Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+comparison.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+library_name: comfyui
+pipeline_tag: text-to-image
+tags:
+  - qwen-image
+  - qwen-image-2.1
+  - taesd
+  - tiny-autoencoder
+  - vae
+  - comfyui
+  - preview
+---
+
+# TAE Qwen-Image 2.1 · AcademiaSD
+
+<p align="center">
+  <b>Tiny AutoEncoder (TAESD-style decoder) for fast, sharp live previews of Qwen-Image 2.1 in ComfyUI.</b>
+</p>
+
+![Original · TAE · Latent2RGB](comparison.jpg)
+
+<p align="center"><i>Left: Qwen-Image 2.1 VAE · Center: <b>TAEQwenImage21_AcademiaSD</b> · Right: Latent2RGB (ComfyUI's default preview for this model)</i></p>
+
+ComfyUI previews Qwen-Image 2.1 only with Latent2RGB, a linear 64→3 color projection that looks blurry and blocky. This decoder is distilled from the Qwen-Image 2.1 VAE: it turns the sampler's latents into a real preview image in about 15 ms, with no need for the full VAE.
+
+| | |
+| :--- | :--- |
+| File | `TAEQwenImage21_AcademiaSD.safetensors` |
+| Size | 3.3 MB (fp16) |
+| Parameters | 1.63 M |
+| Input | Qwen-Image 2.1 latents, 64 channels, as the sampler sees them (`x0`) |
+| Output | RGB at 16× the latent resolution, range [0, 1] |
+| Decode time | ~15 ms for a 1024×1024 preview (RTX 5080, fp16) |
+| Validation PSNR | **30.1 dB** vs 20.9 dB for Latent2RGB |
+
+---
+
+## 🚀 Usage in ComfyUI
+
+1. Download `TAEQwenImage21_AcademiaSD.safetensors` to `ComfyUI/models/vae_approx/`.
+2. Install [ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes).
+3. Add the **Model Preview Override** node between your Qwen-Image 2.1 model and the sampler.
+4. In its `tiny_vae` input, choose `TAEQwenImage21_AcademiaSD.safetensors`.
+
+> ComfyUI's built-in **TAESD** preview method does not pick up this file: core has no tiny decoder entry for Qwen-Image 2.1 and its TAESD loader only supports 8× decoders. Use the KJNodes node.
+
+## 🔧 Training details
+
+- **Teacher:** Qwen-Image 2.1 VAE (`qwen_image_2.1_vae_bf16.safetensors`).
+- **Architecture:** flat TAESD decoder, `Clamp → conv → 4 × (3 blocks + 2× upsample + conv) → block → conv`, width 64.
+- **Latent space:** latents normalized with ComfyUI's `QwenImage21` latent format (mean/std), the same space as the sampler's `x0`, so no extra scaling is needed.
+- **Data:** 4,072 varied images, 512×512 crops, encoded once with the real VAE.
+- **Training:** 30,000 steps, batch 8, 256×256 tiles, AdamW LR 5e-4 with cosine decay, L1 + FFT loss, EMA 0.999, latent noise augmentation for stable previews on the noisy `x0` of the first steps.
+
+## ⚠️ Limitations
+
+- Preview only: use the real VAE for the final decode.
+- Decoder only, there is no encoder.
+- RGB only: the Qwen-Image 2.1 VAE also decodes an alpha channel, which this decoder skips.
+
+---
+
+# 🇪🇸 Español
+
+Tiny AutoEncoder (decoder tipo TAESD) para previsualizar **Qwen-Image 2.1** en ComfyUI con nitidez y en tiempo real. Sustituye a Latent2RGB, la previsualización por defecto, borrosa y pixelada. Destilado del VAE de Qwen-Image 2.1: decodifica una previsualización de 1024 px en unos 15 ms, con 30,1 dB de PSNR frente a 20,9 dB de Latent2RGB.
+
+**Uso:**
+1. Descarga `TAEQwenImage21_AcademiaSD.safetensors` en `ComfyUI/models/vae_approx/`.
+2. Instala [ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes).
+3. Pon el nodo **Model Preview Override** entre el modelo de Qwen-Image 2.1 y el sampler.
+4. En su entrada `tiny_vae`, elige `TAEQwenImage21_AcademiaSD.safetensors`.
+
+El método de previsualización **TAESD** que trae ComfyUI no lo usa, porque no tiene entrada para Qwen-Image 2.1. Usa el nodo de KJNodes.
+
+Solo sirve para previsualizar: la imagen final se decodifica con el VAE real.
+
+---
+
+## 🙏 Credits
+
+- TAESD architecture: [madebyollin/taesd](https://github.com/madebyollin/taesd)
+- Model Preview Override node: [kijai/ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes)
+- Qwen-Image 2.1: Qwen team
+
+## 🔗 AcademiaSD
+
+[YouTube](https://www.youtube.com/@Academia_SD) · [X / Twitter](https://twitter.com/Academia_S_D) · [Discord](https://discord.gg/Syuaduy678) · [Ko-fi](https://ko-fi.com/academiasd)

TAEQwenImage21_AcademiaSD.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fa2ed8e1bf9609ac0e876e4ad89aa00a6c5708021d0c843a2b58d35db84ad4
+size 3259798