End of training

.gitattributes

@@ -33,3 +33,8 @@ 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

README.md

@@ -0,0 +1,53 @@
+---
+base_model: Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers
+library_name: diffusers
+license: other
+inference: true
+tags:
+- sana
+- sana-diffusers
+- text-to-image
+- diffusers
+- control
+- 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. -->
+
+
+# sana-edit-sayakpaul/omnisana-lr_1e-4-wd_0.0001-cd_0.0-scheduler_constant
+
+These are Control weights trained on Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers and [TIGER-Lab/OmniEdit-Filtered-1.2M](https://huggingface.co/datasets/TIGER-Lab/OmniEdit-Filtered-1.2M).
+You can find some example images below.
+
+prompt: Give this the look of a traditional Japanese woodblock print.
+![images_0)](./images_0.png)
+prompt: transform the setting to a winter scene
+![images_1)](./images_1.png)
+prompt: Change it to look like it's in the style of an impasto painting.
+![images_2)](./images_2.png)
+prompt: turn the color of mushroom to gray
+![images_3)](./images_3.png)
+
+
+## License
+
+Please adhere to the licensing terms as described [here](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers/blob/main/LICENSE.txt).
+
+
+## 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]

config.json

@@ -0,0 +1,22 @@
+{
+  "_class_name": "SanaTransformer2DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers",
+  "attention_bias": false,
+  "attention_head_dim": 32,
+  "caption_channels": 2304,
+  "cross_attention_dim": 2240,
+  "cross_attention_head_dim": 112,
+  "dropout": 0.0,
+  "in_channels": 64,
+  "interpolation_scale": null,
+  "mlp_ratio": 2.5,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 70,
+  "num_cross_attention_heads": 20,
+  "num_layers": 20,
+  "out_channels": 32,
+  "patch_size": 1,
+  "sample_size": 32
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7262fcc701d121fa34d42a40d8908afdfbed311ef75c4db0f7b2d374a7c55af
+size 6418183488