Hamaru/MJV4_Hypernetwork

1---2license: creativeml-openrail-m3---4Hypernetwork trained on some Midjourney V4 portraits.5 6Euler a and DPM++ samplers work best. CFG scale at 7 and low step count (<50) work well.7 8Prompts should include words like "portrait", "octane render" and "highly detailed" for best results.9Avoid using face restoration like GFPGAN or CodeFormer if possible