DL3DV/DL3DV-ALL-2K
Updated β’ 26k β’ 4
How to use cyrildiagne/flux2-klein9b-lora-mlsharp-3d-repair with Sharp:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
A LoRA for klein 9b base that can repair 3D views from ml-sharp, fixing geometry issues and restoring original details.
The prompt is expected to be:
"Referring to the scene in image 1, restore the perspective of the scene in image 2. Repair the perspective and missing areas. The camera has moved by: {"x":0,"y":0,"z":0,"pitch":0,"yaw":0,"roll":0}"
With the coordinates updated to be the actual relative camera transform.
Trained on ~5k scenes from DL3DV-10K.
Inference and demo code coming soon.
This LoRA is released under CC BY-NC 4.0 to comply with the non-commercial license of the training data (DL3DV-10K).
Base model
black-forest-labs/FLUX.2-klein-base-9B