B-LORA sliced twice, Content (composition) and Style. I was bored AF and cooked some ComfyUI workflow, which has proven to be extremely efficient and flexible. I think there is no better way for style transfer. Separate Lora load for composition and style, samplers latents decoding vae and straight into IPAdapter Style &amp; Composition SDXL, than sampling and (only if you megalomaniac like me) applying third Lora, which is trained separately with Dreambooth method (trigger + class). I will share ComfyUI workflow, make sure you know how to rename clip vision and ip adapter models, cause i use Unified loader for IP adapter. Ofcourse, each model can be used separately and independently.All captions used for training + comfyUI workflows here: <a target="_blank" rel="ugc" href="https://drive.google.com/drive/folders/1FFS4CnX3RI4B1yhzwqrlEwLd_QGpuYCZ?usp=sharing">https://drive.google.com/drive/folders/1FFS4CnX3RI4B1yhzwqrlEwLd_QGpuYCZ?usp=sharing</a>

B-LORA We Happy Few Content/Style

This is "enhancement" Style Slice. This model was trained separately, with Dreambooth method (trigger + class), no captions, no reg images. trigger word: wehappyfew style

Files with SHA256: d333bf9cd54b4717c24f476f3514b6f19708375fb1bdd1fe2e0b920364105a4c