import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kandinskylab/tiny-kandinsky-s2v-modular-pipe", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Tiny Kandinsky S2V 1.0 (random weights, for tests)
Randomly initialised, tiny versions of every Kandinsky S2V 1.0 component. It generates noise, not video: it exists only so the Diffusers modular pipeline tests can load a complete pipeline in seconds. For the real models see the Kandinsky S2V 1.0 collection.
- Downloads last month
- 168
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support