No showcase images available, the model won't be visible to others.
Run38K
Version Detail
SD 1.5
What's a good start:
I typically start with a relatively small resolution (like 360x640, 512x640, 512x768 for txt2img) and use hires fix with latent upscaler at 0.4 denoising strength.
Then I also use ADetailer to get better faces with 0.2 denoising strength and 512x512 resolution.
There are probably better prompts than the following, but you can already get pretty good pictures with these (just replace {prompt} and {negative_prompt} by whatever you want to generate)
Recommended prompt:
{prompt}
(real-looking-skin) (real-looking-eyes-iris) ((video grainyfilm)) natural cinematic lighting
((amateur photo highly defined))
realistic, best quality, photo-realistic
8k, best quality, masterpiece, realistic, photo-realistic
Recommended negative prompt:
{negative_prompt}
(2D), (3D), ((camera)), ((cartoony)), (CGI), ((drawing)), ((hands)), ((legs)), ((lowres)), ((painting)), ((sketchy)), ((smartphone)), ((The Sims)), (ugly), ((blur))
(worst quality, low quality, normal quality:1.3), lowres
Project 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
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
Describe the image you want to generate, then press Enter to send.