added model

README.md

@@ -1,3 +1,32 @@
 ---
 license: creativeml-openrail-m
 ---
+# Stable Control Representations: Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
+
+[Paper Link](https://arxiv.org/abs/2405.05852)
+
+This model repo provides the Stable Diffusion model finetuned on the images from the Something-Something-v2, Epic Kitchen and the Bridge V2 datasets. This repo is related to the [stable-control-representations](https://github.com/ykarmesh/stable-control-representations/) GitHub repo. 
+
+## Abstract
+
+Vision- and language-guided embodied AI requires a fine-grained understanding of the physical world through language and visual inputs. Such capabilities are difficult to learn solely from task-specific data, which has led to the emergence of pre-trained vision-language models as a tool for transferring representations learned from internet-scale data to downstream tasks and new domains. However, commonly used contrastively trained representations such as in CLIP have been shown to fail at enabling embodied agents to gain a sufficiently fine-grained scene understanding—a capability vital for control. To address this shortcoming, we consider representations from pre-trained text-to-image diffusion models, which are explicitly optimized to generate images from text prompts and as such, contain text-conditioned representations that reflect highly fine-grained visuo-spatial information. Using pre-trained text-to-image diffusion models, we construct Stable Control Representations which allow learning downstream control policies that generalize to complex, open-ended environments. We show that policies learned using Stable Control Representations are competitive with state-of-the-art representation learning approaches across a broad range of simulated control settings, encompassing challenging manipulation and navigation tasks. Most notably, we show that Stable Control Representations enable learning policies that exhibit state-of-the-art performance on OVMM, a difficult open-vocabulary navigation benchmark
+
+
+## Citing SCR
+If you use SCR in your research, please cite [the following paper](https://arxiv.org/abs/2405.05852):
+
+```bibtex
+@inproceedings{gupta2024scr,
+      title={Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control},
+      author={Gunshi Gupta and Karmesh Yadav and Yarin Gal and Dhruv Batra and Zsolt Kira and Cong Lu and Tim G. J. Rudner},
+      year={2024},
+      eprint={2405.05852},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
+
+## Acknowledgements
+We are thankful to the creators of [Stable Diffusion](https://huggingface.co/runwayml/stable-diffusion-v1-5) for releasing the model, which has significantly contributed to the progress in the field. Additionally, we extend our thanks to the authors of [Visual Cortex](https://github.com/facebookresearch/eai-vc) for releasing the code for CortexBench evaluations.
+
+

unet_ema/config.json

@@ -0,0 +1,74 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 5000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad60f4867e946aa11722c4e60c932533773acd72e353584c4280040470220519
+size 3438167536