A LoHa adapter for MOSS-Image-Base (Comfy-Org), trained to improve generation at 4 MP and higher resolutions. Trained on a mix of probably too much anime and photographs 3.5MP to 10MP.

9MP examples

LoRA v0.3

LoRA v0.3

LoRA v0.2

LoRA v0.2

LoRA v0.1

LoRA v0.1

No LoRA

No LoRA

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for comfyanonymous/MOSS_image_MAX_ULTRA_hires_lora_test

Adapter
(1)
this model

Space using comfyanonymous/MOSS_image_MAX_ULTRA_hires_lora_test 1