NOTE : Base model category: ZImageTurbo & Flux1.
Showcase images were created with ComfyUI and are in PNG, include metadata & workflow.
VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption
Description
Steps : 8
Sampler/Scheduler : Seed_3 / Normal --- ipndm / Normal ---- heunpp2 / linear_quadratic or beta
Weighting : 0.75
FAQ
Comments (6)
You outdid yourself here. This purchase was worth it.
Thanks for your feedback
Love this style! makes z-turbo look better than flux :-)
I'm having a tough time placing a character behind an object like a countertop or a desk while this lora is enabled. If I disabled it, the prompt is followed correctly, but when enabled, the character stands in front of the object. (ZIT). I was wondering if you had any suggestions. Using a depth controlnet doesn't seem to help it either.
Use the image obtained without LoRA for noise injection (I2I) instead of using Empty Latent. Normally, by setting the denoising between 0.75 and 0.85, you should get an image that matches the prompt. Vary the seed with a slight modification of the prompt each time (use a VL model, for example).
@Adel_AI thank you sensei. Even with these excellent suggestions I still fight with it. But I will keep trying. Thank you for the response and the suggestions!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.