Upload 5 files

Model/finetuned_crosswalk_model_v1_150_epoch_9/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "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,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

Model/finetuned_crosswalk_model_v1_150_epoch_9/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de28df08485de192bff5d968ca476d47e03d45244085d99fb57da8e53f7cbc60
+size 3438167536

Model/finetuned_vae_v1_150_epoch_9/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

Model/finetuned_vae_v1_150_epoch_9/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
+size 334643268

generate.py

@@ -0,0 +1,41 @@
+import torch
+from diffusers import StableDiffusionPipeline, UNet2DConditionModel, AutoencoderKL, DDPMScheduler
+from transformers import CLIPTextModel, CLIPImageProcessor, AutoTokenizer
+
+# Load the fine-tuned models
+vae = AutoencoderKL.from_pretrained("./Model/finetuned_vae_v1_150_epoch_9")
+unet = UNet2DConditionModel.from_pretrained("./Model/finetuned_crosswalk_model_v1_150_epoch_9")
+
+scheduler = DDPMScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler")
+
+# Load the CLIP text encoder, tokenizer, and feature extractor
+tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-large-patch14")
+text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")
+feature_extractor = CLIPImageProcessor.from_pretrained("openai/clip-vit-large-patch14")
+
+# Load the fine-tuned Stable Diffusion pipeline
+pipeline = StableDiffusionPipeline(
+    vae=vae,
+    text_encoder=text_encoder,
+    tokenizer=tokenizer,
+    unet=unet,
+    scheduler=scheduler,
+    feature_extractor=feature_extractor,  
+    safety_checker=None,  
+)
+
+# Move the pipeline to GPU (if available)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+print ("Working with: ",device)
+pipeline.to(device)
+
+# Generate an image from a text prompt
+prompt = "a crosswalk image"  # Customize your prompt here
+with torch.amp.autocast('cuda'):
+        image = pipeline(prompt, num_inference_steps=50, guidance_scale=9).images[0]
+
+# Save or show the generated image
+image.resize((640,360)).save("output.png")
+image.resize((640,360)).show()
+
+