End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: creativeml-openrail-m
+library_name: diffusers
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+base_model: stabilityai/stable-diffusion-2-1-base
+inference: true
+---
+
+<!-- This model card has been generated automatically according to the information the training script had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+
+# controlnet-moritzef/model_lr1e4
+
+These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning.
+You can find some example images below.
+
+prompt: A realistic google streetview image taken in Berlin (Germany), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_0)](./images_0.png)
+prompt: A realistic google streetview image taken in New York (USA), that looks normal and has a beauty-score of 27, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_1)](./images_1.png)
+prompt: A realistic google streetview image taken in Rome (Italy), that looks normal and has a beauty-score of 23, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_2)](./images_2.png)
+prompt: A realistic google streetview image taken in Mexico City (Mexico), that looks very ugly and has a beauty-score of 18, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_3)](./images_3.png)
+prompt: A realistic google streetview image taken in Tel Aviv (Israel), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_4)](./images_4.png)
+prompt: A realistic google streetview image taken in Kyoto (Japan), that looks very ugly and has a beauty-score of 16, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_5)](./images_5.png)
+prompt: A realistic google streetview image taken in Gaborone (Botswana), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_6)](./images_6.png)
+prompt: A realistic google streetview image taken in Melbourne (Australia), that looks normal and has a beauty-score of 28, where scores are between 10 and 40 and higher scores indicate more beauty.
+![images_7)](./images_7.png)
+
+
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+# TODO: add an example code snippet for running this diffusion pipeline
+```
+
+#### Limitations and bias
+
+[TODO: provide examples of latent issues and potential remediations]
+
+## Training details
+
+[TODO: describe the data used to train the model]

checkpoint-100000/controlnet/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

checkpoint-100000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c49e7fae99c39280b6e66695868470bba81794aa096118310a233e6c06267f
+size 1456953560

checkpoint-100000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1bbd2e414e51ed45ff29716247c6abbe1a7c475e6066da285c4d46ef06d56a
+size 2914111182

checkpoint-100000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a25e10b472d9b197f5f1c83d53a132ddf247b71c55eb71adf3f7b590771654a
+size 14408

checkpoint-100000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b35b67e2e1b2d26fc187ae57fff5b681d4784f24f7821ee9f2eb1e824cca739
+size 1000

config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1e19a206f40b021ddae15a7e30068ce96634e520c232f2f3481bb45ce984b5
+size 1456953560