This repository is a collection of Control LoRA models for Krea-2. Each model has its own control behavior, training data, and training configuration. More models, including lineart controls, may be added over time.
Loosely follows the overall silhouette, pose, and broad composition
Available
krea2-lineart
Lineart-guided generation
Planned
krea2-anythng
krea2-anythng is the model that loosely follows the input image's overall silhouette and broad composition. It leaves room for the prompt and Krea-2 to determine appearance and detail. It is not an exact edge-tracing or pixel-perfect structure model.
Krea2 Control Plus start_percent and end_percent setting example
These example images are provided by the comfyui-krea2-controlnetPlus repository.
Install the custom node according to its repository.
Put the safetensors file in ComfyUI's models/loras directory.
Prepare an image whose broad silhouette/composition should guide generation.
Encode it with Krea2 Control Plus Image Encode. For krea2-anythng, start with channel_mode=rgb, normalize=none, invert=false, and match_latent_size.
Load the model with Krea2 Control Plus LoRA Loader. Start with start_percent=0.0 and end_percent=1.0.
Attach the control latent with the required Krea2 Control Plus Apply node.
Send the resulting model to the normal Krea-2 sampler and use your text prompt.
The custom node repository provides example_workflows/Krea2Controlnet.json.
krea2-anythng training reference
This configuration applies specifically to krea2-anythng; future models in this repository may use different datasets and settings.
The model was first trained for 6,000 steps at a learning rate of 1e-4. Training was then resumed from the step-6,000 weights with a lower learning rate of 3e-5 and continued to step 7,000. The published file is the final step-7,000 checkpoint.
The 13B base was frozen. Training updated rank-64 LoRA weights across the 28 DiT blocks and the expanded input projection for the VAE-encoded control latent.
krea2-anythng limitations
Intended for rough whole-image silhouette, pose, and layout guidance.
Fine contours, faces, small objects, and exact spatial relationships may differ.
Prompt, seed, sampler, and control start/end percentages affect adherence.
Outputs inherit Krea-2's behavior and limitations.
Experimental; evaluate outputs before production use.
License and attribution
Use each checkpoint in accordance with the Krea-2 base model and inference software licenses and terms. Thanks to the Krea-2 ControlNet training implementation and ComfyUI Krea2 Control Plus integration.
