first commit

README.md

@@ -1,3 +1,14 @@
 ---
 license: mit
 ---
+
+This is a controlnet for [Waifu Diffusion 1.5 beta 2](https://huggingface.co/waifu-diffusion/wd-1-5-beta2) which aims to guide image generation by conditioning outputs with images from a common category of the training target examples. The current checkpoint has been trained for approx. 100k steps on a filtered subset of (Danbooru 2021)[https://gwern.net/danbooru2021] using artists as the conditioned category with the aim of learning robust style transfer from an image example.
+
+Major limitations:
+
+ - The current checkpoint was trained on 768x768 crops without aspect ratio checkpointing. Loss in coherence for non-square aspect ratios can be expected.
+ - The training dataset is extremely noisy and used without filtering stylistic outliers from within each category, so performance may be less than ideal.
+ - The Waifu Diffusion base model is a hybrid anime/photography model, and can unpredictably jump between those modalities.
+ - As styling is incredibly sensitive to divergences in model checkpoints, the capabilities of this controlnet are not expected to predictably apply to other SD 2.X checkpoints.
+
+Waifu Diffusion 1.5 beta 2 is licensed under (Fair AI Public License 1.0-SD)[https://freedevproject.org/faipl-1.0-sd/]. This controlnet imposes no restrictions beyond the MIT license, but it cannot be used independently of a base model.

config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "FlaxControlNetModel",
+  "_diffusers_version": "0.16.0.dev0",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "only_cross_attention": false,
+  "sample_size": 32,
+  "use_linear_projection": true
+}

diffusion_flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339b3dd18e3c5a477089d057e2263eeca6e121a4cd08531e34c7ac79f8cabc68
+size 1456925250