Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Made from handpicked 40 images to get the best results of texture and face.
Model source
Source description
Made from handpicked 40 images to get the best results of texture and face.
I recommend using v1 for softer look, v2 is good for upscaling or yottea's chromatic abberation.
Trigger words makes lora much stronger. Only use @96yottea if you need artist tag activated and need more UMPH in image.
Recommended settings:
Sampler:
er_sde
euler
dpmpp_sde_gpu
Scheduler:
Sources
1 sourceModel artifacts
1 artifact7ef90aea-0239-4692-a844-51748b965deb.TA_trained.safetensors
safetensors · BF16 · 448 MB · SHA-256 8f41f6890f1f…9b64 · Civitai
DownloadSource excerpts
1 excerptSource context: 486 downloads · Type LORA · Base model Krea 2
beta - for more drawn style
linear_quadratic - for more softened, 3d look
Sampling steps: 25-40
CFG: 4-5
Lora Strength: 0.6-0.8
