got prompt 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 2 model_type EPS adm 0 making attention of type 'vanilla-pytorch' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla-pytorch' with 512 in_channels missing {'cond_stage_model.logit_scale', 'cond_stage_model.text_projection'} left over keys: dict_keys(['cond_stage_model.transformer.text_model.embeddings.position_ids', 'model_ema.decay', 'model_ema.num_updates']) [AnimateDiffEvo] - [0;32mINFO[0m - Loading motion module mm_sd_v14.ckpt [AnimateDiffEvo] - [0;32mINFO[0m - Using fp16, converting motion module to fp16 loading new [AnimateDiffEvo] - [0;32mINFO[0m - Regular AnimateDiff activated - latents passed in (16) less or equal to context_length None. [AnimateDiffEvo] - [0;32mINFO[0m - Injecting motion module mm_sd_v14.ckpt version v1. loading new unload clone16 unload clone 15 unload clone 14 unload clone 13 unload clone 12 unload clone 11 unload clone 10 unload clone 9 unload clone 8 unload clone 7 unload clone 6 unload clone 5 unload clone 4 unload clone 3 unload clone 2 unload clone 1 0%| | 0/20 [00:00