Add stage-1 bidirectional teacher checkpoints to the model card

README.md

@@ -8,6 +8,7 @@ library_name: artifixer
  
 ArtiFixer is a few-step causal auto-regressive model that enhances and extends 3D reconstruction. The related source code provides implementations for training, evaluation, and inference, supporting various stages including bidirectional training, diffusion forcing, and Self-Forcing-style DMD distillation.  
 ArtiFixer was developed by NVIDIA (Spatial Intelligence Lab) and is released in two variants: a 14B variant based on Wan2.1's 14B model, and a lighter-weight 1.3B variant based on Wan2.1's 1.3B model that trades some reconstruction quality for significantly higher throughput and lower training and inference compute.  
+In addition to the distilled few-step causal auto-regressive models, this repository also provides the bidirectional diffusion **teacher** checkpoints from which each released model was distilled (`artifixer-s1-14b.pt` and `artifixer-s1-1.3b.pt`, the stage-1 bidirectional training outputs). The teachers use full bidirectional attention with standard multi-step diffusion sampling instead of few-step causal auto-regressive rollout. They are provided for research on distillation, sampling, and long-rollout behavior, and as the starting point for reproducing the diffusion-forcing and DMD distillation stages.  
 _This model is for research and development only._
  
 ### License/Terms of Use:
@@ -25,7 +26,7 @@ Developers and researchers working on 3D reconstruction, diffusion models, and a
  
 ### Release Date:
  
-**Other:** Hugging Face: 06/04/2026 (14B variant) and 07/21/2026 (1.3B variant) via https://research.nvidia.com/labs/sil/projects/artifixer/
+**Other:** Hugging Face: 06/04/2026 (14B variant), 07/21/2026 (1.3B variant), and 09/2026 (bidirectional teacher checkpoints) via https://research.nvidia.com/labs/sil/projects/artifixer/
  
 ## Reference(s):
  
@@ -36,7 +37,7 @@ Developers and researchers working on 3D reconstruction, diffusion models, and a
 **Architecture Type:** Transformer  
 **Network Architecture:** ArtifixerTransformer (built on Wan2.1's WanTransformer3DModel)  
 **This model was developed based on Wan-AI/Wan2.1-T2V-14B-Diffusers (14B variant) and Wan-AI/Wan2.1-T2V-1.3B-Diffusers (1.3B variant).**  
-**Number of model parameters:** 14B variant: ~16.9B trainable (16,910,955,584); 1.3B variant: ~1.68B trainable (1,678,749,760)
+**Number of model parameters:** 14B variant: ~16.9B trainable (16,910,955,584); 1.3B variant: ~1.68B trainable (1,678,749,760). The teacher checkpoints share the architecture and parameter counts of their respective variants.
  
 ## Input:
  
@@ -50,7 +51,7 @@ Developers and researchers working on 3D reconstruction, diffusion models, and a
 **Output Type(s):** Image  
 **Output Format:** RGB (Red, Green, Blue)  
 **Output Parameters:** Two-Dimensional (2D) image frames  
-**Other Properties Related to Output:** Generates enhanced images via a few-step causal auto-regressive diffusion model. At 4 denoising steps on a single GPU, the 14B variant reaches 8.36 FPS and the 1.3B variant 34.38 FPS; with 1 denoising step and 4-GPU context parallelism, the 1.3B variant reaches up to 101.77 FPS.
+**Other Properties Related to Output:** Generates enhanced images via a few-step causal auto-regressive diffusion model. At 4 denoising steps on a single GPU, the 14B variant reaches 8.36 FPS and the 1.3B variant 34.38 FPS; with 1 denoising step and 4-GPU context parallelism, the 1.3B variant reaches up to 101.77 FPS. The bidirectional teacher checkpoints instead run standard multi-step diffusion sampling with full bidirectional attention; the FPS figures above apply to the distilled causal auto-regressive models only.
  
 Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g., GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
  
@@ -64,7 +65,8 @@ The integration of foundation and fine-tuned models into AI systems requires add
  
 ## Model Version(s):
  
-ArtiFixer 14B v1.0, ArtiFixer 1.3B v1.0  
+ArtiFixer 14B v1.0, ArtiFixer 1.3B v1.0, ArtiFixer 14B Teacher v1.0, ArtiFixer 1.3B Teacher v1.0  
+The teacher checkpoints are the stage-1 bidirectional models from which the corresponding released causal auto-regressive models were distilled.  
 ArtiFixer integrates with PyTorch and requires CUDA environments. It uses Dockerfiles for CUDA 12 and 13, supporting both x86_64 and aarch64 architectures. The model can be run using torchrun (or accelerate) with multi-GPU setups and requires dependencies such as flash-attn, accelerate, diffusers, and transformers.
  
 ## Training, Testing, and Evaluation Datasets:
@@ -86,7 +88,7 @@ ArtiFixer integrates with PyTorch and requires CUDA environments. It uses Docker
  
 ### Evaluation Dataset:
  
-All numbers below are measured with the released checkpoints. Artifact removal on the Nerfbusters and DL3DV benchmarks (Difix3D+ protocol; NB = Nerfbusters):
+All numbers below are measured with the released causal auto-regressive checkpoints (`artifixer-14b.pt`, `artifixer-1.3b.pt`). Artifact removal on the Nerfbusters and DL3DV benchmarks (Difix3D+ protocol; NB = Nerfbusters):
  
 | Method | NB PSNR↑ | NB SSIM↑ | NB LPIPS↓ | NB FID↓ | DL3DV PSNR↑ | DL3DV SSIM↑ | DL3DV LPIPS↓ | DL3DV FID↓ |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |

config.json

@@ -12,6 +12,14 @@
     "artifixer-1.3b": {
       "weight_file": "artifixer-1.3b.pt",
       "base_model": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
+    },
+    "artifixer-s1-14b": {
+      "weight_file": "artifixer-s1-14b.pt",
+      "base_model": "Wan-AI/Wan2.1-T2V-14B-Diffusers"
+    },
+    "artifixer-s1-1.3b": {
+      "weight_file": "artifixer-s1-1.3b.pt",
+      "base_model": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
     }
   },
   "intended_use": "3D reconstruction enhancement and extension",