v3.0 updatePlease use v3.0 with v3.3g workflow<a target="_blank" rel="ugc" href="https://civarchive.com/models/933018/workflows-flux-in-context-lora-for-product-design">https://civarchive.com/models/933018/</a>v2.0 updateBetter 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 treeOutput 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 gardonAs newly discoved in context lora usage of Flux.<a target="_blank" rel="ugc" href="https://ali-vilab.github.io/In-Context-LoRA-Page/">https://ali-vilab.github.io/In-Context-LoRA-Page/</a>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:<a target="_blank" rel="ugc" href="https://civarchive.com/models/933018/workflows-flux-in-context-lora-for-product-design">https://civarchive.com/models/933018/workflows-flux-in-context-lora-for-product-design</a>Feel free to dm me if you have any query.Contact: <a target="_blank" rel="ugc" href="mailto:lrzjason@gmail.com">lrzjason@gmail.com</a>QQ Group: 866612947

Flux Product Design v3.0 IC_CONSIS - In Context Lora

This version targeted to enhanced the consistency of input image.Focused on recovered details from input image.

Files with SHA256: d2b3ce84e5e8b571200a2f8b256365126907502164ff390ae6264e32bbdee030