Make Ghibli Style Photos without ChatGPT or Internet

 Make Ghibli Style Photos without ChatGPT or Internet



Make Ghibli Style Photos without ChatGPT or Internet

Recently, the internet exploded with excitement about using OpenAI’s ChatGPT for generating Ghibli style images, transforming real-life photos into animations. And yes, it delivers impressive results.

This comes as no shock to stable diffusion and flux users— we’ve had this capability for ages. What’s truly remarkable is how we’ve moved from juggling specific checkpoints, controlnet models, and loras to achieving the same with just a few words.

Not long ago, creating such transformations meant diving into technical things like lora, controlnet, and instantID. Now, OpenAI has wrapped it all into a seamless chat interface. You simply tell the chatbot what you want, and voilà — it’s done. This extends beyond Ghibli style to virtually any image aesthetic. I must admit, it’s a brilliant end-user product.

Yet some of us crave more control and privacy. Thanks to years of open-source community efforts, we can achieve this with just a touch more patience.

Why bother when ChatGPT and other platforms (like Huggingface) already handle this? Some people worry about:
1. Privacy — concerns about personal photos uploaded to servers beyond their control
2. Customization — more control over generation variations
3. Offline access — free generation anywhere, anytime, internet-free

For folks like me, these reasons are more than enough to justify the DIY approach. Follow this guide and you won’t need much technical expertise — just basic computer installation skills (like downloading stuff and moving files) will be enough to transform your photos into Ghibli-style animations.

Setting Up ComfyUI

Before going offline to create some awesome art, let’s grab these essentials:

Download ComfyUI: [link] 

It’s basically a ready-to-use app — just download and run! Works with Nvidia graphics cards or MacOS. Just visit their site, click download, and follow the instructions.

Remember where you install it* (example: “C:\comfyui\custom_nodes\ComfyUI-Manager” on Windows).

*If you don’t mind doing some homework and installing ComfyUI in the traditional way, you may be able to run this on most of the Windows, MacOS, or Linux devices. Here I only present the easy way.*

Get ComfyUI Manager: [link]

This makes installing other tools super easy. Just go to GitHub, download it, and extract the files into your “…\comfyui\custom_nodes\ComfyUI-Manager” folder.

(The folder name should be “ComfyUI-Manager”, NOT “ComfyUI-Manager-main”!! Rename it after extraction!)

(There’s a formal installation method too if you’re curious)

Download Models

— Grab the FLUX model from (https://huggingface.co/lllyasviel/FLUX.1-dev-gguf/tree/main) → put in `ComfyUI\models\unet`
(I’m using the 8-bit version for memory reasons. Q4 works fine with 8GB VRAM or 16GB RAM Macs, but more VRAM = better quality)
 
 — VAE: (https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.safetensors) → `ComfyUI/models/vae`
 
 — CLIP Model: (https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors) → `ComfyUI/models/clip`
 
 — T5 Model: (https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp16.safetensors) → `ComfyUI/models/clip`

Get the Style LoRA:

Grab this Ghibli style LoRA(https://civitai.com/models/1411365/studio-chatgpt-ghibli) → `ComfyUI\models\loras`
 (Thanks to the lora author who made this in lightning speed!! This is just an example — feel free to explore other styles!)

Redux Models:

— CLIP Vision: (https://huggingface.co/Comfy-Org/sigclip_vision_384/resolve/main/sigclip_vision_patch14_384.safetensors) → `ComfyUI/models/clip_vision`
 
 — Redux Model: (https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/resolve/main/flux1-redux-dev.safetensors) → `ComfyUI/models/style_models`

First Launch

Fire up ComfyUI and give it a few minutes on first boot while it installs necessary packages.

Install Custom Nodes

Once loaded, you’ll see the interface with a “Manager” button in the top right. Click it, then “Custom Nodes Manager,” and search for these two must-haves:
 — “KJNodes for ComfyUI” 
 — “ComfyUI-GGUF”

After installing the two custom nodes, you need to restart comfyui.

Final Step

Download my workflow file here [link] and open it in ComfyUI. No errors? You’re all set to create!

Start uploading photos and enjoy creating your own Ghibli magic!

Now, you can fully go offline and generating images!

Location: Canada

Comments

Post a Comment

Popular posts from this blog

What is Tang Ping? Investigating the Social Media Phenomenon Through Natural Language Processing

Image
The phrase "Tang Ping" (躺平) has been gaining attention since 2023, particularly in the wake of China's stringent and protracted COVID-19 societal lockdown. Literally translated as "lying flat, " Tang Ping has emerged as a popular sentiment among Chinese individuals on social media. Its significance is so profound that it now has its own Wikipedia entry (“ Tang Ping ,” 2023) and has even garnered the attention of the BBC (“China’s New ‘tang Ping’ Trend Aims to Highlight Pressures of Work Culture,” 2021) . As described in a BBC article, Tang Ping represents "an antidote to society's pressures to find jobs and perform well while working long shifts." It advocates for "not overworking, being content with more attainable achievements and allowing time to unwind." Wow, what a philosophical mindset. While there's a fascinating story behind the term "Tang Ping," I'm not the best storyteller, and this isn't a research pap...
Read more

Using LLMs on Your Phone Locally in Three Easy Steps

Image
  This post was published here at Medium, click for details: https://medium.com/@frank.t.f.ye/using-llms-on-your-phone-locally-in-three-easy-steps-30367c3a60a3 Recently, I’ve been exploring ways to run Large Language Models locally on my phone, and I’m excited to share what I’ve learned. With the latest mobile devices packing increasingly powerful hardware, running your own AI models locally has become a reality. The recent release of smaller but capable Llama 3.2 models has made it possible to run these on both iOS and Android devices. This is particularly useful when you need to handle tasks like drafting emails in situations where you either don’t have internet access or have privacy concerns about using cloud-based AI services. iOS Users If you’re using Apple devices like me, setting up a local LLM is surprisingly straightforward. Just head to the App Store and download “LLM Farm” — it’s an impressive local LLM runner developed by Artem ( Link ) and it’s completely open-source!...
Read more

Shifting Preferences of Mainland Chinese Tourists' Interests from Luxury to Budget Experiences in Hong Kong - Data From Little Redbook

Image
It seems that Hong Kong will never be the same as before. Background Not long ago, news reports in Hong Kong media started to highlight the changing preferences of mainland tourists. The main theme was that, after two years of COVID-19 lockdowns, the high expectations of a boom in tourism were wrong. Mainland tourists did come to Hong Kong, but there were fewer, who spent less. The tourism industry is a critical component of Hong Kong's economy, contributing to approximately 4.5% of its GDP and employing around 257,000 people, accounting for about 6.6% of total employment in 2018 (GovHK, 2020). More than 80% of the total inflow of tourists was contributed by mainland visitors (Hong Kong Tourism Board, 2023). However, visitor arrivals experienced a significant downturn starting in 2019, which persisted until the full border reopening in February 2023. For more than three years, travel restrictions such as cross-border regulations, and quarantine requirements greatly diminished the v...
Read more