Say what to change in plain words, and the full Qwen Image 2.1 model edits your picture. Switches write the prompt for you, upscale the result to 8 megapixels, make it about three times faster, or make a new picture instead.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>
Want the 8-step Turbo checkpoint instead? That's my <a target="_blank" rel="ugc" href="https://civarchive.com/models/2994247">Turbo version</a> of this workflow.
<h3>How to use it</h3>
<ol>
<li>Load your picture.</li>
<li>Write the change, like "make it snow". With Auto prompt on, a few words are enough.</li>
<li>Run. A before and after slider shows your picture against the edit.</li>
<li>To make a new picture instead, switch Edit a picture off, write a prompt and set the size in Latent Size.</li>
</ol>
<h3>The four switches</h3>
<ul>
<li>Edit a picture. On as the file opens: the prompt changes the picture you load, at 2 megapixels in your picture's own shape. It also turns my Consistency LoRA on at 0.5, which keeps the edit lined up with your picture. Off: the prompt makes a new picture.</li>
<li>Auto prompt. Qwen writes the full prompt from a few words of yours. For an edit it looks at your picture and writes the instruction. What it wrote shows in Show Text.</li>
<li>Upscale the result. Redraws the result bigger in tiles with my Restore LoRA, to the Megapixels you set. It opens at 8.</li>
<li>Fast. The Viggle Turbo LoRA with its own 6 steps instead of 25. About three times faster, a little softer.</li>
</ul>
<h3>What you need</h3>
<ul>
<li>AusBoss nodes 2.15.0 or newer. In ComfyUI-Manager, search "AusBoss". Already have them? Update first.</li>
<li>ComfyUI 0.38 or newer.</li>
<li>
The models:
</li>
<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>For Edit a picture (on as the file opens), my Consistency LoRA: <a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/Qwen-Image-2.1-Consistency-LoRA/resolve/main/qwen-image-2.1-consistency.safetensors">qwen-image-2.1-consistency.safetensors</a> → <code>models/loras</code> · 159 MB</li>
<li>Only for Upscale the result, my Restore LoRA: <a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/Qwen-Image-2.1-Restore-LoRA/resolve/main/qwen-image-2.1-restore.safetensors">qwen-image-2.1-restore.safetensors</a> → <code>models/loras</code> · 159 MB</li>
<li>Only for Fast, the Viggle Turbo LoRA: <a target="_blank" rel="ugc" href="https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors">Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors</a> → <code>models/loras</code> · 680 MB</li>
</ul>
<h3>Tips</h3>
<ul>
<li>The steps are in the Steps box, under the switches. 25 is what Qwen's own template uses. With Fast on, the picture runs Viggle's own 6 steps and the box goes to 8 for the upscale.</li>
<li>For an edit, say what changes and what stays: "Change the black t-shirt to a red sweater. Keep everything else the same."</li>
<li>For a restyle, raise the Consistency row to 1. A painting or anime look can come back zoomed in or shifted. At 1 it brought my restyles from about 24 px of movement down to 1.6 px. 0.5 is enough for snow or new clothes and keeps a little more skin detail.</li>
<li>Removing a person? Say what they're holding goes too. Otherwise a cup or a phone can stay behind.</li>
<li>Don't like the result? Press New seed on the Seed node.</li>
<li>Times on an RTX 5090 at 2 megapixels: about 15 seconds at 25 steps, about 6 with Fast. The upscale to 8 megapixels adds about 85 seconds, or about 55 with Fast.</li>
<li>If the run stops at a red LoRA Loader, a LoRA that is switched on is missing. Download it from the list above.</li>
</ul>
<h3>What it does not do</h3>
<ul>
<li>It takes one picture. For an outfit from another photo, see my <a target="_blank" rel="ugc" href="https://civarchive.com/models/3000002">Turbo Multi-Image Edit page</a>. To change only an area you paint, see my <a target="_blank" rel="ugc" href="https://civarchive.com/models/3000390">Qwen Image 2.1 Inpaint page</a>.</li>
<li>The upscale is a redraw. Fine detail is made up to fit, and small lettering can come back misspelled.</li>
<li>Want it with core nodes only? Pick v1.1 in the version list and download its second file, the one ending in 3295395.</li>
</ul>
<h3>Credits</h3>
Qwen Image 2.1 is by <a target="_blank" rel="ugc" href="https://huggingface.co/Qwen/Qwen-Image-2.1">Alibaba Qwen</a>, under the Qwen Research License: non-commercial use only. The ComfyUI files are from <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image-2.1">Comfy-Org</a>. The Viggle Turbo LoRA is by <a target="_blank" rel="ugc" href="https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo">Viggle</a>, for research use under the same license.
v2.0 (2026-10-20): rebuilt. Change a picture or make a new one, with Auto prompt, Upscale, Fast and a Steps box. v1.1 (2026-09-30): new layout, an empty LoRA Loader for the Consistency LoRA, and transparent PNGs no longer come back on black. v1.0 (2026-09-24): 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 Generate + Edit | Full Model, Auto Prompt

Files with SHA256: b232c615a2fb40cc66d7fcf2594e55ac9637f58002d487cd1a8d017a8e977b2a