From 15d6fd8137d1b0e3f674c41735ff9d19769a7d2b Mon Sep 17 00:00:00 2001 From: Leojc Date: Wed, 27 Aug 2025 15:27:28 +0800 Subject: [PATCH] Fix typos (#298) --- comfyui/wan2_2/nodes.py | 4 ++-- comfyui/wan2_2_fun/nodes.py | 4 ++-- examples/cogvideox_fun/app.py | 2 +- examples/cogvideox_fun/launch_api.py | 2 +- examples/cogvideox_fun/predict_i2v.py | 6 +++--- examples/cogvideox_fun/predict_t2v.py | 6 +++--- examples/cogvideox_fun/predict_v2v.py | 6 +++--- examples/cogvideox_fun/predict_v2v_control.py | 6 +++--- examples/phantom/predict_s2v.py | 8 ++++---- examples/wan2.1/app.py | 2 +- examples/wan2.1/launch_api.py | 2 +- examples/wan2.1/predict_i2v.py | 8 ++++---- examples/wan2.1/predict_t2v.py | 8 ++++---- examples/wan2.1_fun/app.py | 2 +- examples/wan2.1_fun/launch_api.py | 2 +- examples/wan2.1_fun/predict_i2v.py | 8 ++++---- examples/wan2.1_fun/predict_t2v.py | 8 ++++---- examples/wan2.1_fun/predict_v2v_control.py | 8 ++++---- examples/wan2.1_fun/predict_v2v_control_camera.py | 8 ++++---- examples/wan2.1_fun/predict_v2v_control_ref.py | 8 ++++---- examples/wan2.2/app.py | 2 +- examples/wan2.2/launch_api.py | 2 +- examples/wan2.2/predict_i2v.py | 12 ++++++------ examples/wan2.2/predict_t2v.py | 12 ++++++------ examples/wan2.2/predict_ti2v.py | 12 ++++++------ examples/wan2.2_fun/app.py | 2 +- examples/wan2.2_fun/launch_api.py | 2 +- examples/wan2.2_fun/predict_i2v.py | 12 ++++++------ examples/wan2.2_fun/predict_i2v_5b.py | 12 ++++++------ examples/wan2.2_fun/predict_t2v.py | 12 ++++++------ examples/wan2.2_fun/predict_t2v_5b.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control_5b.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control_camera.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control_camera_5b.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control_ref.py | 12 ++++++------ examples/wan2.2_fun/predict_v2v_control_ref_5b.py | 12 ++++++------ scripts/wan2.2/train.py | 4 ++-- scripts/wan2.2/train_lora.py | 4 ++-- videox_fun/ui/wan2_2_fun_ui.py | 10 +++++----- videox_fun/ui/wan2_2_ui.py | 10 +++++----- videox_fun/ui/wan_fun_ui.py | 6 +++--- videox_fun/ui/wan_ui.py | 6 +++--- 43 files changed, 156 insertions(+), 156 deletions(-) diff --git a/comfyui/wan2_2/nodes.py b/comfyui/wan2_2/nodes.py index 7de8831..291e744 100755 --- a/comfyui/wan2_2/nodes.py +++ b/comfyui/wan2_2/nodes.py @@ -134,11 +134,11 @@ class LoadWan2_2Model: raise ValueError("Please download Fun model") # Get Vae - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - vae = Choosen_AutoencoderKL.from_pretrained( + vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) diff --git a/comfyui/wan2_2_fun/nodes.py b/comfyui/wan2_2_fun/nodes.py index 1c1e605..9b36ccf 100755 --- a/comfyui/wan2_2_fun/nodes.py +++ b/comfyui/wan2_2_fun/nodes.py @@ -134,11 +134,11 @@ class LoadWan2_2FunModel: print(f"- {os.path.join(eas_cache_dir, folder)}") raise ValueError("Please download Fun model") - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - vae = Choosen_AutoencoderKL.from_pretrained( + vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) diff --git a/examples/cogvideox_fun/app.py b/examples/cogvideox_fun/app.py index e520055..63463fb 100755 --- a/examples/cogvideox_fun/app.py +++ b/examples/cogvideox_fun/app.py @@ -22,7 +22,7 @@ if __name__ == "__main__": # "client" represents the client mode, offering a simple UI that sends requests to a remote API for generation. ui_mode = "normal" - # GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. + # GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory. diff --git a/examples/cogvideox_fun/launch_api.py b/examples/cogvideox_fun/launch_api.py index 5f74da9..067330c 100755 --- a/examples/cogvideox_fun/launch_api.py +++ b/examples/cogvideox_fun/launch_api.py @@ -22,7 +22,7 @@ def main(): parser.add_argument('--world_size', type=int, default=8, help='Number of parallel workers') parser.add_argument( '--gpu_memory_mode', type=str, default="model_cpu_offload", help=''' -GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. +GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. model_full_load means that the entire model will be moved to the GPU. model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, diff --git a/examples/cogvideox_fun/predict_i2v.py b/examples/cogvideox_fun/predict_i2v.py index 0020080..112fe02 100755 --- a/examples/cogvideox_fun/predict_i2v.py +++ b/examples/cogvideox_fun/predict_i2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.fp8_optimization import (convert_model_weight_to_float8, r from videox_fun.utils.lora_utils import merge_lora, unmerge_lora from videox_fun.utils.utils import get_image_to_video_latent, save_videos_grid -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -138,7 +138,7 @@ text_encoder = T5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Euler": EulerDiscreteScheduler, "Euler A": EulerAncestralDiscreteScheduler, "DPM++": DPMSolverMultistepScheduler, @@ -146,7 +146,7 @@ Choosen_Scheduler = scheduler_dict = { "DDIM_Cog": CogVideoXDDIMScheduler, "DDIM_Origin": DDIMScheduler, }[sampler_name] -scheduler = Choosen_Scheduler.from_pretrained( +scheduler = Chosen_Scheduler.from_pretrained( model_name, subfolder="scheduler" ) diff --git a/examples/cogvideox_fun/predict_t2v.py b/examples/cogvideox_fun/predict_t2v.py index c9030d3..5133955 100755 --- a/examples/cogvideox_fun/predict_t2v.py +++ b/examples/cogvideox_fun/predict_t2v.py @@ -26,7 +26,7 @@ from videox_fun.utils.lora_utils import merge_lora, unmerge_lora from videox_fun.utils.utils import get_image_to_video_latent, save_videos_grid from videox_fun.dist import set_multi_gpus_devices, shard_model -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -130,7 +130,7 @@ text_encoder = T5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Euler": EulerDiscreteScheduler, "Euler A": EulerAncestralDiscreteScheduler, "DPM++": DPMSolverMultistepScheduler, @@ -138,7 +138,7 @@ Choosen_Scheduler = scheduler_dict = { "DDIM_Cog": CogVideoXDDIMScheduler, "DDIM_Origin": DDIMScheduler, }[sampler_name] -scheduler = Choosen_Scheduler.from_pretrained( +scheduler = Chosen_Scheduler.from_pretrained( model_name, subfolder="scheduler" ) diff --git a/examples/cogvideox_fun/predict_v2v.py b/examples/cogvideox_fun/predict_v2v.py index 9dc1bde..b1d7a43 100755 --- a/examples/cogvideox_fun/predict_v2v.py +++ b/examples/cogvideox_fun/predict_v2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.fp8_optimization import (convert_model_weight_to_float8, r from videox_fun.utils.utils import get_video_to_video_latent, save_videos_grid from videox_fun.dist import set_multi_gpus_devices, shard_model -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -137,7 +137,7 @@ text_encoder = T5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Euler": EulerDiscreteScheduler, "Euler A": EulerAncestralDiscreteScheduler, "DPM++": DPMSolverMultistepScheduler, @@ -145,7 +145,7 @@ Choosen_Scheduler = scheduler_dict = { "DDIM_Cog": CogVideoXDDIMScheduler, "DDIM_Origin": DDIMScheduler, }[sampler_name] -scheduler = Choosen_Scheduler.from_pretrained( +scheduler = Chosen_Scheduler.from_pretrained( model_name, subfolder="scheduler" ) diff --git a/examples/cogvideox_fun/predict_v2v_control.py b/examples/cogvideox_fun/predict_v2v_control.py index 2f4380b..3668d3b 100755 --- a/examples/cogvideox_fun/predict_v2v_control.py +++ b/examples/cogvideox_fun/predict_v2v_control.py @@ -27,7 +27,7 @@ from videox_fun.utils.lora_utils import merge_lora, unmerge_lora from videox_fun.utils.utils import get_video_to_video_latent, save_videos_grid from videox_fun.dist import set_multi_gpus_devices, shard_model -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -133,7 +133,7 @@ text_encoder = T5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Euler": EulerDiscreteScheduler, "Euler A": EulerAncestralDiscreteScheduler, "DPM++": DPMSolverMultistepScheduler, @@ -141,7 +141,7 @@ Choosen_Scheduler = scheduler_dict = { "DDIM_Cog": CogVideoXDDIMScheduler, "DDIM_Origin": DDIMScheduler, }[sampler_name] -scheduler = Choosen_Scheduler.from_pretrained( +scheduler = Chosen_Scheduler.from_pretrained( model_name, subfolder="scheduler" ) diff --git a/examples/phantom/predict_s2v.py b/examples/phantom/predict_s2v.py index c01e142..d2cf201 100644 --- a/examples/phantom/predict_s2v.py +++ b/examples/phantom/predict_s2v.py @@ -30,7 +30,7 @@ from videox_fun.utils.utils import (filter_kwargs, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -180,15 +180,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1/app.py b/examples/wan2.1/app.py index a5634a2..aee89fb 100755 --- a/examples/wan2.1/app.py +++ b/examples/wan2.1/app.py @@ -22,7 +22,7 @@ if __name__ == "__main__": # "client" represents the client mode, offering a simple UI that sends requests to a remote API for generation. ui_mode = "normal" - # GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. + # GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory. diff --git a/examples/wan2.1/launch_api.py b/examples/wan2.1/launch_api.py index 73dac80..a9d8c43 100755 --- a/examples/wan2.1/launch_api.py +++ b/examples/wan2.1/launch_api.py @@ -22,7 +22,7 @@ def main(): parser.add_argument('--world_size', type=int, default=8, help='Number of parallel workers') parser.add_argument( '--gpu_memory_mode', type=str, default="model_cpu_offload", help=''' -GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. +GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. model_full_load means that the entire model will be moved to the GPU. model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, diff --git a/examples/wan2.1/predict_i2v.py b/examples/wan2.1/predict_i2v.py index befe23c..5345980 100755 --- a/examples/wan2.1/predict_i2v.py +++ b/examples/wan2.1/predict_i2v.py @@ -26,7 +26,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -177,15 +177,15 @@ clip_image_encoder = CLIPModel.from_pretrained( clip_image_encoder = clip_image_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1/predict_t2v.py b/examples/wan2.1/predict_t2v.py index 97acaac..26bd668 100755 --- a/examples/wan2.1/predict_t2v.py +++ b/examples/wan2.1/predict_t2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -165,15 +165,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1_fun/app.py b/examples/wan2.1_fun/app.py index 60de1a5..80b459d 100755 --- a/examples/wan2.1_fun/app.py +++ b/examples/wan2.1_fun/app.py @@ -22,7 +22,7 @@ if __name__ == "__main__": # "client" represents the client mode, offering a simple UI that sends requests to a remote API for generation. ui_mode = "normal" - # GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. + # GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory. diff --git a/examples/wan2.1_fun/launch_api.py b/examples/wan2.1_fun/launch_api.py index 1ee8847..2f90094 100755 --- a/examples/wan2.1_fun/launch_api.py +++ b/examples/wan2.1_fun/launch_api.py @@ -22,7 +22,7 @@ def main(): parser.add_argument('--world_size', type=int, default=8, help='Number of parallel workers') parser.add_argument( '--gpu_memory_mode', type=str, default="model_full_load", help=''' -GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. +GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. model_full_load means that the entire model will be moved to the GPU. model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, diff --git a/examples/wan2.1_fun/predict_i2v.py b/examples/wan2.1_fun/predict_i2v.py index 96a2f0d..52baeb5 100755 --- a/examples/wan2.1_fun/predict_i2v.py +++ b/examples/wan2.1_fun/predict_i2v.py @@ -26,7 +26,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -178,15 +178,15 @@ clip_image_encoder = CLIPModel.from_pretrained( clip_image_encoder = clip_image_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1_fun/predict_t2v.py b/examples/wan2.1_fun/predict_t2v.py index e49dac3..fb085fb 100755 --- a/examples/wan2.1_fun/predict_t2v.py +++ b/examples/wan2.1_fun/predict_t2v.py @@ -26,7 +26,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -177,15 +177,15 @@ else: clip_image_processor = None # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) if transformer.config.in_channels != vae.config.latent_channels: diff --git a/examples/wan2.1_fun/predict_v2v_control.py b/examples/wan2.1_fun/predict_v2v_control.py index 67ba5b5..6810cd6 100755 --- a/examples/wan2.1_fun/predict_v2v_control.py +++ b/examples/wan2.1_fun/predict_v2v_control.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -188,15 +188,15 @@ clip_image_encoder = CLIPModel.from_pretrained( clip_image_encoder = clip_image_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1_fun/predict_v2v_control_camera.py b/examples/wan2.1_fun/predict_v2v_control_camera.py index f8d8507..d66077b 100755 --- a/examples/wan2.1_fun/predict_v2v_control_camera.py +++ b/examples/wan2.1_fun/predict_v2v_control_camera.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, ge from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -188,15 +188,15 @@ clip_image_encoder = CLIPModel.from_pretrained( clip_image_encoder = clip_image_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.1_fun/predict_v2v_control_ref.py b/examples/wan2.1_fun/predict_v2v_control_ref.py index 8599274..5f01abc 100755 --- a/examples/wan2.1_fun/predict_v2v_control_ref.py +++ b/examples/wan2.1_fun/predict_v2v_control_ref.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, ge from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -188,15 +188,15 @@ clip_image_encoder = CLIPModel.from_pretrained( clip_image_encoder = clip_image_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2/app.py b/examples/wan2.2/app.py index 1fb0fd8..07f33bc 100644 --- a/examples/wan2.2/app.py +++ b/examples/wan2.2/app.py @@ -22,7 +22,7 @@ if __name__ == "__main__": # "client" represents the client mode, offering a simple UI that sends requests to a remote API for generation. ui_mode = "normal" - # GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. + # GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory. diff --git a/examples/wan2.2/launch_api.py b/examples/wan2.2/launch_api.py index 86a5ddf..c5d3005 100644 --- a/examples/wan2.2/launch_api.py +++ b/examples/wan2.2/launch_api.py @@ -22,7 +22,7 @@ def main(): parser.add_argument('--world_size', type=int, default=8, help='Number of parallel workers') parser.add_argument( '--gpu_memory_mode', type=str, default="model_full_load", help=''' -GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. +GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. model_full_load means that the entire model will be moved to the GPU. model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, diff --git a/examples/wan2.2/predict_i2v.py b/examples/wan2.2/predict_i2v.py index cb7bb52..7369e99 100644 --- a/examples/wan2.2/predict_i2v.py +++ b/examples/wan2.2/predict_i2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -162,11 +162,11 @@ if transformer_high_path is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -198,15 +198,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2/predict_t2v.py b/examples/wan2.2/predict_t2v.py index 578bbaa..a68c6e4 100755 --- a/examples/wan2.2/predict_t2v.py +++ b/examples/wan2.2/predict_t2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -158,11 +158,11 @@ if transformer_high_path is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -193,15 +193,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2/predict_ti2v.py b/examples/wan2.2/predict_ti2v.py index 8d46563..548f599 100755 --- a/examples/wan2.2/predict_ti2v.py +++ b/examples/wan2.2/predict_ti2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -167,11 +167,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -202,15 +202,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( ) # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/app.py b/examples/wan2.2_fun/app.py index 1844be3..4091a88 100755 --- a/examples/wan2.2_fun/app.py +++ b/examples/wan2.2_fun/app.py @@ -22,7 +22,7 @@ if __name__ == "__main__": # "client" represents the client mode, offering a simple UI that sends requests to a remote API for generation. ui_mode = "normal" - # GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. + # GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory. diff --git a/examples/wan2.2_fun/launch_api.py b/examples/wan2.2_fun/launch_api.py index e1261dc..851be75 100755 --- a/examples/wan2.2_fun/launch_api.py +++ b/examples/wan2.2_fun/launch_api.py @@ -22,7 +22,7 @@ def main(): parser.add_argument('--world_size', type=int, default=8, help='Number of parallel workers') parser.add_argument( '--gpu_memory_mode', type=str, default="model_full_load", help=''' -GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. +GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8]. model_full_load means that the entire model will be moved to the GPU. model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, diff --git a/examples/wan2.2_fun/predict_i2v.py b/examples/wan2.2_fun/predict_i2v.py index 7ac02b1..0b1d037 100644 --- a/examples/wan2.2_fun/predict_i2v.py +++ b/examples/wan2.2_fun/predict_i2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -168,11 +168,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -204,15 +204,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_i2v_5b.py b/examples/wan2.2_fun/predict_i2v_5b.py index 62db9cc..3c5468f 100644 --- a/examples/wan2.2_fun/predict_i2v_5b.py +++ b/examples/wan2.2_fun/predict_i2v_5b.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -170,11 +170,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -206,15 +206,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_t2v.py b/examples/wan2.2_fun/predict_t2v.py index e119e26..8f17b96 100644 --- a/examples/wan2.2_fun/predict_t2v.py +++ b/examples/wan2.2_fun/predict_t2v.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -161,11 +161,11 @@ if transformer_high_path is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -197,15 +197,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_t2v_5b.py b/examples/wan2.2_fun/predict_t2v_5b.py index 9285640..9f501b3 100644 --- a/examples/wan2.2_fun/predict_t2v_5b.py +++ b/examples/wan2.2_fun/predict_t2v_5b.py @@ -25,7 +25,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_to_video_latent, from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -164,11 +164,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -200,15 +200,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control.py b/examples/wan2.2_fun/predict_v2v_control.py index b7a5dd1..39ed056 100644 --- a/examples/wan2.2_fun/predict_v2v_control.py +++ b/examples/wan2.2_fun/predict_v2v_control.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control_5b.py b/examples/wan2.2_fun/predict_v2v_control_5b.py index 1fc353e..a7ebb5e 100644 --- a/examples/wan2.2_fun/predict_v2v_control_5b.py +++ b/examples/wan2.2_fun/predict_v2v_control_5b.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control_camera.py b/examples/wan2.2_fun/predict_v2v_control_camera.py index 3b0e2e7..eeb6ee1 100644 --- a/examples/wan2.2_fun/predict_v2v_control_camera.py +++ b/examples/wan2.2_fun/predict_v2v_control_camera.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control_camera_5b.py b/examples/wan2.2_fun/predict_v2v_control_camera_5b.py index 82d5a6e..d0b9fbb 100644 --- a/examples/wan2.2_fun/predict_v2v_control_camera_5b.py +++ b/examples/wan2.2_fun/predict_v2v_control_camera_5b.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control_ref.py b/examples/wan2.2_fun/predict_v2v_control_ref.py index b201673..f5bb16c 100644 --- a/examples/wan2.2_fun/predict_v2v_control_ref.py +++ b/examples/wan2.2_fun/predict_v2v_control_ref.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/examples/wan2.2_fun/predict_v2v_control_ref_5b.py b/examples/wan2.2_fun/predict_v2v_control_ref_5b.py index 38f35a2..c4c2b70 100644 --- a/examples/wan2.2_fun/predict_v2v_control_ref_5b.py +++ b/examples/wan2.2_fun/predict_v2v_control_ref_5b.py @@ -29,7 +29,7 @@ from videox_fun.utils.utils import (filter_kwargs, get_image_latent, get_image_t from videox_fun.utils.fm_solvers import FlowDPMSolverMultistepScheduler from videox_fun.utils.fm_solvers_unipc import FlowUniPCMultistepScheduler -# GPU memory mode, which can be choosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. +# GPU memory mode, which can be chosen in [model_full_load, model_cpu_offload_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, sequential_cpu_offload]. # model_full_load means that the entire model will be moved to the GPU. # # model_full_load_and_qfloat8 means that the entire model will be moved to the GPU, @@ -181,11 +181,11 @@ if transformer_2 is not None: print(f"missing keys: {len(m)}, unexpected keys: {len(u)}") # Get Vae -Choosen_AutoencoderKL = { +Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] -vae = Choosen_AutoencoderKL.from_pretrained( +vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(model_name, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ).to(weight_dtype) @@ -217,15 +217,15 @@ text_encoder = WanT5EncoderModel.from_pretrained( text_encoder = text_encoder.eval() # Get Scheduler -Choosen_Scheduler = scheduler_dict = { +Chosen_Scheduler = scheduler_dict = { "Flow": FlowMatchEulerDiscreteScheduler, "Flow_Unipc": FlowUniPCMultistepScheduler, "Flow_DPM++": FlowDPMSolverMultistepScheduler, }[sampler_name] if sampler_name == "Flow_Unipc" or sampler_name == "Flow_DPM++": config['scheduler_kwargs']['shift'] = 1 -scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) +scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(config['scheduler_kwargs'])) ) # Get Pipeline diff --git a/scripts/wan2.2/train.py b/scripts/wan2.2/train.py index bc8c1f4..b1d8b1c 100644 --- a/scripts/wan2.2/train.py +++ b/scripts/wan2.2/train.py @@ -892,11 +892,11 @@ def main(): ) text_encoder = text_encoder.eval() # Get Vae - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - vae = Choosen_AutoencoderKL.from_pretrained( + vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(args.pretrained_model_name_or_path, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ) diff --git a/scripts/wan2.2/train_lora.py b/scripts/wan2.2/train_lora.py index 1950453..6fac6fc 100755 --- a/scripts/wan2.2/train_lora.py +++ b/scripts/wan2.2/train_lora.py @@ -891,11 +891,11 @@ def main(): ) text_encoder = text_encoder.eval() # Get Vae - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - vae = Choosen_AutoencoderKL.from_pretrained( + vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(args.pretrained_model_name_or_path, config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(config['vae_kwargs']), ) diff --git a/videox_fun/ui/wan2_2_fun_ui.py b/videox_fun/ui/wan2_2_fun_ui.py index f526e33..0e4a07a 100644 --- a/videox_fun/ui/wan2_2_fun_ui.py +++ b/videox_fun/ui/wan2_2_fun_ui.py @@ -47,11 +47,11 @@ class Wan2_2_Fun_Controller(Fun_Controller): self.diffusion_transformer_dropdown = diffusion_transformer_dropdown if diffusion_transformer_dropdown == "none": return gr.update() - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[self.config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - self.vae = Choosen_AutoencoderKL.from_pretrained( + self.vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(diffusion_transformer_dropdown, self.config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(self.config['vae_kwargs']), ).to(self.weight_dtype) @@ -87,9 +87,9 @@ class Wan2_2_Fun_Controller(Fun_Controller): ) self.text_encoder = self.text_encoder.eval() - Choosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] - self.scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) + Chosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] + self.scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) ) # Get pipeline diff --git a/videox_fun/ui/wan2_2_ui.py b/videox_fun/ui/wan2_2_ui.py index 46f8244..4fcf81c 100644 --- a/videox_fun/ui/wan2_2_ui.py +++ b/videox_fun/ui/wan2_2_ui.py @@ -46,11 +46,11 @@ class Wan2_2_Controller(Fun_Controller): self.diffusion_transformer_dropdown = diffusion_transformer_dropdown if diffusion_transformer_dropdown == "none": return gr.update() - Choosen_AutoencoderKL = { + Chosen_AutoencoderKL = { "AutoencoderKLWan": AutoencoderKLWan, "AutoencoderKLWan3_8": AutoencoderKLWan3_8 }[self.config['vae_kwargs'].get('vae_type', 'AutoencoderKLWan')] - self.vae = Choosen_AutoencoderKL.from_pretrained( + self.vae = Chosen_AutoencoderKL.from_pretrained( os.path.join(diffusion_transformer_dropdown, self.config['vae_kwargs'].get('vae_subpath', 'vae')), additional_kwargs=OmegaConf.to_container(self.config['vae_kwargs']), ).to(self.weight_dtype) @@ -86,9 +86,9 @@ class Wan2_2_Controller(Fun_Controller): ) self.text_encoder = self.text_encoder.eval() - Choosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] - self.scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) + Chosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] + self.scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) ) # Get pipeline diff --git a/videox_fun/ui/wan_fun_ui.py b/videox_fun/ui/wan_fun_ui.py index 19b4043..315bde8 100755 --- a/videox_fun/ui/wan_fun_ui.py +++ b/videox_fun/ui/wan_fun_ui.py @@ -83,9 +83,9 @@ class Wan_Fun_Controller(Fun_Controller): else: self.clip_image_encoder = None - Choosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] - self.scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) + Chosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] + self.scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) ) # Get pipeline diff --git a/videox_fun/ui/wan_ui.py b/videox_fun/ui/wan_ui.py index 858c5d3..5e1e89d 100755 --- a/videox_fun/ui/wan_ui.py +++ b/videox_fun/ui/wan_ui.py @@ -82,9 +82,9 @@ class Wan_Controller(Fun_Controller): else: self.clip_image_encoder = None - Choosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] - self.scheduler = Choosen_Scheduler( - **filter_kwargs(Choosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) + Chosen_Scheduler = self.scheduler_dict[list(self.scheduler_dict.keys())[0]] + self.scheduler = Chosen_Scheduler( + **filter_kwargs(Chosen_Scheduler, OmegaConf.to_container(self.config['scheduler_kwargs'])) ) # Get pipeline