Update README.md

README.md

@@ -1,3 +1,20 @@
 ---
 license: apache-2.0
+pipeline_tag: text-to-image
+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.  
+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)
+- Example inference code [here](https://github.com/vladmandic/sdnext/blob/dev/modules/vae/sd_vae_micro.py)
+
+Training 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
+```