weights and unet_merged

README.md

@@ -1,3 +1,41 @@
 ---
 license: cc-by-nc-nd-4.0
+language:
+- en
+pipeline_tag: text-to-video
+tags:
+- video generation
+- image generation
 ---
+# Generative Photography
+
+
+<p align="center">
+ &nbsp&nbsp <a href="https://generative-photography.github.io/project/">Project Page</a> &nbsp&nbsp| &nbsp&nbsp <a href="https://arxiv.org/abs/2412.02168">Paper</a> &nbsp&nbsp| &nbsp&nbsp <a href="https://github.com/pandayuanyu/generative-photography">Github</a>&nbsp&nbsp 
+<br>
+-----
+
+[**Generative Photography: Scene-Consistent Camera Control for
+Realistic Text-to-Image Synthesis**]("") <be>
+
+In this repository, we present **Generative Photography**, a 
+new 
+
+## 🔥 Latest News!!
+
+* March 3, 2025: Release offical code and pre-trained weights.
+* Feb 26, 2025: Paper is accepted by CVPR 2025!
+* Dec 20, 2024: Release dataset.
+
+
+## Citation
+If you find our work helpful, please cite us.
+```bibtex
+@article{Yuan_2024_GenPhoto,
+  title={Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis},
+  author={Yuan, Yu and Wang, Xijun and Sheng, Yichen and Chennuri, Prateek and Zhang, Xingguang and Chan, Stanley},
+  journal={CVPR},
+  year={2025}
+}
+```
+

unet_merged/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.6.0",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet_merged/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271d13f0e7799e4fc96b45c91fa7c54fdd67b99ff53bf30b7dbc9ef1c9eac279
+size 3438167504

weights/RealEstate10K_LoRA.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798b894092f96d2d141a4932546eeb19cc60955ba69456921649e6efe34e2554
+size 1156140341

weights/checkpoint-bokehK.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf405f1c9799557e9b4ecc2b80b53cde56055ed78c0e27c55c341c74c5d375a
+size 2619385373

weights/checkpoint-color_temperature.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82f87d79dbd7236abdd8a9aa7cd25e47044739f899846b183a13fa10dd41501
+size 2619385373

weights/checkpoint-focal_length.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f756e0dcdaeefc869bf39ffdb1b73ec5523b800437185f0a310fa68182c35e1
+size 2619385373

weights/checkpoint-shutter_speed.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fad5584cfd1595d6196125b90861ab2d2ee0db962df38a88344be8282fdb11a
+size 2619385373

weights/v3_sd15_mm.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2412711886f61091846f53204aabc38aa6e09356d62a9808abe4daa802168343
+size 1673262583