Keep Cosmos checkpoint usage concise in the model card

Retain the S1/S3 checkpoint table and metadata/memory notes; link to the full inference and training guides. Evaluation results, licenses and all other model-card sections are unchanged.

README.md

@@ -149,85 +149,21 @@ Additional results — Tanks & Temples and multi-view consistency (supplement)
 **Acceleration Engine:** FlashAttention (FA3/FA4); PyTorch SDPA (cuDNN) fallback on Ampere  
 **Test Hardware:** NVIDIA A100 80GB, NVIDIA H100, NVIDIA GB200 (Blackwell)
  
-## Cosmos3-Nano checkpoints and usage
+### Cosmos3-Nano checkpoints
 
 | Checkpoint | Training stage | Sampling |
 | --- | --- | --- |
 | [`artifixer-s1-cosmos3-nano.pt`](./artifixer-s1-cosmos3-nano.pt) | S1 bidirectional teacher, step 25,000 | Bidirectional, 50 steps, text guidance 5 |
 | [`artifixer-cosmos3-nano.pt`](./artifixer-cosmos3-nano.pt) | S3 DMD, EMA step 700 | Causal KV cache, 4 steps; block/window/sink = 7/21/7 latent frames |
 
-S1 is the teacher used to initialize the diffusion-forcing stage preceding S3
-DMD distillation. Both variants are trained on DL3DV-10K (DL3DV-ALL-960P),
-using sparse-view reconstructions, calibrated cameras, and text captions.
-The [training guide](https://github.com/nv-tlabs/ArtiFixer/blob/main/docs/training.md)
-describes the three-stage recipe and the checkpoint handoffs.
+Keep each checkpoint's `.metadata.json` sidecar beside its `.pt` file. Each
+FP32 checkpoint is approximately 63.2 GB; BF16 transformer weights alone need
+31.6 GB, before the VAE, activations, and KV cache.
 
-Each FP32 transformer checkpoint is approximately 63.2 GB (58.9 GiB). BF16
-runtime transformer weights alone occupy 31.6 GB (29.4 GiB), before the VAE,
-activations, and KV cache. Use the matching ArtiFixer source and Docker
-environment from the [repository](https://github.com/nv-tlabs/ArtiFixer), with
-host FFmpeg supplied as described in the
-[setup guide](https://github.com/nv-tlabs/ArtiFixer/blob/main/docs/setup.md).
-
-Download both checkpoints and their required metadata sidecars:
-
-```bash
-export CHECKPOINT_ROOT=/data/artifixer-checkpoints
-hf download nvidia/ArtiFixer \
-    artifixer-cosmos3-nano.pt artifixer-cosmos3-nano.metadata.json \
-    artifixer-s1-cosmos3-nano.pt artifixer-s1-cosmos3-nano.metadata.json \
-    licenses/NOTICE.txt licenses/OpenMDW-1.1.txt \
-    licenses/NVIDIA-OneWay-Noncommercial-License-22Mar2022.pdf \
-    SHA256SUMS --local-dir "$CHECKPOINT_ROOT"
-(cd "$CHECKPOINT_ROOT" && sha256sum --check SHA256SUMS)
-```
-
-Prepare a calibrated COLMAP scene using the repository's input-layout guide.
-Use the actual source FPS (60 in this DL3DV example), a fresh output root,
-and Cosmos token-ID prompts:
-
-```bash
-export COLMAP_SCENE=/data/colmap-scenes/my_scene
-export SCENE_ROOT=/data/artifixer-prep/my_scene-cosmos3
-python -m data_processing.prepare_colmap_artifixer_inputs \
-    --colmap_dir "$COLMAP_SCENE" --output_root "$SCENE_ROOT" \
-    --captioning_model_id Qwen/Qwen3-VL-4B-Instruct \
-    --prompt_format cosmos3_omni_token_ids --dataset_fps 60
-
-python -m model_eval.run_inference \
-    --evalset reconstructed_colmap \
-    --checkpoint "$CHECKPOINT_ROOT/artifixer-cosmos3-nano.pt" \
-    --model_id nvidia/Cosmos3-Nano \
-    --model_revision 23314034b82f46b45339035dba67c3ee9bbcb8ba \
-    --split_path "$SCENE_ROOT/split.json" --render_trajectory all_frames \
-    --save_dir /data/artifixer-corrected --render_name cosmos3-nano-s3 \
-    --inference_pipeline kv_cache --num_inference_steps 4 \
-    --frames_per_block 7 --local_attn_size 21 --sink_size 7 \
-    --camera_pose_alignment last --seed 42
-```
-
-For the S1 teacher, use the same prepared inputs with bidirectional sampling:
-
-```bash
-python -m model_eval.run_inference \
-    --evalset reconstructed_colmap \
-    --checkpoint "$CHECKPOINT_ROOT/artifixer-s1-cosmos3-nano.pt" \
-    --model_id nvidia/Cosmos3-Nano \
-    --model_revision 23314034b82f46b45339035dba67c3ee9bbcb8ba \
-    --split_path "$SCENE_ROOT/split.json" --render_trajectory all_frames \
-    --save_dir /data/artifixer-corrected --render_name cosmos3-nano-s1 \
-    --inference_pipeline bidirectional --num_inference_steps 50 \
-    --text_guidance_scale 5 --bidirectional_chunk_size 81 \
-    --camera_pose_alignment last --seed 42
-```
-
-Keep each metadata sidecar beside its weights. The camera-pose alignment is
-`last`; camera rays use the first target camera as their fixed origin. The model
-profile selects flow shift 5 and RoPE FPS 24; source FPS controls prompt timing.
-Wan T5 embedding files are incompatible with Cosmos token-ID prompts. Use a new
-render name for each setting to avoid reusing completed outputs. Text guidance
-is supported by the S1 bidirectional pipeline; S3 KV-cache sampling does not use
-text CFG.
+See the [Cosmos3-Nano inference guide](https://github.com/nv-tlabs/ArtiFixer/blob/main/docs/inference.md#cosmos3-nano)
+for setup, downloads, and S1/S3 commands, and the
+[training guide](https://github.com/nv-tlabs/ArtiFixer/blob/main/docs/training.md)
+for the three-stage recipe.
 
 ## Ethical Considerations: