Flux.1-Krea-Merged-Schnell (FLUX.1-schnell + FLUX.1-Krea-dev)

The Flux.1-Krea-Merged-Schnell repository features merged parameters that combine two leading image generation models: black-forest-labs/FLUX.1-schnell, renowned for its ultra-fast, precision prompt following and efficient 1–4 step professional image production, and black-forest-labs/FLUX.1-Krea-dev, celebrated for guidance-distilled training, aesthetic curation, and photorealistic output. The resulting unified model empowers users to generate visually striking, high-quality images at remarkable speed, balancing sharp style consistency and realism with creative flexibility, and is fully compatible with the Diffusers library’s FluxPipeline for streamlined, accessible text-to-image workflows in both research and creative settings.

prompt : a tiny astronaut hatching from an egg on mars

---

prompt : a tiny astronaut hatching from an egg on the moon

---

Sub-Memory-efficient merging code (FLUX.1-schnell + FLUX.1-Krea-dev)

Installing Required Packages

%%capture
!pip install git+https://github.com/huggingface/transformers.git
!pip install git+https://github.com/huggingface/diffusers.git
!pip install git+https://github.com/huggingface/peft.git
!pip install git+https://github.com/huggingface/accelerate.git
!pip install safetensors huggingface_hub hf_xet

hf-login

from huggingface_hub import notebook_login, HfApi
notebook_login()

merge.py

from diffusers import FluxTransformer2DModel
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
import glob
import torch

# Initialize model with empty weights
with init_empty_weights():
 config = FluxTransformer2DModel.load_config("black-forest-labs/FLUX.1-schnell", subfolder="transformer")
 model = FluxTransformer2DModel.from_config(config)

# Download checkpoints
schnell_ckpt = snapshot_download(repo_id="black-forest-labs/FLUX.1-schnell", allow_patterns="transformer/*")
krea_ckpt = snapshot_download(repo_id="black-forest-labs/FLUX.1-Krea-dev", allow_patterns="transformer/*")

# Get sorted shard paths
schnell_shards = sorted(glob.glob(f"{schnell_ckpt}/transformer/*.safetensors"))
krea_shards = sorted(glob.glob(f"{krea_ckpt}/transformer/*.safetensors"))

# Initialize dictionaries for merged and guidance weights
merged_state_dict = {}
guidance_state_dict = {}

# Merge shards
for schnell_shard, krea_shard in zip(schnell_shards, krea_shards):
 state_dict_schnell = safetensors.torch.load_file(schnell_shard)
 state_dict_krea = safetensors.torch.load_file(krea_shard)

 # Process keys from schnell model
 for k in list(state_dict_schnell.keys()):
 if "guidance" in k:
 # Keep guidance weights from schnell model
 guidance_state_dict[k] = state_dict_schnell.pop(k)
 else:
 # Average non-guidance weights if key exists in krea
 if k in state_dict_krea:
 merged_state_dict[k] = (state_dict_schnell.pop(k) + state_dict_krea.pop(k)) / 2
 else:
 raise ValueError(f"Key {k} missing in krea shard.")

 # Check for residual keys in krea (e.g., extra guidance keys)
 for k in list(state_dict_krea.keys()):
 if "guidance" in k:
 # Skip extra guidance keys in krea
 state_dict_krea.pop(k)
 else:
 raise ValueError(f"Unexpected non-guidance key in krea shard: {k}")

 # Verify no unexpected residue
 if len(state_dict_schnell) > 0:
 raise ValueError(f"Residue in schnell shard: {list(state_dict_schnell.keys())}")
 if len(state_dict_krea) > 0:
 raise ValueError(f"Residue in krea shard: {list(state_dict_krea.keys())}")

# Combine merged and guidance state dictionaries
merged_state_dict.update(guidance_state_dict)

# Load merged state dictionary into model
load_model_dict_into_meta(model, merged_state_dict)

# Convert to bfloat16 and save
model.to(torch.bfloat16).save_pretrained("merged/transformer")

api = HfApi()
repo_id = "prithivMLmods/Flux.1-Krea-Merged-Schnell"

api.upload_folder(
 folder_path="merged/",
 path_in_repo=".",
 repo_id=repo_id,
 repo_type="model",
 revision="main"
)

---

Inference Code🧨

from diffusers import FluxPipeline
import torch

pipeline = FluxPipeline.from_pretrained(
 "prithivMLmods/Flux.1-Krea-Merged-Schnell", torch_dtype=torch.bfloat16
).to("cuda")
image = pipeline(
 prompt="a tiny astronaut hatching from an egg on the moon",
 guidance_scale=3.5,
 num_inference_steps=28,
 height=1024,
 width=1024,
 max_sequence_length=512,
 generator=torch.manual_seed(0),
).images[0]
image.save("img0.png")

---

Quick Start with Gradio and Transformers🤗

COMPARATOR : FLUX.1-Dev(Realism) and Flux.1-Krea-Merged-Schnell (FLUX.1-schnell + FLUX.1-Krea-dev)

Installing Required Packages

%%capture
!pip install git+https://github.com/huggingface/transformers.git
!pip install git+https://github.com/huggingface/diffusers.git
!pip install git+https://github.com/huggingface/peft.git
!pip install git+https://github.com/huggingface/accelerate.git
!pip install safetensors huggingface_hub hf_xet

hf-login

from huggingface_hub import notebook_login, HfApi
notebook_login()

Recommended runtime type

@hardware-accelerator : H200

---

For more information, visit the documentation.

Flux is a suite of state-of-the-art text-to-image generation models based on diffusion transformers, developed by Black Forest Labs. The models are designed for high-quality generative image tasks, including text-to-image, inpainting, outpainting, and advanced structure or depth-controlled workflows. Flux is available through the Hugging Face diffusers library.

For detailed guides, examples, and API refer to:

• Main Flux Pipeline Documentation
• Flux Transformer Model Documentation

black-forest-labs/FLUX.1-Krea-dev

black-forest-labs/FLUX.1-schnell

(FLUX.1-schnell + FLUX.1-Krea-dev) | (Flux.1-Dev + Flux.1-Krea-Dev) • 3 items • Updated 2 days ago