Templates-PandaMeme (FLUX.2-klein-base-4B)

This model is part of the first batch of Diffusion Templates series models open-sourced by DiffSynth-Studio. It's an Easter egg model capable of generating various quirky panda-head meme images.

Open-source code: DiffSynth-Studio
Technical report: arXiv
Project page: GitHub
Documentation: English Version、中文版
Online demo: ModelScope
Models: ModelScope、ModelScope International、HuggingFace
Datasets: ModelScope、ModelScope International、HuggingFace

Demo

|Prompt: A meme with a happy expression.|Prompt: A meme with a sleepy expression.|Prompt: A meme with a surprised expression.|

|-|-|-|

|![](./assets/image_PandaMeme_happy.jpg)|![](./assets/image_PandaMeme_sleepy.jpg)|![](./assets/image_PandaMeme_surprised.jpg)|

Inference Code

Install DiffSynth-Studio

git clone https://github.com/modelscope/DiffSynth-Studio.git
cd DiffSynth-Studio
pip install -e .

Direct inference (requires 40G GPU memory)

from diffsynth.diffusion.template import TemplatePipeline
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch

pipe = Flux2ImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
)
template = TemplatePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-PandaMeme")],
)
image = template(
    pipe,
    prompt="A meme with a sleepy expression.",
    seed=0, cfg_scale=4, num_inference_steps=50,
    template_inputs = [{}],
    negative_template_inputs = [{}],
)
image.save("image_PandaMeme_sleepy.jpg")
image = template(
    pipe,
    prompt="A meme with a happy expression.",
    seed=0, cfg_scale=4, num_inference_steps=50,
    template_inputs = [{}],
    negative_template_inputs = [{}],
)
image.save("image_PandaMeme_happy.jpg")
image = template(
    pipe,
    prompt="A meme with a surprised expression.",
    seed=0, cfg_scale=4, num_inference_steps=50,
    template_inputs = [{}],
    negative_template_inputs = [{}],
)
image.save("image_PandaMeme_surprised.jpg")

Enable lazy loading and memory management, requires 24G GPU memory

from diffsynth.diffusion.template import TemplatePipeline
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch

vram_config = {

"offload_dtype": "disk",

"offload_device": "disk",

"onload_dtype": torch.float8_e4m3fn,

"onload_device": "cpu",

"preparing_dtype": torch.float8_e4m3fn,

"preparing_device": "cuda",

"computation_dtype": torch.bfloat16,

"computation_device": "cuda",

}

pipe = Flux2ImagePipeline.from_pretrained(

torch_dtype=torch.bfloat16,

device="cuda",

model_configs=[

ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/.safetensors", *vram_config),

ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/.safetensors", *vram_config),

ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),

tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),

vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,

)

template = TemplatePipeline.from_pretrained(

torch_dtype=torch.bfloat16,

device="cuda",

model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-PandaMeme")],

lazy_loading=True,

)

image = template(

pipe,

prompt="A meme with a sleepy expression.",

seed=0, cfg_scale=4, num_inference_steps=50,

template_inputs = [{}],

negative_template_inputs = [{}],

)

image.save("image_PandaMeme_sleepy.jpg")

image = template(

pipe,

prompt="A meme with a happy expression.",

seed=0, cfg_scale=4, num_inference_steps=50,

template_inputs = [{}],

negative_template_inputs = [{}],

)

image.save("image_PandaMeme_happy.jpg")

image = template(

pipe,

prompt="A meme with a surprised expression.",

seed=0, cfg_scale=4, num_inference_steps=50,

template_inputs = [{}],

negative_template_inputs = [{}],

)

image.save("image_PandaMeme_surprised.jpg")


## Training Code

After installing DiffSynth-Studio, use the following script to start training. For more information, please refer to the [DiffSynth-Studio Documentation](https://diffsynth-studio-doc.readthedocs.io/zh-cn/latest/).

modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/Template-KleinBase4B-PandaMeme/*" --local_dir ./data/diffsynth_example_dataset

accelerate launch examples/flux2/model_training/train.py \

--dataset_base_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-PandaMeme \

--dataset_metadata_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-PandaMeme/metadata.jsonl \

--extra_inputs "template_inputs" \

--max_pixels 1048576 \

--dataset_repeat 50 \

--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \

--template_model_id_or_path "DiffSynth-Studio/Template-KleinBase4B-PandaMeme:" \

--tokenizer_path "black-forest-labs/FLUX.2-klein-4B:tokenizer/" \

--learning_rate 1e-4 \

--num_epochs 2 \

--remove_prefix_in_ckpt "pipe.template_model." \

--output_path "./models/train/Template-KleinBase4B-PandaMeme_full" \

--trainable_models "template_model" \

--use_gradient_checkpointing \

--find_unused_parameters