.
This repository retains its MIT license metadata. FLUX.1-Kontext-dev, VGGT, and any example assets remain subject to their respective licenses and terms; the repository metadata does not replace those terms.
bibtex
@inproceedings{li2026viewweaver, title={ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization}, author={Li, Yaowei and Li, Xiaoyu and Zhang, Zhaoyang and Li, Hongxiang and Chen, Long and Shan, Ying and Zou, Yuexian}, booktitle={Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers}, pages={1--12}, year={2026}}hf auth loginhf download Yw22/ViewWeaver --local-dir checkpoints/viewweaverhf download facebook/VGGT-1B --local-dir checkpoints/vggthf download black-forest-labs/FLUX.1-Kontext-dev --local-dir checkpoints/flux-kontextcheckpoints/├── viewweaver/│ ├── lora_dit.safetensors│ ├── view_moe_double.safetensors│ └── view_moe_single.safetensors├── vggt/│ └── model.safetensors└── flux-kontext/ ├── model_index.json ├── transformer/ ├── vae/ ├── text_encoder/ ├── text_encoder_2/ ├── tokenizer/ ├── tokenizer_2/ └── scheduler/conda create -n viewweaver python=3.12 -yconda activate viewweaverpython -m pip install torch==2.8.0 torchvision==0.23.0 \ --index-url https://download.pytorch.org/whl/cu128 cd /path/to/ViewWeaverpython -m pip install -e '.[prepare]' \ 'numpy==1.26.4' 'opencv-python==4.11.0.86'export PYTHON="$(command -v python)"CUDA_VISIBLE_DEVICES=0 bash scripts/run_case.sh --case examples/mario \ --reference-view 0 --azimuth -15 --elevation 15 \ --camera-distance 4.5 --offset-y 0.18 --save-comparison@inproceedings{li2026viewweaver, title={ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization}, author={Li, Yaowei and Li, Xiaoyu and Zhang, Zhaoyang and Li, Hongxiang and Chen, Long and Shan, Ying and Zou, Yuexian}, booktitle={Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers}, pages={1--12}, year={2026}}