Moss | Coria Style Lora
Base Model:Moss-Image-Base-bf16
Generation settings
Works at resolutions between 512^2 and 1536^2 pixels.
No dmd 30-50 steps, CFG 3-5
+ dmd 8 steps, CFG 1
A variety of samplers work. Some of my favorites:
Euler + SGM
Euler + Simple
I recommend using Base + dmd2 distillation acceleration for inference; it tends to perform better than SFT, but this is just a suggestion—it depends on your personal preference.
Quoted from the official description; you may also refer to the parameter settings shown in the example image
Anima |Coria Style TLora
Base Model:Anima Base-v1
Lora is a type of Tlora; for specific differences, please refer to the Tlora GitHub repository.
Generation settings
Works at resolutions between 512^2 and 1536^2 pixels.
30-50 steps, CFG 4-6.
A variety of samplers work. Some of my favorites:
er_sde: neutral style, flat colors, sharp lines. I use this as a reasonable default.
euler_a: Softer, thinner lines. Can sometimes tend towards a 2.5D look. CFG can be pushed a bit higher than other samplers without burning the image.
dpmpp_2m_sde_gpu: similar in style to er_sde but can produce more variety and be more "creative". Depending on the prompt it can get too wild sometimes.
If going for a more realistic / painterly look, the beta57 scheduler (ComfyUI RES4LYF custom node pack) can help make better textures, since it puts more emphasis on low-noise timesteps.
Quoted from the official description; you may also refer to the parameter settings shown in the example image