Update README.md

README.md

@@ -14,6 +14,25 @@ This is a BF16 conversion of [`black-forest-labs/FLUX.2-small-decoder`](https://
 
 `FLUX.2 Small Decoder` is a distilled VAE decoder that serves as a **drop-in replacement** for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged.
 
+Both images below have been generated using FLUX.2 Klein NVFP4 with BF16 VAEs.
+
+<table style="width:auto">
+  <tr>
+    <td align="center"><img src="./images/flux2-vae-small.png" style="width:45%"/></td>
+    <td align="center"><img src="./images/flux2-vae.png" style="width:45%"/></td>
+  </tr>
+  <tr>
+    <td align="center"><b>FLUX.2 VAE small</b></td>
+    <td align="center"><b>FLUX.2 VAE</b></td>
+  </tr>
+</table>
+
+**Prompt**
+<pre>A black cat holding a sign that says 'hello world' in typewriter font</pre>
+
+
+
+
 # **Key Features**
 
   1. **~1.4x faster decoding** compared to the full decoder.
@@ -28,35 +47,6 @@ Compatible with all open FLUX.2 models:
 - [FLUX.2-klein-9b-kv](https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv)
 - [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev)
 
-# **Usage**
-
-```shell
-pip install git+https://github.com/huggingface/diffusers.git
-```
-
-```python
-import torch
-from diffusers import Flux2KleinPipeline, AutoencoderKLFlux2
-
-device = "cuda"
-dtype = torch.bfloat16
-
-vae = AutoencoderKLFlux2.from_pretrained("InsecureErasure/FLUX.2-small-decoder-BF16", torch_dtype=dtype)
-pipe = Flux2KleinPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-4B", vae=vae, torch_dtype=dtype)
-pipe.enable_model_cpu_offload()
-
-prompt = "A black cat holding a sign that says 'hello world' in typewriter font"
-image = pipe(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    guidance_scale=1.0,
-    num_inference_steps=4,
-    generator=torch.Generator(device=device).manual_seed(0)
-).images[0]
-image.save("flux-klein-small-decoder.png")
-```
-
 ---
 # License