The original source of this model is <a rel="ugc" href="https://huggingface.co/Felldude/QWEN_2.1_HDR_VAE">Felldude/QWEN_2.1_HDR_VAE</a> ; All I have done a conversion of the VAE to ComfyUI format. As this work is derived from the official Qwen Image 2.1 materials, the Qwen Research License Agreement applies; I do not impose any additional terms. Please consult the source link for full information on the model, and refer to Qwen materials for any license-related questions. In summary (Information below is partial information from the source README): <h2 id="qwen-image-2.1-hdr-vae">Qwen Image 2.1 HDR VAE</h2>Fine-tuned Qwen Image 2.1 autoencoder for RGBA / HDR-oriented reconstruction.The goal is stronger dynamic range, color volume, and detail energy for HDR-style workflows—not perfect fidelity to the source frame.<h3 id="intended-use">Intended use</h3><ul><li>HDR-oriented encode/decode in Qwen Image pipelines</li><li>Image editing / generation stacks that benefit from punchier latents</li><li>Research on RGBA + high dynamic range autoencoders</li></ul>Not intended for: archival reconstruction, metrics-maximizing ablations, or any setting where matching the input pixel-for-pixel matters more than look.<h3 id="limitations">Limitations</h3><ul><li>Will diverge from the source on sharpness, saturation, and color volume by design</li><li>Alpha is supported; behavior on unusual alpha mattes is not heavily tuned</li><li>Very large resolutions are memory-heavy (16× latent downscale)</li></ul>

HDR VAE for Qwen Image 2.1 (ComfyUI port)

Original conversion to ComfyUI format.

Files with SHA256: 9298a6274a0c7ce12fc9a8f644d1fc40829db25446960f37261b5d77c48dbb5f