「liquid lemons」 🍋 📷
~ Recommended Settings & Training Parameters Below! ~
This is a Qwen-Image style lora trained on mid to late 90s and 2000s stock photography, the kind you would see in advertisements of the time and such. No trigger word is required but photography keywords (ex: "a photograph of... ...shallow depth of field, natural lighting...") can help the style come through. I trained this model on all real (no synthetic) data, and no human subjects were included to attempt to maximize compatibility with character/other loras. The effect is quite strong, so if you are using character loras it would be best to reduce the strength below 1.00 (around .40 to .50 is good). Please let me know what you think if you use it. :)
Recommended Settings
Strength ... 0.40 - 1.00
Steps ... 20 - 50 (or above)
CFG ... 3.0 - 5.0
Sampler/Scheduler ... any but res_2s/bong_tangent (RES4LYF) is good.
This model and Qwen in general does best with long detailed captions and high resolutions with a high step count (lower if you're using res_2s). Check the showcase for examples + ComfyUI workflow. Qwen is quite prompt dependent. If the style isn't coming through right away, try to reduce any keywords that might be fighting with the style. Tweak your prompt to help beat out the plastic Qwen look :)
Custom nodes I used in the workflow are:
Rgthree (https://github.com/rgthree/rgthree-comfy)
Optional: Post-processing nodes (https://github.com/EllangoK/ComfyUI-post-processing-nodes)
Training Parameters
Because I hate gatekeeping, in the spirit of open source goodness, here's what I used ~
Tool ... Diffusion-pipe
LR ... 0.0003
Dim or "Rank" ... 8
Steps ... 2??0
Epochs ... 80
Scheduler ... AdamW8Bit
134 total images, 1 repeats