Add files using upload-large-folder tool

README.md

@@ -0,0 +1,71 @@
+---
+license: cc-by-nc-sa-4.0
+library_name: diffusers
+pipeline_tag: text-to-image
+base_model: lcybuaa/Text2Earth
+tags:
+  - controlnet
+  - remote-sensing
+  - xbd
+  - building-damage
+---
+
+# Text2Earth ControlNet for xBD
+
+ControlNet fine-tuned on [xBD](https://xview2.org/download) post-event imagery. It takes a building-damage mask and samples a matching satellite image from [Text2Earth](https://huggingface.co/lcybuaa/Text2Earth).
+
+The ControlNet is the only trained module. Text2Earth (UNet, VAE, text encoder) stays frozen.
+
+## Conditioning
+
+| Item | Value |
+| --- | --- |
+| Base model | [lcybuaa/Text2Earth](https://huggingface.co/lcybuaa/Text2Earth) |
+| Conditioning | 3-channel binary damage mask, RGB order, values in `{0, 1}` |
+| Prompt | `18_GOOGLE_LEVEL_a high resolution satellite image` |
+| Scheduler | Euler discrete |
+| Steps / guidance | 50 / 1.0 |
+
+Binary channels follow the xBD hues: background black, no-damage green, minor blue, major yellow, destroy red, un-classified white.
+
+## Usage
+
+```python
+import torch
+from diffusers import (
+    ControlNetModel,
+    EulerDiscreteScheduler,
+    StableDiffusionControlNetPipeline,
+)
+from PIL import Image
+
+repo = "BiliSakura/Text2Earth-ControlNet-xBD"
+base = "lcybuaa/Text2Earth"
+dtype = torch.float16
+
+controlnet = ControlNetModel.from_pretrained(
+    repo, subfolder="controlnet", torch_dtype=dtype
+)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    base,
+    controlnet=controlnet,
+    scheduler=EulerDiscreteScheduler.from_pretrained(base, subfolder="scheduler"),
+    torch_dtype=dtype,
+    safety_checker=None,
+).to("cuda")
+
+image = pipe(
+    "18_GOOGLE_LEVEL_a high resolution satellite image",
+    image=Image.open("mask.png"),
+    num_inference_steps=50,
+    guidance_scale=1.0,
+    controlnet_conditioning_scale=1.0,
+).images[0]
+image.save("post_event.png")
+```
+
+Weights are under `controlnet/`.
+
+## License
+
+[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/), the license of the xBD dataset these weights were trained on.

controlnet/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.36.0",
+  "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": "timestep",
+  "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
+}

controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b83e5bbba46432b2aec5c2f9f8cf7d9f7d294159eabf20b711de8509a4bb52
+size 1465156288