Update README.md

README.md

@@ -6,15 +6,33 @@ library_name: diffusers
 
 # MicroDecoder
 
-**Micro-VAE** that can be trained on *any* diffusion model in ~15min and provides low-quality reconstruction from latents in ~0.01sec.  
-Inference includes noise correction based on current timestep, intention blurring and upscale interpolation: all with intention of providing as fast-as-possible reconstruction that is viable on any noise level.  
+**Micro-VAE** that can be trained on *any* diffusion model in **~15min** and provides low-quality reconstruction from latents to RGB in **~0.01sec**.  
+Inference includes noise correction based on current timestep, intentional blurring plus upscale interpolation: all with intention of providing as fast-as-possible reconstruction that is viable and consistent with any noise levels.  
 Intended use-case is live-preview during generative model inference.  
 
-- Training code [here](https://github.com/vladmandic/sdnext/blob/dev/modules/vae/sd_vae_micro_train.py)
+- Model definition and training code [here](https://github.com/vladmandic/sdnext/blob/dev/modules/vae/sd_vae_micro_train.py)
 - Example inference code [here](https://github.com/vladmandic/sdnext/blob/dev/modules/vae/sd_vae_micro.py)
 
-Training examples:
+## Examples
+
 ```shell
 sd_vae_micro_train.py --dim 256 --epochs 350 --resolution 512 --scale 8 --lr 0.0003 --folder ~/generative/Input/vae/ --vae AutoencoderKLQwenImage21 --repo Qwen/Qwen-Image-2.1 --output AutoencoderKLQwenImage21.safetensors
 sd_vae_micro_train.py --dim 256 --epochs 350 --resolution 512 --scale 4 --lr 0.0003 --folder ~/generative/Input/vae/ --vae AutoencoderKLFlux2 --repo black-forest-labs/FLUX.2-klein-9B --output AutoencoderKLFlux2.safetensors
 ```
+
+```log
+Encoding Latents: 100%
+Training MicroDecoder [350 epochs | Channels: 32 | Hidden: 256 | Scale: 4x]
+Dataset: 360 train samples | 40 validation samples | EMA decay: 0.999
+
+Epoch  | Train Tot | Tr PSNR | Tr SSIM | Val Tot  | Val PSNR | Val SSIM | Val L1  | Val LAB
+--------------------------------------------------------------------------------------------
+001/350  | 5.7244    | 10.38   | 0.3431  | 5.9729   | 10.56    | 0.3047   | 0.2676  | 0.4254  *
+100/350  | 2.7690    | 25.49   | 0.8030  | 2.2011   | 26.52    | 0.8672   | 0.0376  | 0.0699  *
+200/350  | 2.4006    | 27.04   | 0.8400  | 1.1679   | 34.24    | 0.9635   | 0.0132  | 0.0317  *
+300/350  | 2.3950    | 28.05   | 0.8472  | 1.0002   | 35.63    | 0.9723   | 0.0113  | 0.0282  *
+350/350  | 2.3010    | 28.51   | 0.8511  | 0.9781   | 35.83    | 0.9734   | 0.0111  | 0.0278  *
+
+Training complete! Best validation PSNR: 35.83 dB (Epoch 350)
+Saved best EMA model weights to: AutoencoderKLFlux2.safetensors
+```