Sd3.5-Merged

SD3.5-Merged

This repository contains the merged version of Stable Diffusion 3.5, combining the best features from both the Large and Turbo variants.

Merge & Upload

To access the Stable Diffusion 3.5 models, one needs to fill the forms in the corresponding repositories, and then huggingface_cli login to let your system know who you are and whether you have access to the models!

from diffusers import SD3Transformer2DModel
from huggingface_hub import snapshot_download
from accelerate import init_empty_weights
from diffusers.models.model_loading_utils import load_model_dict_into_meta
import safetensors.torch
from huggingface_hub import upload_folder
import glob
import torch

large_model_id = "stabilityai/stable-diffusion-3.5-large"
turbo_model_id = "stabilityai/stable-diffusion-3.5-large-turbo"

with init_empty_weights():
    config = SD3Transformer2DModel.load_config(large_model_id, subfolder="transformer")
    model = SD3Transformer2DModel.from_config(config)

large_ckpt = snapshot_download(repo_id=large_model_id, allow_patterns="transformer/*")
turbo_ckpt = snapshot_download(repo_id=turbo_model_id, allow_patterns="transformer/*")

large_shards = sorted(glob.glob(f"{large_ckpt}/transformer/*.safetensors"))
turbo_shards = sorted(glob.glob(f"{turbo_ckpt}/transformer/*.safetensors"))

merged_state_dict = {}
guidance_state_dict = {}

for i in range(len((large_shards))):
    state_dict_large_temp = safetensors.torch.load_file(large_shards[i])
    state_dict_turbo_temp = safetensors.torch.load_file(turbo_shards[i])

    keys = list(state_dict_large_temp.keys())
    for k in keys:
        if "guidance" not in k:
            merged_state_dict[k] = (state_dict_large_temp.pop(k) + state_dict_turbo_temp.pop(k)) / 2
        else:
            guidance_state_dict[k] = state_dict_large_temp.pop(k)

    if len(state_dict_large_temp) > 0:
        raise ValueError(f"There should not be any residue but got: {list(state_dict_large_temp.keys())}.")
    if len(state_dict_turbo_temp) > 0:
        raise ValueError(f"There should not be any residue but got: {list(state_dict_turbo_temp.keys())}.")

merged_state_dict.update(guidance_state_dict)
load_model_dict_into_meta(model, merged_state_dict)

model.to(torch.bfloat16).save_pretrained("transformer")

upload_folder(
    repo_id="prithivMLmods/Sd3.5-Merged",
    folder_path="transformer",
    path_in_repo="transformer",
)

Inference

from diffusers import StableDiffusion3Pipeline
import torch

pipeline = StableDiffusion3Pipeline.from_pretrained(
    "prithivMLmods/Sd3.5-Merged", torch_dtype=torch.bfloat16
).to("cuda")

prompt = "a tiny astronaut hatching from an egg on the moon"
image = pipeline(
    prompt=prompt,
    guidance_scale=1.0,
    num_inference_steps=6,  # Run faster ⚡️
    generator=torch.manual_seed(0),
).images[0]
image.save("sd-3.5-merged.png")