v3.0 update

Please use v3.0 with v3.3g workflow

https://civarchive.com/models/933018/

v2.0 update

Better prompt following, Better consistency. Work greate with IC_TRY_ON lora:

Prompt Example:

Flux Template:

[SIDE_BY_SIDE], The image pair highlights a product sample to the well designed product advertisement; [SAMPLE_IMAGE] {Image1_desc}; [PRODUCT_IMAGE] {Image2_desc};

Input Image Description Refer to [IMAGE1]:

an illustration of a stylized tree with black branches and green leaves, adorned with pink flowers. A small bird is perched on one of the branches, and another bird is flying nearby. The background is white, and there is a simple depiction of grass at the base of the tree

Output Image Description Refer to [IMAGE2]:

In a serene dusk outdoor setting, a [SAMPLE_IMAGE] illustration printed on a t-shirt as a well designed product, fullbody shot of a whiteman wear the t shirt in a gardon

As newly discoved in context lora usage of Flux.

https://ali-vilab.github.io/In-Context-LoRA-Page/

We could use image as condition to generate similar output.

I introduce this workflow to simply remove the ic-lighting and inpainting models for product background editing.

This lora trained with very few images which is a weak guidance and weak generalization.

If it is usaful, please give me some buzz for further training.

Please use with the following workflow:

https://civarchive.com/models/933018/workflows-flux-in-context-lora-for-product-design

Feel free to dm me if you have any query.

Contact: [email protected]

QQ Group: 866612947