Panorama Lora
Back

Panorama Lora
11 1 5

Architectural

Panorama Lora

This model has been trained on 2:1 ratio (2048x1024) images.

Therefore, if you use this ratio as width and height, you may get good results.

However, the panorama viewer is very flexible in terms of resolution, and FLUX.1 seems to generalize well.

For example, gallery samples were generated at 1536×640 (approximately 21:9) because this is relatively fast (about 16 seconds on the HF inference API).


It generally works well for "normal" requests, but if the model is asked to create spherical distortions of uncommon content, locations, or angles, it may encounter difficulties.

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/7a3a12c1e8aa44f684834b2a9ca245e0?from=search&versionUuid=4d215f0b076f44369079456c03cf4438 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

老土

老土

Architectural

Model Information

Active
Original author：
精选模型托管处
Model Type：
LoRA
Basic Model：
F1基础 D
Trigger Words：
panoramic
Resource Name：
models/loras/F.1全景图_1.0.safetensors
MD5：
030d7e68db16e21998e7744bbabd25e0

This model has been trained on 2:1 ratio (2048x1024) images.

Therefore, if you use this ratio as width and height, you may get good results.

However, the panorama viewer is very flexible in terms of resolution, and FLUX.1 seems to generalize well.

For example, gallery samples were generated at 1536×640 (approximately 21:9) because this is relatively fast (about 16 seconds on the HF inference API).


It generally works well for "normal" requests, but if the model is asked to create spherical distortions of uncommon content, locations, or angles, it may encounter difficulties.

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/7a3a12c1e8aa44f684834b2a9ca245e0?from=search&versionUuid=4d215f0b076f44369079456c03cf4438 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request