Update README: Fix image URLs, show all 7 scale comparisons, update repo references

README.md

@@ -16,7 +16,7 @@ tags:
 widget:
 - text: "a beautiful garden scene with colorful flowers and butterflies, highly detailed, professional photography, vibrant colors"
   output:
-    url: "https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl-10k/resolve/main/examples/example.png"
+    url: "https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/example.png"
 inference: true
 ---
 
@@ -121,7 +121,7 @@ pipe = StableDiffusionXLControlLoraV3Pipeline.from_pretrained(
 )
 
 # Load Control LoRA weights
-pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k", adapter_name="brightness")
+pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl", adapter_name="brightness")
 pipe.to("cuda")
 
 # Load grayscale/brightness control image
@@ -213,24 +213,24 @@ The model includes intermediate checkpoints from throughout training:
 
 ```python
 # Early checkpoint (25% - 2,500 samples)
-pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k",
+pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl",
                        adapter_name="brightness",
-                       revision="checkpoint-78")
+                       subfolder="checkpoint-78")
 
 # Mid checkpoint (50% - 5,000 samples)
-pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k",
+pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl",
                        adapter_name="brightness",
-                       revision="checkpoint-156")
+                       subfolder="checkpoint-156")
 
 # Late checkpoint (75% - 7,500 samples)
-pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k",
+pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl",
                        adapter_name="brightness",
-                       revision="checkpoint-234")
+                       subfolder="checkpoint-234")
 
 # Near-final checkpoint (99% - 9,984 samples)
-pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k",
+pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl",
                        adapter_name="brightness",
-                       revision="checkpoint-312")
+                       subfolder="checkpoint-312")
 
 # Final model (10,000 samples, main branch - recommended)
 pipe.load_lora_weights("Oysiyl/controlnet-lora-brightness-sdxl-10k",
@@ -286,9 +286,25 @@ The model includes checkpoints from throughout training:
 
 ### Visual Comparison
 
-![Checkpoint Progression](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl-10k/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_1.0.png)
+Each comparison shows QR input + all 5 checkpoints (25%, 50%, 75%, 99%, 100%) at different conditioning scales:
+
+#### Scale 0.25 (Subtle Control)
+![Scale 0.25](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_0.25.png)
 
-*Checkpoint progression at scale 1.0, showing improvement from 25% to 100% training*
+#### Scale 0.5 (Light Control)
+![Scale 0.5](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_0.5.png)
+
+#### Scale 0.7 (Moderate Control)
+![Scale 0.7](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_0.7.png)
+
+#### Scale 1.0 (Balanced Control - Recommended)
+![Scale 1.0](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_1.0.png)
+
+#### Scale 1.25 (Strong Control)
+![Scale 1.25](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_1.25.png)
+
+#### Scale 1.5 (Very Strong Control)
+![Scale 1.5](https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl/resolve/main/examples/controlnet_lora_checkpoint_comparison_scale_1.5.png)
 
 ### Key Observations
 
@@ -388,24 +404,26 @@ accelerate launch --mixed_precision="bf16" train_sdxl.py \
   --init_lora_weights="gaussian"
 ```
 
-## Available Branches
+## Available Checkpoints
+
+All checkpoints are available in the main branch:
 
-- `main`: Final model (10,000 samples, recommended)
-- `checkpoint-78`: Early checkpoint (2,500 samples)
-- `checkpoint-156`: Mid checkpoint (5,000 samples)
-- `checkpoint-234`: Late checkpoint (7,500 samples)
-- `checkpoint-312`: Near-final checkpoint (9,984 samples)
+- **Root directory**: Final model (10,000 samples, recommended)
+- **checkpoint-78/**: Early checkpoint (2,500 samples, 25% trained)
+- **checkpoint-156/**: Mid checkpoint (5,000 samples, 50% trained)
+- **checkpoint-234/**: Late checkpoint (7,500 samples, 75% trained)
+- **checkpoint-312/**: Near-final checkpoint (9,984 samples, 99% trained)
 
 ## Citation
 
 ```bibtex
-@misc{controlnet-lora-brightness-sdxl-10k,
+@misc{controlnet-lora-brightness-sdxl,
   author = {Oysiyl},
   title = {ControlNet LoRA SDXL - Brightness Control (10k @ 1024×1024)},
   year = {2026},
   publisher = {HuggingFace},
   journal = {HuggingFace Model Hub},
-  howpublished = {\url{https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl-10k}}
+  howpublished = {\url{https://huggingface.co/Oysiyl/controlnet-lora-brightness-sdxl}}
 }
 ```