{"id":7870,"date":"2026-09-30T13:15:49","date_gmt":"2026-09-30T04:15:49","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/30\/qi-2-1-anyangle-camera-control-lora\/"},"modified":"2026-09-30T21:29:40","modified_gmt":"2026-09-30T12:29:40","slug":"qi-2-1-anyangle-camera-control-lora","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/30\/qi-2-1-anyangle-camera-control-lora\/","title":{"rendered":"QI_2.1_AnyAngle Camera Angle Control LoRA: 48GB+ VRAM, File List"},"content":{"rendered":"

Sample outputs are available on the model card<\/a>.<\/em><\/p>\n

<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\nlilylilith\/QI_2.1_AnyAngle<\/a><\/td>\n<\/tr>\n
Family guide<\/td>\nQwen-Image-2.1 guide (3 articles)<\/a><\/td>\n<\/tr>\n
Publisher guide<\/td>\nAlibaba (Qwen): models and licenses<\/a><\/td>\n<\/tr>\n
Published<\/td>\n2026-09-28<\/td>\n<\/tr>\n
License<\/td>\napache-2.0<\/td>\n<\/tr>\n
Formats<\/td>\nsafetensors<\/a><\/td>\n<\/tr>\n
Source type<\/td>\nPrimary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Values determined by this site’s code when the information was collected. Dates are JST.<\/em><\/p>\n

<\/p>\n

Overview<\/h2>\n

In AI image generation, specifying camera angles in prompts often fails to yield the intended composition, a common challenge faced by many engineers. While existing image editing models (such as Qwen Image Edit and FLUX.2) are beginning to make it possible to change camera angles in existing images, most of them have limited azimuth and elevation options, falling short of the free control creators demand. Furthermore, it has been reported that attempting dramatic angle changes causes the image style to deviate significantly from the original.<\/p>\n

“QI_2.1_AnyAngle” is a LoRA designed to overcome these challenges. This model inputs the original image and a “coarse” image generated from a 3D model or Gaussian Splat as references into Qwen Image 2.1, transforming the image to any camera angle while maintaining style consistency.<\/p>\n

The specific workflow is as follows. First, a Gaussian Splat or 3D model is generated from the original image using tools such as Tripo Splat, Trellis2, or Pixal3D. Next, the model is imported into Blender, adjusted to the desired camera angle, and rendered. Finally, this rendered image and the original image are provided to Qwen Image 2.1 with the AnyAngle LoRA applied, along with the instruction prompt “Change the camera angle from to .”, to achieve the target angle.<\/p>\n

Specifications<\/h2>\n