calcuis/krea-gguf

gguf quantized version of krea

• 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

run it with gguf-connector

• able to opt - 2-bit, 4-bit or 8-bit model for dequant while executing:

ggc k4

reference

• base model from black-forest-labs
• diffusers from huggingface
• comfyui from comfyanonymous
• gguf-node (pypi|repo|pack)
• gguf-connector (pypi)