Add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+unet/*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,49 @@
 ---
 license: apache-2.0
+datasets:
+- yuvalkirstain/pickapic_v2
+language:
+- en
+pipeline_tag: text-to-image
 ---
+Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation (https://huggingface.co/papers/2402.10210)
+
+# SPIN-Diffusion-iter1
+
+This model is a self-play fine-tuned diffusion model at iteration 2 from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) using synthetic data based on on the [yuvalkirstain/pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2) dataset.
+
+## Model Details
+
+### Model Description
+
+- Model type: An diffusion model with unet fine-tuned, based on the strucure of stable diffusion 1.5
+- Language(s) (NLP): Primarily English
+- License: Apache-2.0
+- Finetuned from model: runwayml/stable-diffusion-v1-5
+
+### Training hyperparameters
+The following hyperparameters were used during training:
+
+- learning_rate: 2.0e-05
+- train_batch_size: 8
+- distributed_type: multi-GPU
+- num_devices: 8
+- train_gradient_accumulation_steps: 32
+- total_train_batch_size: 2048
+- optimizer: AdamW
+- lr_scheduler: "linear"
+- lr_warmup_steps: 200
+- num_training_steps: 500
+
+  
+## Citation
+```
+@misc{yuan2024self,
+      title={Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation}, 
+      author={Yuan, Huizhuo and Chen, Zixiang and Ji, Kaixuan and Gu, Quanquan},
+      year={2024},
+      eprint={2402.10210},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "",
+  "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,
+  "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,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "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,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28320ac0c93dc9bdc7fd2a67130e54b9c9cb8e1a678957db2a32d0d2533eea66
+size 3438167536