End of training

README.md

@@ -0,0 +1,39 @@
+
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+inference: true
+---
+    
+# controlnet-SargeZT/controlnet-sd-xl-1.0-depth-16bit-zoe
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
+You can find some example images below.
+prompt: a black and white cat laying on top of a keyboard
+![images_0)](./images_0.png)
+prompt: a wooden bench sitting in the middle of a forest
+![images_1)](./images_1.png)
+prompt: a ripe banana sitting on top of a wooden table
+![images_2)](./images_2.png)
+prompt: a large jetliner sitting on top of an airport tarmac
+![images_3)](./images_3.png)
+prompt: two girls are playing soccer on a field
+![images_4)](./images_4.png)
+prompt: a laptop computer sitting on top of a desk
+![images_5)](./images_5.png)
+prompt: a man riding skis on top of a body of water
+![images_6)](./images_6.png)
+prompt: a small plane is flying through the air
+![images_7)](./images_7.png)
+
+
+
+## License
+
+[SDXL 1.0 License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)

checkpoint-3000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad657580563cd47a6d01fad4dbbbd94718abfc2147c2401659726e0fe215e91
+size 20017245213

checkpoint-3000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10a64b8ec4ab1ee81407f331b71f59e737c3472e62148fa3f3491eda1460d58
+size 14727

checkpoint-3000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1f9398b77268202e8e1465734a63d123b1ef11c27f20f2473677e9883a6869
+size 557

checkpoint-3000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5239ab2381305ae3898ff682944f2f2d00b994d0812b456736063d20ca7a10
+size 563

checkpoint-4000/controlnet/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.19.3",
+  "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
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-4000/controlnet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2594d899512bd4c7f815cdb406489aa361027d3c36951a3d6ac31ed1b6e54c96
+size 5004438321

checkpoint-4000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af91808b8221f30880be6ed96f5dba336ec210d224bb255f6c70d3f5124963f5
+size 20017245213

checkpoint-4000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d927d8aa94b6725fc2a7b48150b6b54a375bb9cd96f83ab1b5298628de9ed43
+size 14727

checkpoint-4000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a61ecdaa4a69ba865e0b9e19169660549c34c60a83537ab5ece413678520ab
+size 557

checkpoint-4000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105d6580de739d529fa465e32f1833e2248ffd7e0f899527364081ef0bdb1475
+size 563

checkpoint-5000/controlnet/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.19.3",
+  "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
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-5000/controlnet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b5555c93a67a621d021a8fbd5ca1e1b2078d1c20a45f2d786cb59ece16da74
+size 5004438321

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26854861fa554476886918017e6ce2d50ec50b0fe928a9cd6cfb1e4e7d33dee5
+size 20017245213

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09f3525a2133cee4c46a75b89306446311c2b3db230b63acabcbe77696baf7c
+size 14727

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41313b6733b65c1acca917a7c2ced06503c11b898e6cd5de1e6a9f13bfb54ef
+size 557

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36607a976be36244ad46bcfa4be6fb5bea011d713149f3a57643bfc07960ced
+size 563

config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.19.3",
+  "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
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7045e46da30684d8df4b08490d02f81881be146fe9d175559e393800a0353e61
+size 5004438321