<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6131a690-3699-4804-868e-d9b4f549d454/width=525/6131a690-3699-4804-868e-d9b4f549d454.jpeg" />GENOVA APEX is an experimental model.I created by merging my previous Gene Quantum model <a target="_blank" rel="ugc" href="https://civarchive.com/models/885573/flux-gene-beauty">https://civarchive.com/models/885573/flux-gene-beauty</a> with DEDISTILLED models and my own trained LoRAs. The process involved multiple stages and is purely an experiment to achieve high detail and realism similar to DEDISTILLED in just 8 generation steps(+ 8 generation steps Hires. Fix) .Version (UNet) – This version requires Flux VAE, Clip-L, and T5XXL to work effectively with the Flux development model.Recommended Settings for Optimal Generation<ul><li>Sampling Method and Schedule Type: Euler Beta</li><li>Sampling Steps: 8 steps</li><li>I use Hires. Fix because it provides significantly better results: 8 steps, upscale 1.2.</li><li>My configuration: RAM 64Gb, VRAM 16Gb</li><li>Workflow for ComfyUi: I use a straightforward workflow for image generation, available here: <a target="_new" rel="ugc" href="https://civarchive.com/models/670083/workflow-flux-photos-dev-version-12k-quantum-update">Flux Photos DEV Workflow</a><ul><li>HyperDetailer workflow FLUX PHOTOS DEV (HyperDetailer update) <a target="_blank" rel="ugc" href="https://civarchive.com/models/670083">https://civarchive.com/models/670083</a></li></ul>However, it requires a lot of memory because the process includes nodes for detail enhancement and upscaling, which also deliver the best results.</li><li>Please note that the quality on Forge may be lower than on ComfyUI. Here are the parameters I used: last update Forge, steps 8, euler beta, Distilled CFG Scale 3.5, CFG Scale 1 and I recommend use Hires.Fix Upscaler Latent or other be better, 8 steps, Upscale by 1,2 (higher upscale factors give better results but are slower and require more VRAM/RAM), Denoising strength 0,7, Distilled CFG Scale 3.5, CFG Scale 1 .</li><li>My Prompt Writing Assistant: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/7868/gpts-flux-photo-prompt-gen">https://civarchive.com/articles/7868/gpts-flux-photo-prompt-gen</a><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/187fc65c-4f6e-4d27-87f8-9b9af23a2589/width=525/187fc65c-4f6e-4d27-87f8-9b9af23a2589.jpeg" />P.S. The results I observe during the modeling process are even better than those I obtain from the final output of this process. Therefore, I continue experimenting, as the reason for this discrepancy has not yet been found...<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/abc23187-521c-45e0-98bd-17690364d97b/width=525/abc23187-521c-45e0-98bd-17690364d97b.jpeg" /></li></ul>

GENOVA APEX

This model is more accurate and has better results

Files with SHA256: 53c05abe8ac780db00959ad28d1836167097e0cda41e73ee65bfca0b5733dcff