Sign In

FFusionXL 0.9 SDXL model + Diffusers

34
369
1
0
Type
Checkpoint Trained
Stats
369
Uploaded
Jul 26, 2023
Base Model
SDXL 0.9
Hash
AutoV2
1D10EAFB6D
0
0
0
0
0

ffusionXLs.png

Download ModelFFusionXL SDXL DEMO

FusionXL SDXL model + Diffusers

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("FFusion/FFusionXL-09-SDXL", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")

FFusionXL-09-SDXL

ffusionXL.jpg

Model

FFXL based on SDXL consists of a two-step pipeline for latent diffusion: First, we use a base model to generate latents of the desired output size. In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") to the latents generated in the first step, using the same prompt.

Download

Model Description

FFusionAI_00187_.png

Model Sources

  • Demo:FFusionXL SDXL DEMO

    Hugging Face ModelGitHubFacebookCivitai

🧨 Diffusers

Make sure to upgrade diffusers to >= 0.18.0:

pip install diffusers --upgrade

In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:

pip install invisible_watermark transformers accelerate safetensors

You can use the model then as follows

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("FFusion/FFusionXL-09-SDXL", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")

# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()

prompt = "An astronaut riding a green horse"

images = pipe(prompt=prompt).images[0]

When using torch >= 2.0, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline:

pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)

If you are limited by GPU VRAM, you can enable cpu offloading by calling pipe.enable_model_cpu_offload instead of .to("cuda"):

- pipe.to("cuda")
+ pipe.enable_model_cpu_offload()

Uses

fusion.ai334.jpg

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include

  • Generation of artworks and use in design and other artistic processes.

  • Applications in educational or creative tools.

  • Research on generative models.

  • Safe deployment of models which have the potential to generate harmful content.

  • Probing and understanding the limitations and biases of generative models.

Excluded uses are described below.

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

Limitations and Bias

Limitations

  • The model does not achieve perfect photorealism

  • The model cannot render legible text

  • The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to β€œA red cube on top of a blue sphere”

  • Faces and people in general may not be generated properly.

  • The autoencoding part of the model is lossy.

Bias

While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.

Attribution:

"SDXL 0.9 is licensed under the SDXL Research License, Copyright (c) Stability AI Ltd. All Rights Reserved."

License

SDXL 0.9 Research License" FFXL 0.9 Research License"

Email

SAMPLES

fusion.ai_00093_.pngfusion.ai_00113_.png

fusion.ai333.png

ffusion.aeei.png