Duplicate from ezlee258258/Inversion-DPO

Co-authored-by: Yize Li <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,73 @@
+---
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+library_name: diffusers
+license: apache-2.0
+pipeline_tag: text-to-image
+tags:
+- stable-diffusion-xl
+- stable-diffusion
+- diffusers
+- inversion
+- dpo
+- fine-tuned
+---
+
+# Inversion-DPO
+
+Official Inversion-DPO weights fine-tuned from Stable Diffusion XL. Only the trained UNet module is provided.
+
+**Paper**: [Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models](https://huggingface.co/papers/2507.11554)
+
+**Code Repository**: https://github.com/MIGHTYEZ/Inversion-DPO
+
+## Model Description
+
+This repository contains the fine-tuned UNet weights from the Inversion-DPO method, built upon Stable Diffusion XL. The model has been trained using Direct Preference Optimization (DPO) techniques combined with inversion methods to improve generation quality and alignment.
+
+## Quick Start
+
+```python
+from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel
+import torch
+
+# Load the fine-tuned UNet
+unet = UNet2DConditionModel.from_pretrained(
+    "ezlee258258/Inversion-DPO",
+    subfolder="unet"
+)
+
+# Load the pipeline with the fine-tuned UNet
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    unet=unet
+)
+pipe = pipe.to("cuda")
+
+# Generate images
+prompt = "A beautiful landscape with mountains and lakes"
+image = pipe(prompt).images[0]
+image.save("output.png")
+```
+
+## Citation
+
+If you use this model in your research, please cite our work:
+
+```bibtex
+@misc{li2025inversiondpo,
+    title={Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models},
+    author={Zejian Li and Yize Li and Chenye Meng and Zhongni Liu and Yang Ling and Shengyuan Zhang and Guang Yang and Changyuan Yang and Zhiyuan Yang and Lingyun Sun},
+    year={2025},
+    eprint={2507.11554},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+## Acknowledgments
+
+Built upon [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) by Stability AI.
+
+## Contact
+
+For questions and support, please visit our [GitHub repository](https://github.com/MIGHTYEZ/Inversion-DPO).

unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.30.0",
+  "_name_or_path": "comin/IterComp",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950210e4fc3472952f4623d0f0e094f6042894580aa34fef397935e67eb6e167
+size 9988139160

unet/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782ab256cbfcb2541a6b7b96129bdbc5e1455dad18af32fe03568301e2084f03
+size 281938304