Tag: . technique

  • Z-Image Prompt Assist

    Z-Image Prompt Assist

    Z-Image Prompt Assist

    Benchmark comparison chart of all aesthetics offered via “PASS” and how Z-IMAGE failed most of them.

    comfyui

    generative ai

    Comparison

    This is a comparison benchmark running Z-Image Turbo model testing the various Genre options found in my latest toll Prompt Assistant v1.1, affectionately nicknamed PASS.

    For the sake of testing purposes, I am using exactly the same prompt, same seed, the same sampler, same scheduler and same resolution of 824 x 1328 ( 1536 x 2048 would have been ideal ). The only change will be on the initial aesthetic value that will be note on each image caption.

    I hope this comparision can be somewhat useful to understand what genre means in generative art. You are invited to play around with the PASS tool and use to guide your future generations with JSon and Long string text outputs ready to be copied and pasted nto your workflow.

    Z-Image using Sampler DMPP_SDE + Scheduler BETA
    Z-Image using DMPP_SDE + BETA
    Z-Image using Sampler DMPP_SDE + Scheduler BETA
    Z-Image using EULER_ANCESTRAL + DDIM UNIFORM

    Prompt to be used

    				
    					Photorealistic, Bright / Airy aesthetic. Subject: A 40yr female Mixed Latino-European minimalist (wearing a matte grey suit without shirt underneath, long trousers and high-heels), pose: leaning on her car, intense gaze expression. Featuring: a Ferrari (yellow with pristine body conditions). Scene set in a skyscrapper rooftop in Dubai with soft diffused light. Technical: high angle, shot on Hasselblad medium format, 50mm lens.
    				
    			

    WHAT I LEARNED FROM THIS BENCHMARK

    Z-Image Turbo excels in beautiful photorealistic images of daily subjects as long it stays within a cinematic / editorial portraiture realm.

    When experimenting with more artistic and edgy prompts pushing the aesthetics far away from the common reality, Z-Image Turbo starts to fail and ignores these prompt instructions, as if it is addicted or trained only to a certain aesthetic only.

    Z-Image can not follow specific Aesthetic/Genre prompts.

    Z-IMAGE BEST SAMPLER + SCHEDULER RESULTS

    DDIM + DDIM_UNIFORM
    DMPP_SDE + BETA
    DMPP_SDE + KARRAS

    Sampler + scheduler comparison – all native combinations

    DDIM + SIMPLE
    DDIM + SGM_UNIFORM
    DDIM + KARRAS
    DDIM + EXPONENTIAL
    DDIM + BETA
    DDIM + NORMAL
    DDIM + DDIM_UNIFORM
    DDIM + LINEAR_QUADRATIC
    DDIM + KL_OPTIMAL
    EULER + SIMPLE
    EULER + SGM_UNIFORM
    EULER + KARRAS
    EULER + EXPONENTIAL
    EULER + BETA
    EULER + NORMAL
    EULER + DDIM_UNIFORM
    EULER + LINEAR_QUADRATIC
    EULER + KL_OPTIMAL
    EULER ANCESTRAL + SIMPLE
    EULER ANCESTRAL + SGM_UNIFORM
    EULER ANCESTRAL + KARRAS
    EULER ANCESTRAL + EXPONENTIAL
    EULER ANCESTRAL + BETA
    EULER ANCESTRAL + NORMAL
    EULER ANCESTRAL + DDIM_UNIFORM
    EULER ANCESTRAL + LINEAR_QUADRATIC
    EULER ANCESTRAL + KL_OPTIMAL
    DMPP_SDE + SIMPLE
    DMPP_SDE + SGM_UNIFORM
    DMPP_SDE + KARRAS
    DMPP_SDE + EXPONENTIAL
    DMPP_SDE + BETA
    DMPP_SDE + NORMAL
    DMPP_SDE + DDIM_UNIFORM
    DMPP_SDE + LINEAR_QUADRATIC
    DMPP_SDE + KL_OPTIMAL
    Bright / Airy
    Bright / Airy
    Moody
    Moody
    Dark
    Dark
    Soft / Dreamy
    Soft / Dreamy
    Ethereal
    Ethereal
    Analog / Film Grain
    Analog / Film Grain
    Vintage
    Vintage
    Retro
    Retro
    Nostalgic
    Nostalgic
    Vaporwave
    Vaporwave
    Synthwave
    Synthwave
    Cyberpunk
    Cyberpunk
    Futuristic
    Futuristic
    Dystopian
    Dystopian
    Utopian
    Utopian
    Minimalist
    Minimalist
    Maximalist
    Maximalist
    Clean
    Clean
    Grunge
    Grunge
    Gothic
    Gothic
    Luxury
    Luxury
    Cozy
    Cozy
    Street Style
    Street Style
    Whimsical
    Whimsical
    Surreal
    Surreal
    Psychedelic
    Psychedelic
    Glitch
    Glitch
    Y2K
    Y2K
    Dark Academia
    Dark Academia
    Light Academia
    Light Academia
    Neon
    Neon
    Pastel
    Pastel
    Monochrome
    Monochrome

    Just aesthetics is not enough

    The benchmark proved that by changing just the aesthetics value will cause no identifiable changes to the output result. Z-Image can not understand the aesthetic value on it’s own, rather you have to change completely one portion of the prompt to ensure the aesthetic is described in more words.

    Take a closer look on the next examples with comparison on aesthetics word value and whole portion prompt rewriting.

    Important note: Styles like surreal, glitch, dystopian and others similar that pushes a very specific appeal to the end result will absolutely not be considered by Z-Image rendering this model useless if your intent is anything other than Editorial / Street / Cinematic or Photorealistic.

    Neon
    Neon
    Neon + Extra prompting
    Neon + Extra prompting

    Final veridict

    By no means I am assuming that Z-Image Turbo has severe flaws, rather pin-pointing that this model seems to be built to attend a specific use: realism for editorial, cinematic and street photography featuring humans.

    Rendering objects can be complex for Z-Image and logos and specific parts details on objects can not be handled properly. For example: the vehicle is identifiable as a Ferrari but the logo, emblem and details on the wheels, handles and front lights are completely mishandled.

    Some of the details flaws can be rebuilt with upscaling techniques or even inpainting, thus, requiring an extra process to fix it.

plugins premium WordPress