Based on Anima Preview 2
Anima is a 2-billion parameter text-to-image model developed by CircleStone Labs in collaboration with Comfy Org. Built on the NVIDIA Cosmos architecture and utilizing the Qwen text encoder, it serves as a specialized foundation for high-end anime and artistic generation.
Model recipe
Merge of AnimaYume_v0.3 + AnimaCatTower_v0.4 + own trained LoRAs
Merging the models:
Merging the loras:
Workflows are embedded in the images.
Personal Recommended Settings
Steps: 25
CFG Scale: 5.0
Sampler:
euler_ancestralScheduler:
simple
Description
FAQ
Comments (5)
How do you merge Anima models?
I did it using ComfyUI. I created Lora using the Anima Standalone Trainer.
@litch264187 TY
@litch264187 what node or custom node do you use to merge it. Is it simple model merge node. I have tried DARE model merge But it didn't do anything I don't know that's because it's designed for SD 1.5 and SDXL. Great work 👍
@AnimaXx Hi, I've added images with details to the model's page description.