Open Bilal143260 opened 8 months ago
yes, see instantid (using ip-adapter + controlnet)
Why is using ip-adapter+controlnet over adding more attention layers a better choice?
Why is using ip-adapter+controlnet over adding more attention layers a better choice?
I am not sure which is better, maybe should do some experiments
If I add more attention layers, what changes would I need to make in inference code?
yes, see instantid (using ip-adapter + controlnet)
- ip-adapter-face + controlnet-openpose 效果看着不太好,是需要重新finetune吗
` controlnet_model_path = "stablediffusion/lllyasviel/control_v11p_sd15_openpose"
controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained( base_model_path, controlnet=controlnet, torch_dtype=torch.float16, scheduler=noise_scheduler, vae=vae, feature_extractor=None, safety_checker=None ) `
Is it a good idea to add more attention layers for extra conditioning? Or adding controlnet with IP_adapter would the job better?