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
Model trained on civitai with 20 images.
Recommended resources : Fluxmania
Recommended inference : dpmpp_2m or heunpp2 / sgm_uniform / 20 steps / guidance : 3.5
Weighting : around 0.75
FAQ
Comments (10)
What would you say is the difference against V1?
Arlequin version's dataset is more oriented toward a slightly blurred effect, with a much more pronounced color variety.
It would be best to compare this version with V1 to detect the differences.
@Adel_AI awesome,can you please upload to tensor art?
@alternative_Universe Sorry, I no longer update my account on Tensorart, this platform is rubbish, we spend all our time solving model copying and complaint issues.
@Adel_AI oh,I understand, anyway I hope you can soon work for chroma!
@alternative_Universe The models that interest me most besides Flux are Wan and Qwen
Can Renee Burri's lora come out, it's just hope :)
Maybe
how about a checkpoint for z iamge?
Currently, there are no ComfyUI nodes available for Z_Image_Turbo merges.
A useful LoRa library will also need to be built to integrate with the models.
This should be feasible in a month or more, I think.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.