Photon mixed with LCM LoRA correct?

bold strategy... let's see if it works out. until then, i'll just add my own lcm

Hi.I tried your model yesterday and I like it. In AnimateDiff it generates quickly at 1024x576 resolution
Here's an example:
https://www.youtube.com/shorts/7EEmGHpAyFw

So, it's mixed with LCM lora already, we don't need to add LCM lora with this, bypass that guys or you will have very sharp images. I was not aware of this.. overall works great for 8 steps in animatediff. Thanks 😍

Good and very fast, thanks

wHAT ARE THE BEST EMBEDDINGS, LORAS AND MOTION lORAS FOR THIS CHECKPOINT, IN A VID2 VID WORKFLOW

[AnimateDiffEvo] - INFO - Loading motion module AnimateLCM_sd15_t2v.ckpt

[AnimateDiffEvo] - INFO - Loading motion LoRA pxlpshr_shatter_400.safetensors

!!! Exception during processing !!! Error while deserializing header: HeaderTooLarge

Traceback (most recent call last):

  File "/home/ubuntu/ai/ComfyUI/execution.py", line 317, in execute

    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)

                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/ubuntu/ai/ComfyUI/execution.py", line 192, in get_output_data

    return_values = mapnode_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)

                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/ubuntu/ai/ComfyUI/execution.py", line 169, in mapnode_over_list

    process_inputs(input_dict, i)

  File "/home/ubuntu/ai/ComfyUI/execution.py", line 158, in process_inputs

    results.append(getattr(obj, func)(**inputs))

                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/ubuntu/ai/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/nodes_gen1.py", line 146, in load_mm_and_inject_params

    motion_model = load_motion_module_gen1(model_name, model, motion_lora=motion_lora, motion_model_settings=motion_model_settings)

                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/ubuntu/ai/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_injection.py", line 1280, in load_motion_module_gen1

    load_motion_lora_as_patches(motion_model, lora)

  File "/home/ubuntu/ai/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_injection.py", line 1209, in load_motion_lora_as_patches

    state_dict = comfy.utils.load_torch_file(lora_path)

Personally I found this works best with faces more than bodies. It also adds a lot of focus which I haven't figured out how curtail the focus yet.

Works incredible on low light and greyscale images, takes a bit longer to get the result on these images but they turn out great with the tile controlnet.