Upload 2 files

README.md

@@ -0,0 +1,70 @@
+---
+license: creativeml-openrail-m
+datasets:
+- ioclab/grayscale_image_aesthetic_3M
+language:
+- en
+---
+
+# Model Card for ioclab/ioc-controlnet
+
+This model brings brightness control to Stable Diffusion, allowing users to colorize grayscale images or recolor generated images.
+
+## Model Details
+
+- **Developed by:** [@shichen](https://github.com/chenbaiyujason)
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** Stable Diffusion ControlNet model for [web UI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
+- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
+
+
+## Uses
+
+Recommendation Weight: **0.4-0.9**
+
+Recommendation Exit Timing: **0.4-0.9**
+
+As more datasets are still being trained in this model, it is expected to take 2-4 days. Therefore, flexible weight adjustments should be made based on different scenarios and specific results. If you have generated good images or encountered any problems, you can discuss them on Hugging Face~~~
+
+![1](./image/s33.png)
+
+![1](./image/s9.jpg)
+
+![1](./image/s10.jpg)
+
+![1](./image/s11.jpg)
+
+![1](./image/s34.png)
+
+
+![1](./image/s26.jpg)
+
+
+For more information, please refer to the document link at the bottom.
+
+Please note that the model is still under training iteration!! Please come back every 3 days to check if the latest modified version has been released.
+
+
+
+### HuggingFace Space Demo
+
+Waiting for upload
+
+<!-- [huggingface.co/spaces/ioclab/brightness-controlnet](https://huggingface.co/spaces/ioclab/brightness-controlnet) -->
+
+### Direct Use
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+[More Information Needed]
+
+
+## More Info
+
+[illumination ControlNet 使用教程](https://aigc.ioclab.com/sd-showcase/light_controlnet.html) (Chinese)

config.json

@@ -1,6 +1,8 @@
 {
-  "_class_name": "FlaxControlNetModel",
+  "_class_name": "ControlNetModel",
   "_diffusers_version": "0.16.0.dev0",
+  "_name_or_path": "./controlnet_flax",
+  "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -8,6 +10,7 @@
     1280,
     1280
   ],
+  "class_embed_type": null,
   "conditioning_embedding_out_channels": [
     16,
     32,
@@ -22,12 +25,21 @@
     "CrossAttnDownBlock2D",
     "DownBlock2D"
   ],
+  "downsample_padding": 1,
   "dropout": 0.0,
   "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_class_embeds": null,
   "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
   "sample_size": 32,
+  "upcast_attention": false,
   "use_linear_projection": false
 }