Yet another amateur photo LoRA to improve realism.
Z-Image V1:
A new version for Z-Image trained on a small dataset.
V4 Beta 2:
Trained on more images.
V4 Beta 1:
I have started to create a completely new dataset with only high quality images. For Beta 1 I used 111 images, though I plan to significantly increase it for Beta 2. All images only have the caption "43stet1c", but it isn't needed to mention it in your prompt.
This combination seems to produce the best and most consistent results so far.
Increase the strength if the effect isn't strong enough.
V3:
Same dataset as V2 but completely recaptioned with Claude 3.5 Sonnet and upscaled to 1024 with Gigapixel.
V2:
Trained on 124 images with no captions at all. Let me know if this works better than V1. Results can be inconsistent, use HiRes fix and Beta scheduler.
V1:
This was trained on a dataset of 61 "aesthetic" images captioned with Claude 3.5 Sonnet.
Description
Completely new dataset, captioned using only the word "43stet1c"
FAQ
Comments (7)
hi, trained on 512x512 or 1024x1024 images ?
1024
@powerpuff nice, training done on your computer ? cuz im trying to train in 1024 but can't fit it in 24go vram
@aip0pp Nope, I only use the Civit trainer.
@aip0pp try fluxgym, can do it with 12gb
@powerpuff Civitai trainer for Flux actually downscales your input images to 512 before training them.
So realistic model
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.