( Not my Model )

https://civitai.red/models/2826451/kroma?modelVersionId=3188846

Lodestone Rock's new Chroma-based LORA for Krea 2

lodestones (rock)

Their models have a very passionate fanbase of users who generate various flavors of NSFW content and are familiar with Booru style image tags. There is limited info on the model, early feedback is that is works well to unlock NSFW content and seems to improve prompt adherence. There does seem to be some early indications that it does in fact understand Booru tags.

Kroma v0.1 — LoRA for Krea 2

Kroma is a LoRA fine-tune for Krea 2 , packaged as a single ComfyUI-compatible safetensors file. It was rank reduced down to rank 256 / alpha 256 and also carries the fully-fine-tuned normalization and modulation tensors as weight deltas, so it reproduces the original fine-tuned behaviour when loaded on top of the base model.

• File: kroma-v0.1.safetensors (~1.88 GB)

• Type: LoRA (264 adapters) + .diff weight deltas (159 RMSNorm / modulation tensors)

• License: MIT

Note on the format: unlike a "pure" LoRA, this file also includes full-weight deltas for the trained RMSNorm scales and modulation tensors (stored as .diff ). ComfyUI's LoraLoader applies these automatically, so no special handling is needed.

Tips

• Start with strength 1.0 ; lower it (e.g. 0.7–0.9) if you want a subtler effect.

• If the output looks off, confirm the text encoder is loaded with type krea2 (Krea 2 expects a 12-layer Qwen3-VL stack) and that you're on a current ComfyUI.

Conversion / provenance

This LoRA was produced from a K2 (Krea 2) fine-tune checkpoint and converted into the ComfyUI format: LoRA adapters use the native diffusion_model.* key naming, and the fully-fine-tuned RMSNorm / modulation tensors are stored as .diff deltas against the base model. Both are applied by ComfyUI's standard LoraLoader .

License

MIT — see LICENSE . Note that the base Krea 2 model is governed by its own license; this LoRA does not grant any rights to the base weights.