metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md
language:
  - en
library_name: diffusers
base_model:
  - black-forest-labs/FLUX.1-Krea-dev
pipeline_tag: text-to-image
widget:
  - text: a frog holding a sign that says hello world
    output:
      url: output1.png
  - text: a pig holding a sign that says hello world
    output:
      url: output2.png
  - text: a wolf holding a sign that says hello world
    output:
      url: output3.png
  - text: >-
      cute anime girl with massive fluffy fennec ears and a big fluffy tail
      blonde messy long hair blue eyes wearing a maid outfit with a long black
      gold leaf pattern dress and a white apron mouth open holding a fancy black
      forest cake with candles on top in the kitchen of an old dark Victorian
      mansion lit by candlelight with a bright window to the foggy forest and
      very expensive stuff everywhere
    output:
      url: workflow-embedded-demo1.png
  - text: >-
      on a rainy night, a girl holds an umbrella and looks at the camera. The
      rain keeps falling.
    output:
      url: workflow-embedded-demo2.png
  - text: drone shot of a volcano erupting with a pig walking on it
    output:
      url: workflow-embedded-demo3.png
tags:
  - gguf-node
  - gguf-connector

gguf quantized version of krea

run it straight with gguf-connector
opt a gguf file in the current directory to interact with by:

ggc k

GGUF file(s) available. Select which one to use:

flux-krea-lite-q2_k.gguf

flux-krea-lite-q4_0.gguf

flux-krea-lite-q8_0.gguf

Enter your choice (1 to 3): _

note: try experimental lite model with 8-step operation; save up to 70% loading time

run it with diffusers (see example inference below)

import torch
from transformers import T5EncoderModel
from diffusers import FluxPipeline, GGUFQuantizationConfig, FluxTransformer2DModel

model_path = "https://huggingface.co/calcuis/krea-gguf/blob/main/flux1-krea-dev-q2_k.gguf"
transformer = FluxTransformer2DModel.from_single_file(
    model_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    torch_dtype=torch.bfloat16,
    config="callgg/krea-decoder",
    subfolder="transformer"
)

text_encoder = T5EncoderModel.from_pretrained(
    "chatpig/t5-v1_1-xxl-encoder-fp32-gguf",
    gguf_file="t5xxl-encoder-fp32-q2_k.gguf",
    torch_dtype=torch.bfloat16
    )

pipe = FluxPipeline.from_pretrained(
    "callgg/krea-decoder",
    transformer=transformer,
    text_encoder_2=text_encoder,
    torch_dtype=torch.bfloat16
    )
pipe.enable_model_cpu_offload() # could change it to cuda if you have good gpu

prompt = "a pig holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=2.5,
).images[0]
image.save("output.png")

Prompt
a frog holding a sign that says hello world

Prompt
a pig holding a sign that says hello world

Prompt
a wolf holding a sign that says hello world

Prompt
cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere

Prompt
on a rainy night, a girl holds an umbrella and looks at the camera. The rain keeps falling.

Prompt
drone shot of a volcano erupting with a pig walking on it

run it with gguf-node via comfyui

drag krea to > ./ComfyUI/models/diffusion_models
drag clip-l-v2 [248MB], t5xxl [2.75GB] to > ./ComfyUI/models/text_encoders
drag pig [168MB] to > ./ComfyUI/models/vae

reference

base model from black-forest-labs
for model merge details, see sayakpaul
diffusers from huggingface
comfyui from comfyanonymous
gguf-node (pypi|repo|pack)
gguf-connector (pypi)