h4_Realistic

CHECKPOINT
Original - TenStar Fund


Updated:

No showcase images available, the model won't be visible to others.

35

My current Realism Model project.

Playing around with lighting and effects, trying to create a model that can run realistic

looking photographs , high quality high end photo shoots, and ridiculous fantasy elves and

all that good stuff.

Obviously the abilities of the model and the extent will depends and vary per version.

Currently Version 3 produces the best overall realistic images with minimal shine.

Version 2 and 2.5 some how ended up more NSFW than I intended.

Version 1 is unrestricted and a hot mess on the inside, can produce anything with varying

qualities across the board.

I've found that I use each version for a specific purpose, like when I have a crazy Idea, I'll typically goto V1 to test the idea and try to refine it through to v3

Version Detail

SD 1.5
1000
10
New model trained originally on 10k+ images, no resolution below 1024. Higher resolutions, higher quality images. No morphs or deformations in the images, I did my best to limit the low quality hands and faces as well. Merged several times with LoRA for hands, face and eyes. As such typically delivers good faces, hands are always a problem. Merged again with my own Model using learned Diff to "Update" my old model. Came out well. Definitely recommend running with a detailer, or a face fix if you're running full body shots

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.