if_m.py

#!/usr/bin/env python3
from diffusers import DiffusionPipeline
from diffusers.utils import pt_to_pil
import torch

# stage 1
stage_1 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_xformers_memory_efficient_attention()  # remove line if torch.__version__ >= 2.0.0
stage_1.enable_model_cpu_offload()

# stage 2
stage_2 = DiffusionPipeline.from_pretrained(
    "DeepFloyd/IF-II-M-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_xformers_memory_efficient_attention()  # remove line if torch.__version__ >= 2.0.0
stage_2.enable_model_cpu_offload()

# stage 3
safety_modules = {"feature_extractor": stage_1.feature_extractor, "safety_checker": stage_1.safety_checker, "watermarker": stage_1.watermarker}
stage_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16)
stage_3.enable_xformers_memory_efficient_attention()  # remove line if torch.__version__ >= 2.0.0
stage_3.enable_model_cpu_offload()

prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'

# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)

generator = torch.manual_seed(0)

image = stage_1(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt").images
pt_to_pil(image)[0].save("./if_stage_I.png")

image = stage_2(
    image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt"
).images
pt_to_pil(image)[0].save("./if_stage_II.png")

image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
image[0].save("./if_stage_III.png")