Qwen-Image-2.1-Multiple-Angles-LoRA

Qwen-Image-2.1-Multiple-Angles-LoRA

A camera-control LoRA for Qwen-Image-2.1 that reshoots a subject from a chosen angle, with 36 poses plus close-up variants. For image makers who work in ComfyUI or diffusers.

Made by akhaliq on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This LoRA adds viewpoint control to the Qwen-Image-2.1 image model. You give it a photo and ask for a different horizontal angle and height, and it returns the same subject seen from there. The card says no LoRA of this kind existed yet for that base.

Who it suits: Image makers who need the same object or subject from several viewpoints, and who work in ComfyUI or diffusers.

Industry | Who uses it | How they use it | Example
E-commerce | Product photographers | Show an item from other angles | A shoe photo turned to a side view
Design | Concept artists | Explore a subject from new camera positions | A character seen from above
Games | Asset teams | Make reference views of an object | A prop from the back
Marketing | Content teams | Build a set of views from one photo | A twelve-angle orbit of one subject

You can skip it if you want free-form edits, since this LoRA is only for camera position. You can also skip it if you do not use Qwen-Image-2.1.

Where to use it:

• ComfyUI, with a LoRA node added to a Qwen-Image-2.1 graph
• Python with the diffusers library
• Windows, macOS or Linux, with Python for the download step

Use case | Who | What they get back
Angle change | Photographers | The same subject from the angle you request
Orbit sets | Artists | A series of views around one subject
Top-down and close-up views | Designers | High-angle or close framings of an object

How to set it up:

• Python and pip on your computer
• A Qwen-Image-2.1 setup in ComfyUI or diffusers
• The recommended v2 checkpoint, about 319 MB

1. Install the Hugging Face hub package.
2. Download the repository with the hf command.
3. Load the v2 file as a LoRA in your Qwen-Image-2.1 workflow.

pip install -U huggingface_hub
hf download akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA

How to use it: Start every prompt with the trigger word <mva>, then describe the angle you want from the card's pose list. Set the LoRA strength between 0.8 and 1.0, in ComfyUI or diffusers.

Setting | What it does
<mva> | Trigger word that every prompt starts with
12 azimuths | Horizontal angles in 30 degree steps
4 camera heights | Eye level, raised, high angle and top-down
Strength 0.8 to 1.0 | The LoRA weight the card advises

Example: You feed in a photo of a dog and ask for a view from a different horizontal angle at eye level. The model returns the dog from that side. The card shows an orbit through all 12 angles.

For newcomers and experts: If you are new, start with the v2 file and a strength near 1.0, and try one angle at a time. Pick a clear, single-subject photo for your first test.

If you know the field, v2 trained on 13,328 pairs at rank 64 in bf16, against 5,028 pairs at rank 32 for v1. It targets v1's weak spots with characters and unseen identity detail. The author recommends the step 1,500 checkpoint, with 2,000 to 2,500 for stronger angle effects.

Your photo plus an mva prompt
Qwen-Image-2.1 with the LoRA
Same subject from the new angle

Title: Training pairs
v1: 5028
v2: 13328

Good to know:

• License: Apache 2.0
• Cost to run: your own GPU hardware, with no paid service named
• Data it reaches: the photos you give it and the files you download
• Not for: general image edits, since it is built for camera position only
• Files: v1 is kept in the repository and v2 is the recommended download

On Hugging Face, 13 November 2026

• Task: image to image
• Library: diffusers
• Downloads in the last 30 days: 3,505
• Likes: 110
• License: apache-2.0
• Based on: Qwen/Qwen-Image-2.1
• Tags: diffusers, qwen-image-2.1, lora, camera-control, multiple-angles, image-editing, multi-view, dome-objaverse, image-to-image

Links

• Model: https://huggingface.co/akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA
• Files: https://huggingface.co/akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA

Then follow the usage in its model card. Nothing in this kit runs by itself.