Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein
Back
Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein
Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein
Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein
Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein
Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein

Klein 9B lcs consistency LoRA preview solves color shift and pixel offset Flux2 Klein

27.8K Views29 Likes171 Favorites
ACG design

小志Jason

小志Jason

ACG design

Model Information

Active
Model Type:
LoRA
Basic Model:
Flux2-Klein-9B
Resource Name:
models/loras/f2k_9B_lcs_consist_preview.safetensors
MD5:
6cec6a9e7b2d6bcefa1e6372fa882bbe

HF: https://huggingface.co/lrzjason/Consistance_Edit_Lora/tree/main

Civitai: https://civitai.com/models/1939453/model-versions/2771678

多功能普适性lora,可用于原分辨率高清,老照片修复,局部编辑



建议提示词:

{edit prompt}. Transform the image to realistic photograph. add realistic details to the corrupted image. restore high frequence details from the corrupted image.

建议强度:

0.5-0.7

Trained on 4B based. This lora aims to preserve image consistence across multiple input images. Control the lora via lora strength.

More strength means more consistence but it would also hurt edit abilities.

Different image might has different optimal lora strength.


HF: https://huggingface.co/lrzjason/Consistance_Edit_Lora/tree/main

Civitai: https://civitai.com/models/1939453/model-versions/2771678

多功能普适性lora,可用于原分辨率高清,老照片修复,局部编辑



建议提示词:

{edit prompt}. Transform the image to realistic photograph. add realistic details to the corrupted image. restore high frequence details from the corrupted image.

建议强度:

0.5-0.7

Trained on 4B based. This lora aims to preserve image consistence across multiple input images. Control the lora via lora strength.

More strength means more consistence but it would also hurt edit abilities.

Different image might has different optimal lora strength.