Upload README.md with huggingface_hub

README.md

@@ -29,6 +29,8 @@ widget:
 
 # LCM-LoRA SD1.5 - Checkpoint 1600
 
+**Author:** Juhi Singh | [HuggingFace](https://huggingface.co/juhirats)
+
 ## Final Training - Mature
 
 <div align="center">
@@ -60,76 +62,6 @@ This checkpoint represents training at **1600 steps** in our LCM-LoRA progressio
 - 🔧 **Easy Integration**: Drop-in replacement using diffusers
 - 📊 **Proven Quality**: See comparison grid above
 
----
-
-## 📦 All Checkpoints in Series
-
-Click any checkpoint to view its specific characteristics and outputs:
-
-### [Checkpoint 400 - Early Training - Foundation](https://huggingface.co/Mercity/lcm-lora-sd1.5-400)
-
-**Characteristics:** Early training checkpoint showing foundational LCM capabilities. Provides decent quality with room for refinement.
-
-**Best for:** Fast experimentation, understanding early LCM behavior
-
-**Quality:** Good baseline quality, all prompts work correctly
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-400/resolve/main/comparison_grid.png" alt="Checkpoint 400" width="100%">
-</div>
-
-[→ View Full Details for Checkpoint 400](https://huggingface.co/Mercity/lcm-lora-sd1.5-400)
-
----
-
-### [Checkpoint 800 - Mid Training - Vibrant Style](https://huggingface.co/Mercity/lcm-lora-sd1.5-800)
-
-**Characteristics:** Mid-training checkpoint with vibrant, artistic outputs. Strong visual impact with saturated colors and expressive style.
-
-**Best for:** Artistic applications, vibrant aesthetic, expressive style
-
-**Quality:** High visual impact, strong artistic direction, vivid colors
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-800/resolve/main/comparison_grid.png" alt="Checkpoint 800" width="100%">
-</div>
-
-[→ View Full Details for Checkpoint 800](https://huggingface.co/Mercity/lcm-lora-sd1.5-800)
-
----
-
-### [Checkpoint 1200 - High Training - Refined](https://huggingface.co/Mercity/lcm-lora-sd1.5-1200)
-
-**Characteristics:** Higher training with more refined outputs. Some prompts may show signs of overfitting (e.g., occasional missing details).
-
-**Best for:** Balanced colors, natural tones, specific use cases
-
-**Quality:** High technical quality but may miss some prompt details
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1200/resolve/main/comparison_grid.png" alt="Checkpoint 1200" width="100%">
-</div>
-
-[→ View Full Details for Checkpoint 1200](https://huggingface.co/Mercity/lcm-lora-sd1.5-1200)
-
----
-
-### ✨ Checkpoint 1600 - Final Training - Mature (Current)
-
-**Characteristics:** Final training checkpoint with mature, consistent outputs. Well-balanced and reliable across all prompts.
-
-**Best for:** Most training, consistent results, production use
-
-**Quality:** Excellent consistency, balanced outputs, reliable
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/comparison_grid.png" alt="Checkpoint 1600" width="100%">
-</div>
-
----
-
-
-
 ---
 
 ## Checkpoint Comparison
@@ -158,79 +90,25 @@ Compare training progression and characteristics:
 
 ---
 
-## 🧪 Out-of-Distribution (OOD) Validation
+## Visual Comparison Across All Checkpoints
 
-To test generalization beyond the training distribution, we generated images for 5 OOD prompts that are deliberately different from training prompts.
+See how outputs evolve across the training series. Each grid shows: Baseline SD1.5 (50 steps) vs LCM-LoRA at 2, 4, and 6 steps.
 
-**Why OOD Validation?** These prompts test whether the model truly learned general concepts rather than just memorizing training prompts. Good OOD performance indicates robust generalization.
-
-### 🐠 Underwater Scene
+### [Checkpoint 400](https://huggingface.co/Mercity/lcm-lora-sd1.5-400)
 
-**Prompt:** *"underwater coral reef with colorful fish and sea anemones, crystal clear water, natural sunlight filtering through"*
+![Checkpoint 400](https://huggingface.co/Mercity/lcm-lora-sd1.5-400/resolve/main/comparison_grid.png)
 
-**Tests:** Water effects, marine life, underwater lighting (not in training)
+### [Checkpoint 800](https://huggingface.co/Mercity/lcm-lora-sd1.5-800)
 
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/validation/ood_underwater.png" alt="Underwater Scene" width="100%" style="max-width: 512px;">
-  <p><em>Image: ood_underwater.png</em></p>
-</div>
+![Checkpoint 800](https://huggingface.co/Mercity/lcm-lora-sd1.5-800/resolve/main/comparison_grid.png)
 
----
+### [Checkpoint 1200](https://huggingface.co/Mercity/lcm-lora-sd1.5-1200)
 
-### 🚀 Space/Astronomy
+![Checkpoint 1200](https://huggingface.co/Mercity/lcm-lora-sd1.5-1200/resolve/main/comparison_grid.png)
 
-**Prompt:** *"astronaut floating in space with earth in background, stars and galaxies, cinematic lighting, 4k"*
-
-**Tests:** Zero gravity, cosmic environment, space rendering (not in training)
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/validation/ood_space.png" alt="Space/Astronomy" width="100%" style="max-width: 512px;">
-  <p><em>Image: ood_space.png</em></p>
-</div>
-
----
-
-### 🍰 Food Photography
-
-**Prompt:** *"gourmet chocolate cake with berries on elegant plate, professional food photography, soft studio lighting"*
-
-**Tests:** Food textures, studio lighting, product photography (not in training)
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/validation/ood_food.png" alt="Food Photography" width="100%" style="max-width: 512px;">
-  <p><em>Image: ood_food.png</em></p>
-</div>
-
----
-
-### 👴 Human Portrait
-
-**Prompt:** *"close-up portrait of elderly man with weathered face and kind eyes, dramatic side lighting, black and white"*
-
-**Tests:** Human facial features, skin texture, B&W conversion (training had cat portrait, not human closeup)
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/validation/ood_portrait.png" alt="Human Portrait" width="100%" style="max-width: 512px;">
-  <p><em>Image: ood_portrait.png</em></p>
-</div>
-
----
-
-### 🎨 Abstract Art
-
-**Prompt:** *"abstract watercolor painting with flowing colors, pink and blue gradient, artistic ethereal style"*
-
-**Tests:** Non-representational art, color blending (training was all representational)
-
-<div align="center">
-  <img src="https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/validation/ood_abstract.png" alt="Abstract Art" width="100%" style="max-width: 512px;">
-  <p><em>Image: ood_abstract.png</em></p>
-</div>
-
----
-
-All validation images and prompts can be found in the `validation/` directory.
+### Checkpoint 1600 (This Checkpoint)
 
+![Checkpoint 1600](https://huggingface.co/Mercity/lcm-lora-sd1.5-1600/resolve/main/comparison_grid.png)
 
 
 ---
@@ -299,7 +177,7 @@ guidance_scale = 1.0            # Required for LCM
 
 ---
 
-## In-Distribution Sample Outputs
+## Sample Outputs
 
 The comparison grid above shows outputs from this checkpoint at 2, 4, and 6 inference steps, compared to standard SD1.5 at 50 steps.
 
@@ -319,6 +197,34 @@ All sample images for this checkpoint are available in the `samples/` directory.
 
 </details>
 
+### Out-of-Distribution (OOD) Validation Images
+
+To test generalization beyond the training distribution, we generated images for 5 OOD prompts that are deliberately different from training prompts:
+
+1. **🐠 Underwater Scene**
+   - *"underwater coral reef with colorful fish and sea anemones, crystal clear water, natural sunlight filtering through"*
+   - Tests: Water effects, marine life, underwater lighting (not in training)
+
+2. **🚀 Space/Astronomy**
+   - *"astronaut floating in space with earth in background, stars and galaxies, cinematic lighting, 4k"*
+   - Tests: Zero gravity, cosmic environment, space rendering (not in training)
+
+3. **🍰 Food Photography**
+   - *"gourmet chocolate cake with berries on elegant plate, professional food photography, soft studio lighting"*
+   - Tests: Food textures, studio lighting, product photography (not in training)
+
+4. **👴 Human Portrait**
+   - *"close-up portrait of elderly man with weathered face and kind eyes, dramatic side lighting, black and white"*
+   - Tests: Human facial features, skin texture, B&W conversion (training had cat portrait, not human closeup)
+
+5. **🎨 Abstract Art**
+   - *"abstract watercolor painting with flowing colors, pink and blue gradient, artistic ethereal style"*
+   - Tests: Non-representational art, color blending (training was all representational)
+
+**Why OOD Validation?** These prompts test whether the model truly learned general concepts rather than just memorizing training prompts. Good OOD performance indicates robust generalization.
+
+All validation images can be found in the `validation/` directory. See [`validation/prompts.txt`](validation/prompts.txt) for the complete list of prompts used.
+
 ---
 
 ## Performance
@@ -341,44 +247,6 @@ All sample images for this checkpoint are available in the `samples/` directory.
 
 ---
 
-## Advanced Usage
-
-### Speed Optimization
-
-```python
-# Fuse LoRA for faster inference
-pipe.fuse_lora(lora_scale=1.0)
-
-# Use xformers for memory efficiency
-pipe.enable_xformers_memory_efficient_attention()
-
-# Compile model (PyTorch 2.0+)
-pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-```
-
-### Multiple LoRAs
-
-```python
-# Combine with other LoRAs
-pipe.load_lora_weights("other_style.safetensors", adapter_name="style")
-pipe.load_lora_weights("Mercity/lcm-lora-sd1.5-1600", adapter_name="lcm")
-
-# Adjust weights
-pipe.set_adapters(["style", "lcm"], adapter_weights=[0.8, 1.0])
-```
-
-### Switch Between Checkpoints
-
-```python
-# Load different checkpoints from this series
-pipe.load_lora_weights("Mercity/lcm-lora-sd1.5-400")  
-pipe.load_lora_weights("Mercity/lcm-lora-sd1.5-800")  
-pipe.load_lora_weights("Mercity/lcm-lora-sd1.5-1200") 
-pipe.load_lora_weights("Mercity/lcm-lora-sd1.5-1600") 
-```
-
----
-
 ## Series Information
 
 ### Training Progression