目录
run_and_display->ptp_utils.text2image_ldm_stable->diffusion_step->controller.step_callback->AttentionControlEdit.local_blend->class LocalBlend
run_and_display
run_and_display(prompts, controller, latent=None, run_baseline=False, generator=None)
ptp_utils.text2image_ldm_stable
进行整个扩散的过程
def text2image_ldm_stable(
model,
prompt: List[str],
controller,
num_inference_steps: int = 50,
guidance_scale: float = 7.5,
generator: Optional[torch.Generator] = None,
latent: Optional[torch.FloatTensor] = None,
low_resource: bool = False,
):
ptp_utils.register_attention_control
ptp_utils.diffusion_step
单步扩散
diffusion_step(model, controller, latents, context, t, guidance_scale, low_resource=False)
controller.step_callback
step_callback(self, x_t)
AttentionControlEdit.local_blend
__call__(self, x_t, attention_store)