Moss | Jima Style Lora

Base Model:Moss-Image-Base-bf16

I've uploaded three models with different levels of training. Personally, I recommend using the version with 3,500 steps, but you can adjust it yourself if you want to experiment. Content containing NSFW imagery may be subject to some censorship; you can use prompts to minimize this effect.

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

Krea 2 | Jima Style Lora

BASE Model:Krea 2 Raw

Training on ModelsSope

Anima |Jima Style Lora

base Model:Anima Base-v1

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