End of training

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* 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
+image_control.png filter=lfs diff=lfs merge=lfs -text
+images_0.png filter=lfs diff=lfs merge=lfs -text
+images_1.png filter=lfs diff=lfs merge=lfs -text
+images_2.png filter=lfs diff=lfs merge=lfs -text
+images_3.png filter=lfs diff=lfs merge=lfs -text
+images_4.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+library_name: diffusers
+license: openrail++
+inference: true
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+---
+
+<!-- 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-Nawatix/out_multihmr_all
+
+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 woman on a trapeze in the air
+![images_0)](./images_0.png)
+prompt: a woman in red hair and white dress sitting on fire
+![images_1)](./images_1.png)
+prompt: two dancers in white dress and black shoes on stage
+![images_2)](./images_2.png)
+prompt: two men in period clothing stand in front of a table
+![images_3)](./images_3.png)
+prompt: two men are walking down a hallway in a building
+![images_4)](./images_4.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-20000/controlnet/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "/home/schoenherr/diffusers/out_multihmr_all/checkpoint-12500",
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-20000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f4680531fd4f87bf353afed242207d41dcdf863beba17a83efc8411e5782a7
+size 5004167864

checkpoint-20000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962a4c80b61b5f81f6c6cf9548e4affc8de6eed02a31461343eca66b5279ac1f
+size 10008850679

checkpoint-20000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba7f5878b8f6891b05369ccc0bdb99c6a91b0f7503f55eabd614359cb1cdaca
+size 15537

checkpoint-20000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e788c44108c3e2ecbd42824c7166be65aeb1ad73d9b2da7edc1551b68698921
+size 1383

checkpoint-20000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ed641449df44a5f9874edb41ad438ffd85bf6b26dba302eca4c7f8cdb25957
+size 1401

config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "/home/schoenherr/diffusers/out_multihmr_all/checkpoint-12500",
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f4680531fd4f87bf353afed242207d41dcdf863beba17a83efc8411e5782a7
+size 5004167864