model based on https://civitai.com/models/108124/realisticmechv1
converted to use it with animatediff with diffusers on hugging face
A code sample :
import torch from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter from diffusers.utils import export_to_gif
Load the motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
Load SD 1.5 based finetuned model
model_id = "zecloud/mechas" pipe = AnimateDiffPipeline.from_pretrained( model_id, motion_adapter=adapter, torch_dtype=torch.float16 ) scheduler = DDIMScheduler.from_pretrained( model_id, subfolder="scheduler", clip_sample=False, timestep_spacing="linspace", beta_schedule="linear", steps_offset=1, ) pipe.scheduler = scheduler
Enable memory savings
pipe.enable_vae_slicing() pipe.enable_model_cpu_offload()
Define the input prompts and generate the output
output = pipe( prompt=( "half body portrait of man smiling with a mysterious gaze, mecha, science_fiction, city, realistic,mecha, " "a futuristic eiffel tower in the background " ), negative_prompt=( "(worst quality, low quality:1.4), (bad_prompt_version2:0.8), EasyNegative, badhandv4, text, name, letters, " "watermark, two tower" ), num_frames=16, guidance_scale=7.0, num_inference_steps=32, generator=torch.Generator("cpu").manual_seed(42), )
Extract frames and export to GIF
frames = output.frames[0] export_to_gif(frames, "animation.gif")
- Downloads last month
- -