Update README.md

Add an custom content

README.md

@@ -1,32 +1,38 @@
 ---
-emoji: 🎥
-title: 'Self Forcing Wan 2.1 '
-short_description: Real-time video generation
+emoji: 👀
+title: 'RunAsh AI Live Video Streaming  '
+short_description: Real-time video strgeneration
 sdk: gradio
+license: apache-2.0
+colorFrom: red
+colorTo: yellow
+pinned: true
+thumbnail: >-
+  https://cdn-uploads.huggingface.co/production/uploads/6799f4b5a2b48413dd18a8dd/VC40nrxiqjcoyZISss85V.jpeg
 ---
 <p align="center">
-<h1 align="center">Self Forcing</h1>
+<h1 align="center">RunAsh AI Live Video Streaming</h1>
 <h3 align="center">Bridging the Train-Test Gap in Autoregressive Video Diffusion</h3>
 </p>
 <p align="center">
   <p align="center">
-    <a href="https://www.xunhuang.me/">Xun Huang</a><sup>1</sup>
+    <a href="https://.me/">Ram Murmu</a><sup>1</sup>
     ·
-    <a href="https://zhengqili.github.io/">Zhengqi Li</a><sup>1</sup>
+    <a href="https://.github.io/">Vaibhav Murmu</a><sup>1</sup>
     ·
-    <a href="https://guandehe.github.io/">Guande He</a><sup>2</sup>
+    <a href="https://.github.io/"></a><sup></sup>
     ·
-    <a href="https://mingyuanzhou.github.io/">Mingyuan Zhou</a><sup>2</sup>
+    <a href="https://.github.io/"></a><sup></sup>
     ·
-    <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a><sup>1</sup><br>
-    <sup>1</sup>Adobe Research <sup>2</sup>UT Austin
+    <a href="https://research.adobe.com/person/eli-shechtman/"></a><sup>1</sup><br>
+    <sup>1</sup>RunAsh AI Research <sup>2</sup>
   </p>
   <h3 align="center"><a href="https://arxiv.org/abs/2506.08009">Paper</a> | <a href="https://self-forcing.github.io">Website</a> | <a href="https://huggingface.co/gdhe17/Self-Forcing/tree/main">Models (HuggingFace)</a></h3>
 </p>
 
 ---
 
-Self Forcing trains autoregressive video diffusion models by **simulating the inference process during training**, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables **real-time, streaming video generation on a single RTX 4090** while matching the quality of state-of-the-art diffusion models.
+RunAsh AI trains autoregressive video diffusion models by **simulating the inference process during training**, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables **real-time, streaming video generation on a single RTX 4090** while matching the quality of state-of-the-art diffusion models.
 
 ---
 
@@ -45,8 +51,8 @@ Other hardware setup could also work but hasn't been tested.
 ## Installation
 Create a conda environment and install dependencies:
 ```
-conda create -n self_forcing python=3.10 -y
-conda activate self_forcing
+conda create -n runash_ai python=3.10 -y
+conda activate runash_ai
 pip install -r requirements.txt
 pip install flash-attn --no-build-isolation
 python setup.py develop
@@ -56,7 +62,7 @@ python setup.py develop
 ### Download checkpoints
 ```
 huggingface-cli download Wan-AI/Wan2.1-T2V-1.3B --local-dir-use-symlinks False --local-dir wan_models/Wan2.1-T2V-1.3B
-huggingface-cli download gdhe17/Self-Forcing checkpoints/self_forcing_dmd.pt --local-dir .
+huggingface-cli download gdhe17/runash-ai checkpoints/runash_ai_dmd.pt --local-dir .
 ```
 
 ### GUI demo
@@ -72,9 +78,9 @@ Note:
 Example inference script using the chunk-wise autoregressive checkpoint trained with DMD:
 ```
 python inference.py \
-    --config_path configs/self_forcing_dmd.yaml \
-    --output_folder videos/self_forcing_dmd \
-    --checkpoint_path checkpoints/self_forcing_dmd.pt \
+    --config_path configs/runash_ai_dmd.yaml \
+    --output_folder videos/runash_ai_dmd \
+    --checkpoint_path checkpoints/runash_ai_dmd.pt \
     --data_path prompts/MovieGenVideoBench_extended.txt \
     --use_ema
 ```
@@ -83,33 +89,33 @@ Other config files and corresponding checkpoints can be found in [configs](confi
 ## Training
 ### Download text prompts and ODE initialized checkpoint
 ```
-huggingface-cli download gdhe17/Self-Forcing checkpoints/ode_init.pt --local-dir .
-huggingface-cli download gdhe17/Self-Forcing vidprom_filtered_extended.txt --local-dir prompts
+huggingface-cli download gdhe17/runash-ai checkpoints/ode_init.pt --local-dir .
+huggingface-cli download gdhe17/runash-ai vidprom_filtered_extended.txt --local-dir prompts
 ```
-Note: Our training algorithm (except for the GAN version) is data-free (**no video data is needed**). For now, we directly provide the ODE initialization checkpoint and will add more instructions on how to perform ODE initialization in the future (which is identical to the process described in the [CausVid](https://github.com/tianweiy/CausVid) repo).
+Note: Our training algorithm (except for the GAN version) is data-free (**no video data is needed**). For now, we directly provide the ODE initialization checkpoint and will add more instructions on how to perform ODE initialization in the future (which is identical to the process described in the [RunAsh](https://github.com/) repo).
 
-### Self Forcing Training with DMD
+### RunAsh AI Training with DMD
 ```
 torchrun --nnodes=8 --nproc_per_node=8 --rdzv_id=5235 \
   --rdzv_backend=c10d \
   --rdzv_endpoint $MASTER_ADDR \
   train.py \
-  --config_path configs/self_forcing_dmd.yaml \
-  --logdir logs/self_forcing_dmd \
+  --config_path configs/runash_ai_dmd.yaml \
+  --logdir logs/runash_ai_dmd \
   --disable-wandb
 ```
 Our training run uses 600 iterations and completes in under 2 hours using 64 H100 GPUs. By implementing gradient accumulation, it should be possible to reproduce the results in less than 16 hours using 8 H100 GPUs.
 
 ## Acknowledgements
-This codebase is built on top of the open-source implementation of [CausVid](https://github.com/tianweiy/CausVid) by [Tianwei Yin](https://tianweiy.github.io/) and the [Wan2.1](https://github.com/Wan-Video/Wan2.1) repo.
+This codebase is built on top of the open-source implementation of [RunAsh](https://github.com/runash-ai) by [Ram Murmu](https://github.com/rammurmu) and the [Wan2.1](https://github.com/Wan-Video/Wan2.1) repo.
 
 ## Citation
 If you find this codebase useful for your research, please kindly cite our paper:
 ```
-@article{huang2025selfforcing,
-  title={Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion},
-  author={Huang, Xun and Li, Zhengqi and He, Guande and Zhou, Mingyuan and Shechtman, Eli},
-  journal={arXiv preprint arXiv:2506.08009},
+@article{rammurmu 2025 runash ai,
+  title={runash ai: Bridging the Train-Test Gap in Autoregressive Video Diffusion},
+  author={Ram murmu, and Vaibhav Murmu },
+  journal={arXiv preprint arXiv:},
   year={2025}
 }
 ```