How to use ehristoforu/stable-diffusion-v1-5-tiny with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ehristoforu/stable-diffusion-v1-5-tiny", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
This is the official model from RunwayML, only excess weights have been removed from it, the removal of which did not affect the generation results in any way.
Base model
Create short AI videos from text or first and last frames, with synchronized dialogue, effects, and ambience.
