Model reference · open weights
Qwen-Image-Ed-2511-Multiple-Angles-LoRA is an open-weight image model from fal, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Qwen-Image-Edit-2511-Multiple-Angles-LoRA Multi-angle camera control LoRA for Qwen-Image-Edit-2511 96 camera positions • Trained on 3000+ Gaussian Splatting renders • Built with fal.ai Results Highlights Camera System Diagrams Why This LoRA? This is the first multi-angle camera control LoRA for Qwen-Image-Edit-2511. While Qwen-Image-Edit-2511 has built-in viewpoint capabilities, this LoRA provides: - 96 precise camera poses - Exact control over camera position - 3000+ training pairs - Massive dataset for maximum accuracy - Gaussian Splatting data - 3D-consistent training for better spatial understanding - Low-angle excellence - Proper support for ground-level and low camera positions (-30°) Prompt Format Quick Examples 96 Camera Positions 4 Elevations × 8 Azimuths × 3 Distances = 96 Poses Azimuths (Horizontal Rotation) Elevations (Vertical Angle) Distances All 96 Prompts Reference CLOSE-UP (32 prompts) Low-angle (-30°) Eye-level (0°) Elevated (30°) High-angle (60°) MEDIUM SHOT (32 prompts) Low-angle (-30°) Eye-level (0°) — Reference pose: front view eye-level shot medium shot Elevated (30°) High-angle (60°) WIDE SHOT (32 prompts) Low-angle (-30°) Eye-level (0°) Elevated (30°) High-angle (60°) Files ▶️ Try it live on fal.ai Recommended Settings - LoRA Strength: 0.8 - 1.0 - Base Model: Qwen/Qwen-Image-Edit-2511 Training Details Tips for Best Results 1. Use the exact prompt format - <sks trigger is essential 2. Respect the order - [azimuth] [elevation] [distance] 3. Start with LoRA strength 0.9 - Adjust based on results 4. Try low-angle shots - This LoRA excels at low camera positions (-30°) 5. Input image matters - Clear subjects with good lighting work best Related Work - Qwen-Image-Edit-2511 - Base model - Flux-2-Multi-Angles-LoRA-v2 - Multi-angle for Flux (72 poses) - next-scene-qwen-image-lora Author Built by Lovis Odin (@lovis93 • @odinlovis) at fal Trained using fal Qwen Image Edit 2511 Trainer If you find this useful, please star the repo! Issues? Open a discussion in the Community tab
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | fal |
|---|---|
| Type | Image models |
| Variants | 1 |
| Runs with | diffusers |
| Based on | Qwen/Qwen-Image-Edit-2511 |
| Released | 2026-01-07 |
| Popularity | 64k downloads / month |
| Likes | 1,518 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qwen-Image-Edit-2511-Multiple-Angles-LoRA | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys qwen-image-ed-2511-multiple-angles-lora for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen-image-ed-2511-multiple-angles-lora below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen-image-ed-2511-multiple-angles-lora","prompt":"a red bicycle","size":"1024x1024"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗