Add files using upload-large-folder tool

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+---
+# ControlEarth
+
+ControlNet model conditioned on OpenStreetMaps (OSM) to generate the corresponding satellite images.
+
+Trained on the region of the Central Belt.
+
+## Repo structure
+
+This repo is self-contained and includes:
+
+- **controlnet/** — ControlNet weights (OSM → satellite)
+- **text_encoder/**, **unet/**, **vae/**, **scheduler/**, **tokenizer/** — Stable Diffusion v1-5 base
+- **demo_images/** — Placeholder for input OSM images
+- **inference_demo.py** — Full diffusers inference script (uses only this repo, no external downloads)
+
+## Dataset used for training
+
+The dataset used for the training procedure is the
+[WorldImagery Clarity dataset](https://www.arcgis.com/home/item.html?id=ab399b847323487dba26809bf11ea91a).
+
+The code for the dataset construction can be accessed in https://github.com/miquel-espinosa/map-sat.
+
+## Usage
+
+```bash
+# From the repo root
+python inference_demo.py
+```
+
+Or load programmatically:
+
+```python
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
+import torch
+
+repo = "/path/to/controlearth"  # or "." when run from repo root
+controlnet = ControlNetModel.from_pretrained(f"{repo}/controlnet", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    repo, controlnet=controlnet, torch_dtype=torch.float16,
+    safety_checker=None, requires_safety_checker=False
+)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+pipe.enable_model_cpu_offload()
+
+image = pipe("convert this openstreetmap into its satellite view", num_inference_steps=50, image=control_image).images[0]
+```
+
+![examples image](https://raw.githubusercontent.com/tostyfrosty/map-sat/main/imgs/examples.png)

controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "/root/worksapce/models/mespinosami/controlearth",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "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": false
+}

controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bb55bcbb4dc2e279a0b0c61051e992769acb3748874efd389c5da1a41cabda
+size 1445157120

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

inference_demo.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+"""
+Full diffusers-style inference demo for ControlEarth.
+Uses only this repo's checkpoints (base + controlnet), no external downloads.
+"""
+from pathlib import Path
+
+import torch
+from diffusers import (
+    ControlNetModel,
+    StableDiffusionControlNetPipeline,
+    UniPCMultistepScheduler,
+)
+from PIL import Image
+
+
+def main():
+    repo = Path(__file__).resolve().parent
+    controlnet_path = repo / "controlnet"
+    demo_images = repo / "demo_images"
+    out_dir = repo / "outputs"
+    out_dir.mkdir(exist_ok=True)
+
+    print("Loading ControlNet...")
+    controlnet = ControlNetModel.from_pretrained(
+        str(controlnet_path), torch_dtype=torch.float16
+    )
+
+    print("Loading pipeline (base + controlnet)...")
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        str(repo),
+        controlnet=controlnet,
+        torch_dtype=torch.float16,
+        safety_checker=None,
+        requires_safety_checker=False,
+    )
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_model_cpu_offload()
+
+    prompt = "convert this openstreetmap into its satellite view"
+    num_inference_steps = 50
+
+    # Find OSM images in demo_images
+    image_exts = {".png", ".jpg", ".jpeg", ".webp"}
+    image_paths = [
+        p for p in demo_images.iterdir()
+        if p.is_file() and p.suffix.lower() in image_exts
+    ]
+
+    if not image_paths:
+        print(f"No images found in {demo_images}. Creating a placeholder run.")
+        # Create minimal 512x512 RGB placeholder for demo
+        placeholder = Image.new("RGB", (512, 512), color=(200, 200, 200))
+        image_paths = [None]
+        control_images = [placeholder]
+    else:
+        control_images = [
+            Image.open(p).convert("RGB") for p in sorted(image_paths)
+        ]
+
+    for idx, control_image in enumerate(control_images):
+        name = image_paths[idx].stem if image_paths[idx] else "placeholder"
+        print(f"Generating for {name}...")
+        for i in range(3):
+            result = pipe(
+                prompt,
+                num_inference_steps=num_inference_steps,
+                image=control_image,
+            ).images[0]
+            out_path = out_dir / f"{name}-{i}.png"
+            result.save(out_path)
+            print(f"  Saved {out_path}")
+
+    print(f"Done. Outputs in {out_dir}")
+
+
+if __name__ == "__main__":
+    main()

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.6.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.6.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null,
+  "clip_sample": false
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334
+size 492265874

text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05eee911f195625deeab86f0b22b115d7d8bc3adbfc1404f03557f7e4e6a8fd7
+size 246187076

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "openai/clip-vit-large-patch14",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.6.0",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7da0e21ba7ea50637bee26e81c220844defdf01aafca02b2c42ecdadb813de4
+size 3438354725

unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30eb3dc47c90e4a55476332b284b2331774c530edbbb83b70cacdd9e7b91af92
+size 1719327893

unet/diffusion_pytorch_model.non_ema.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3
+size 3438167536

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1
+size 3438167540

vae/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.6.0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
+size 334707217

vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7643b3e40b9f128eda5fe174fea73c3ef3903562651fb344a79439709c2e503
+size 167405651

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c
+size 334643276