Extend a picture on any side, and Qwen Image 2.1 paints the new area. Qwen3-VL writes the prompt, and my outpaint LoRA keeps your picture in place. Your image goes back on top of the result.It's in my new video: <a target="_blank" rel="ugc" href="https://youtu.be/GociGWQQDSs">I threw a ton of edits at Qwen Image 2.1, FLUX 3 Klein and FIBO 2</a><h2 id="how-to-use-it">How to use it</h2><ol><li>Load your image.</li><li>Pick a ratio, or drag the orange handles out. The small button next to the ratios flips portrait and landscape.</li><li>Optional: finish the sentence in What goes there to say what belongs in the new area.</li><li>Press Run.</li></ol><h2 id="what-you-need">What you need</h2><ul><li>AusBoss nodes 2.5.0 or newer. In ComfyUI-Manager, search "AusBoss". Already have them? Update first.</li><li>A ComfyUI build with Text Encode Qwen Image 2.1 (mid-September 2026 or newer).</li><li>The Qwen Image 2.1 models and <a target="_blank" rel="ugc" href="https://civarchive.com/models/2967375">my outpaint LoRA</a>:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors">qwen_image_2.1_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 7.26 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors">qwen3vl_8b_int8_convrot.safetensors</a> → <code>models/text_encoders</code> · 9.35 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors">qwen_image_2.1_vae_bf16.safetensors</a> → <code>models/vae</code> · 676 MB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/Qwen-Image-2.1-Outpaint-LoRA/resolve/main/qwen-image-2.1-outpaint-v2.safetensors">qwen-image-2.1-outpaint-v2.safetensors</a> → <code>models/loras</code> · 159 MB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/Qwen-Image-2.1-Outpaint-LoRA/resolve/main/qwen-image-2.1-outpaint.safetensors">qwen-image-2.1-outpaint.safetensors</a> → <code>models/loras</code> · 159 MB (v1, for big zoom-outs)</li></ul></li></ul><h2 id="tips">Tips</h2><ul><li>Keep the LoRA on. Without it Qwen often shifts your picture. If the file is missing, the run stops at a red LoRA Loader; switch its row off to run without it.</li><li>Say what's missing. The box starts with <code>Also include in the prompt:</code>. Add to it, for example <code>she wears blue jeans.</code> If you delete those words and type your own, the workflow puts them back.</li><li>Pull out at most about your picture's own size on one side per run. More than that can paint a second scene. For more, run again on the result.</li><li>Crop out edges that confuse it. Noise, a frame line or a busy strip along the edge of your picture can make the new area come out strange. Drag the blue handles on Image Crop + Rotate + Pad inward to cut those edges off first.</li><li>Dark corners get extended. A vignette in your photo carries on into the new area.</li><li>Transparent PNG? A person or a scene cut out works. A product cut out with nothing behind it can come back on plain gray, so put it on a background first.</li><li>About 8 seconds a run on an RTX 5090.</li></ul>Tilted picture, or something to crop away? Try <a target="_blank" rel="ugc" href="https://civarchive.com/models/2966883">Qwen Image 2.1 Rotate + Outpaint</a>.<h2 id="credits">Credits</h2>Qwen Image 2.1 is © Alibaba Qwen, under the Qwen Research License: non-commercial use only, and commercial use needs a license from Qwen. The outpaint LoRA is mine and follows that license. I trained it on my own pictures plus CommonCatalog CC-BY, PD12M and anime-with-caption-cc0.v1.2 (2026-09-30): the padding follows your picture, the seam blends in, and your own words always reach the prompt. v1.1 (2026-09-26): a missing LoRA stops the run, LoRA v2 by default. v1.0 (2026-09-25): first release.Questions or bugs: <a target="_blank" rel="ugc" href="https://github.com/ausboss/ComfyUI-AusBoss/issues">GitHub issues</a> or the comments here. Videos on <a target="_blank" rel="ugc" href="https://www.youtube.com/@ausbossdev">YouTube @ausbossdev</a>. More from me on <a target="_blank" rel="ugc" href="https://x.com/Zanzibased">X @Zanzibased</a> and <a target="_blank" rel="ugc" href="https://github.com/ausboss">GitHub</a>.

Qwen Image 2.1 Outpaint | Auto Prompt

First release. Any-side outpaint on Qwen Image 2.1; Qwen3-VL writes the prompt in the style of the outpaint LoRA's training captions. The LoRA is optional but recommended.

Files with SHA256: 9717b9f0536b51584e6f8bea7bf1c83f3f7830e17ee5cd70ec415e98ff4d8f6e