V.4.0
*insert long-winded description here* Also, pineapples are now oversized resins or whatever those things are, bad economy.
V.3.0
By far the most convoluted training i have ever done. From to artificial to low resolution to illustration ( don't even know how that happened ) and the list goes on.
Everything that matters is that i have my little toy to offset my other loras if they don't behave.
The only thing that is still open are more nature photos, landscapes and most important stupid loras.
More time to play with other peoples models.
V2.0
A slightly different approach. Merged smaller lora batches into the checkpoint and extracted a lora from this. A lot better to manage, since with so many pictures and different themes it takes to long to convervege. With less pictures it's faster and easier to determine when it's enough training.
Very happy with the result. It takes the edge of pictures that in some cases still look to artificial or where it looks like a character got photoshopped in.
I would keep the strength low ( around 0.7 ish ) for anything people or animal related, because it can fuck up anatomy and chroma is good enough to handle the rest.
Even though Chroma is more than capable of producing this stuff by itself, needed to balance the fuckups i usually train and for combining loras with each other. Not finished yet, but will most likely pick it up in between to continue training till it converges, which by my calculation will take around 5 million years, roughly.
Kinda works with normal Flux models but reduced influence, at least in Comfy, no guarantee for your personal setup and version.
Trained on version HD rev 0.1
And still no category for Chroma...
Description
Oh boy
FAQ
Comments (8)
This is the only LoRA that remains as a requirement in all of my Chroma.v1-HD work. At only 0.35 strength, its night and day in the outcome of every single image generated. They become an amazing composed photograph.
Your v3 LoRA is really really good.
Amazing LoRa. I have not tried v3 yet, but I use the previous version all the time - at very low strengh - to get a beautiful composition. Thanks!
what is the benefit of this lora over the lenovo lora, lenovo seems better at everything at first glance?
It does pretty much what it says: professional photography. I personnaly use it at very low strenght (~0.3) just for the composition and the unique coloring. Look at the galleries, Lenovo is more about photorealism than photography. So if you are just looking for realism with good looking iphone-type photo, you can stick with Lenovo; if you are looking for something more professionnal, this one is better IMO.
I’m a little late to this comment, but anyway…
I think there’s a noticeable difference between these two LoRAs. Lenovo gives more of a “boring reality” vibe, like amateur phone photos (Lenovo).
Professional Photos, on the other hand, delivers a more polished, studio-like look
They’re both great, just meant for different purposes. There’s no point comparing them directly, just use whichever one fits your case.
By the way, this is a great LoRA. Thanks for sharing it!
Most LoRAs with this level of quality are usually paywalled.
@Jorot Paywalled ... kinda sad. Maybe understandable if that is someone's only income or to offset electricity costs, but considering where most of the training images come from, not even adding self made stuff like photos or artwork, dunno. ( talking about real money, not the monopoly one from this side )
Another thing. Just as a side note, since 2 people sorta answered for me. OP's "question" isn't a question, so there is nothing to answer. The only thing i could do is to make a comparison between both models, which i can't and sure as hell won't do, makes no sense other to make my Lora look better. What i would gain by doing that is beyond me.
@TijuanaSlumlord I agree with you on both points. Either way, thanks again for your contribution. Keep up the great work👍
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.