models/Chroma - Professional Photos - v2.0

Chroma - Professional Photos - v2.0

9/22/2025

5:43:37 PM

Related Keywords & Tags

anatomy correction,chroma,chroma - professional photos,image generation,lora,lora merging,photo,realistic,stable diffusion model,style,tijuanaslumlord,training efficiency,v2.0

Black and white close-up photograph of a mechanical chrome spine focusing on central gears with shallow depth of field and blurred background.

Close-up photograph of a forest floor covered in autumn leaves with a large yellow maple leaf in the center, displaying water droplets, surrounded by smaller brown and red leaves with pine needles and twigs in the background.

Underwater silhouette of a scuba diver in black wetsuit and flippers, floating vertically with sunlight filtering through water above.

Close-up of a fierce oni mask with white cracked skin, sharp black horns, and a menacing grin surrounded by flowing long white hair and soft pink cherry blossom petals.

A mysterious figure standing in a sunlit forest, covered in a tattered moss-covered dark brown cloth adorned with small white flowers, surrounded by bright yellow flowers in soft warm light.

Black and white image of a woman sitting in the rain with wet hair, backlit by a bright light that creates dramatic shadows and highlights on her face and textured clothing.

A mechanical humanoid figure with a rusted cybernetic skull featuring exposed gears, standing in a desolate post-apocalyptic industrial environment with smokestacks and polluted air.

Recommended Parameters

samplers

DPM++ 2M_sgm_uniform

steps

cfg

3.5

clip skip

vae

ae_flux.safetensors

other models

Chroma_Flux1_S_Base\Chroma1-HD.safetensors (d446d9695d)

Tips

Keep the LoRA strength low (around 0.7) for people or animal related images to avoid anatomy issues.

Merging smaller lora batches into one checkpoint leads to faster training and easier convergence judgement.

Chroma alone is capable but combining with this model balances common training errors.

Version Highlights

Different approach and more pictures.

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...

Contributor

TijuanaSlumlord

Long time digital, 3D and traditional artist - Venturing into AI for shenanigans, weird things and inspiration. Mostly for shenanigans. I'll try everything, from cute and funny to deeply disturbing and dark across all styles.

Digital Abstraction by ChronoKnight - [FLUX] - v1.0

Qwen-Image - Qwen_Image_fp8_e4m3fn

Use this model