File size: 1,839 Bytes
42fe352 ab5a77a 42fe352 ab5a77a 42fe352 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
---
pipeline_tag: text-to-video
---
AnimateDiff is a method that allows you to create videos using pre-existing Stable Diffusion Text to Image models.
Converted https://huggingface.co/guoyww/animatediff/blob/main/v3_sd15_mm.ckpt to Huggingface Diffusers format
using Diffuser's convetion script (available https://github.com/huggingface/diffusers/blob/main/scripts/convert_animatediff_motion_module_to_diffusers.py)
The following example demonstrates how you can utilize the motion modules with an existing Stable Diffusion text to image model.
```python
import torch
from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
from diffusers.utils import export_to_gif
# Load the motion adapter
adapter = MotionAdapter.from_pretrained("Warvito/animatediff-motion-adapter-v1-5-3")
# load SD 1.5 based finetuned model
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter)
scheduler = DDIMScheduler.from_pretrained(
model_id,
subfolder="scheduler",
beta_schedule="linear",
clip_sample=False,
timestep_spacing="linspace",
steps_offset=1
)
pipe.scheduler = scheduler
# enable memory savings
pipe.enable_vae_slicing()
pipe.enable_model_cpu_offload()
output = pipe(
prompt=(
"masterpiece, bestquality, highlydetailed, ultradetailed, sunset, "
"orange sky, warm lighting, fishing boats, ocean waves seagulls, "
"rippling water, wharf, silhouette, serene atmosphere, dusk, evening glow, "
"golden hour, coastal landscape, seaside scenery"
),
negative_prompt="bad quality, worse quality",
num_frames=16,
guidance_scale=7.5,
num_inference_steps=25,
generator=torch.Generator("cpu").manual_seed(42),
)
frames = output.frames[0]
export_to_gif(frames, "animation.gif")
```
|