reclaimer (lol): I have found that if you get void (empty) outputs with the unquantized 1.4b and the 7b with your gpu, use ModelComputeDtype fp32 before KSampler

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 dummy9996/seedvr2_1.4B_3b_7b_int4_w4a8_comfyui