GPT-4o Ghibli Stylization

5.0

6 reviews
59
17.2K
6.7K
26
Description

https://github.com/logtd/ComfyUI-Fluxtapoz


https://civitai.com/models/1411365/studio-chatgpt-ghibli


Note: The recommended value for 'skip steps' in the Flow Edit Sampler node is 0-4.

Node Diagram
Discussion
J
Jemish Malaviya2 months ago

Can you provide CFG-Zero-star node

m
makisekurisu2 months ago

Update ComfyUI to the latest version, and you'll have this node. Of course, you can bypass it—it seems to only work for text-to-image tasks.

J
Jemish Malaviya2 months ago

Ok thanks

P
PixelPilfera month ago

Thaaks for this one comment about text to image. Saves me hours of downloading and trying to..

J
Jorge Armando2 months ago

I fixed this by downloading this comfyUi:  https://github.com/comfyanonymous/ComfyUI

It comes with the CFGZeroStar node

f
fello 19752 months ago

I already installed that version and it still does´nt work

吴承峰2 months ago

感谢大佬分享,这是我人生跑通的第一个第三方workflow,效果非常好,除了速度有点慢,一张图M2 16g的MacBookPro大概需要6600秒。

m
makisekurisu2 months ago

I don't have a Mac, but on an NVIDIA 40-series GPU with 12GB VRAM, it runs in under 60 seconds.

S
Sunix Liu2 months ago

Hi all, just a hint, you need the nightly version not the stable one. Otherwise, you will find the CFG-Zero-star node is missing.

Á
Ádám B.2 months ago

promps pls .

E
Elias Tsiantas2 months ago

This is by far the best workflow. And I have tried them all.

Congrats!

👍1
M
Mohamad Yusoff2 months ago

anyone got this error? is it due to amd card

CLIPTextEncode

Cannot access storage of OpaqueTensorImpl

(Edited)
S
Stephano Di Cola2 months ago

GOOD WORK, CAN I KNOW WHY MY GENERATE IMAGE SEEMS TO BE MIRRORED?

THANKS



sponge_meager_82 months ago

Thanks a lot @makisekurisu for this is a great workflow!

I just have some pictures that don't seem to be getting the effect applied correctly for some reason, it creates what seems to be "something in between" I'm running 1200/1800px images, you can see the input/output images here:  https://ibb.co/20fSxjyN

On a side node: Sometimes it struggles a bit to correctly represent some skin tones, like for example on this picture:  https://ibb.co/RT8QXxhV, the person on the right has a darker skin tone but on the result image I'm getting both with the same skin tone color.

Would appreciate very much any help on those issues! Thanks a lot once again!

m
makisekurisu2 months ago

Set the skip steps to 0;

Generate multiple times to see if you get a satisfying result.

sponge_meager_82 months ago

Thanks a lot for the response!

Using 0 skip steps results in an image very close to the original image with no Ghibli effect applied, if I go above 4 skip steps like 6,7,8 I just end up a blurry image... For some reason my bartender photo never get's the effect, even when I try smaller resolutions like 600x900 or 400x600...

Unfortunately neither increasing or decreasing the skip steps solved any of the issues...

m
makisekurisu2 months ago

skip_steps 0

refine_steps 28

If it still doesn't work, please try adjusting parameters such as the strength of 'applystylemode' yourself. In fact, your image is not particularly unique—I would simply think that you haven't properly understood or utilized this workflow.

(Edited)
❤️1
sponge_meager_82 months ago

Indeed your workflow is new to me with a different approach so I'm still learning it bit by bit.

Changing the skip/refine steps did not solve the problem but increasing the strength of the 'applystylemode' did! Thanks a lot for the help! I see it does struggle a bit with medium to dark skin woman in some cases, but that might more lora specific than workflow related.

Really appreaciate your help thanks!

王夕颜2 months ago

为什么我跑出来都是变形和模糊的

D
Delatha month ago

Prompt execution failed

Prompt outputs failed validation:
VAELoader:
- Value not in list: vae_name: 'ae.safetensors' not in []
UnetLoaderGGUF:
- Value not in list: unet_name: 'flux1-dev-Q8_0.gguf' not in []
DualCLIPLoaderGGUF:
- Value not in list: clip_name1: 'clip_l.safetensors' not in []
- Value not in list: clip_name2: 't5-v1_1-xxl-encoder-Q8_0.gguf' not in []
LoraLoaderModelOnly:
- Value not in list: lora_name: 'studiochatgpt-ghibli-v1.safetensors' not in []
StyleModelLoader:
- Value not in list: style_model_name: 'flux1-redux-dev.safetensors' not in []
CLIPVisionLoader:
- Value not in list: clip_name: 'sigclip_vision_patch14_384.safetensors' not in []

D
Delatha month ago

I cleanly installed comfyui, imported the workflow, installed all the missing nodes i got in the comfyui manager and when i try to run the workflow i get this error, i gather i'm missing some stuff, where can i get it?

A
Anton Bodrova month ago

Hi, can you tell me if it is possible to use your workflow with other Lors? Which lore should be considered?

嗨!

我是 BoredWhy 的 Marcio。

您的这个工作流程真是太棒了!我们已将其在 BoredWhy 上线,方便大家体验和使用。希望您不介意!

请点击这里查看:https://boredwhy.com/workflow/68345328161b78915e59d727

当然,所有的功劳都归您所有!


-----------------


Hey there! Marcio from BoredWhy here.

Super cool workflow! We've put it online for people to easily try out on BoredWhy – hope you don't mind!

Check it out here: https://boredwhy.com/workflow/68345328161b78915e59d727

And of course, full credit goes to you!

Author

57
64.7K
532
191.4K

Reviews

S

Sunix Liu

2 months ago

This is the best one I've tried so far!

E

Electricatom369

2 months ago

CFGZeroStar needs to be installed excellent workflow!

sponge_meager_8

2 months ago

Amazing results!!! The best one!!!

S

Silent

2 months ago

soo good

e

elis_t

2 months ago

This is the closest one you can get from al the workflows out there.

f

frank chia

2 months ago

thanks for making this amazing workflow

Versions (1)

  • - latest (2 months ago)

Primitive Nodes (11)

Anything Everywhere3 (1)

CFGZeroStar (1)

ConfigureModifiedFlux (1)

DualCLIPLoaderGGUF (1)

FlowEditGuider (1)

FlowEditSampler (1)

FluxGuidance (2)

Image Comparer (rgthree) (1)

OutFluxModelSamplingPred (1)

UnetLoaderGGUF (1)

Custom Nodes (15)

ComfyUI

  • - SamplerCustomAdvanced (1)

  • - VAEDecode (1)

  • - BasicScheduler (1)

  • - VAEEncode (1)

  • - DisableNoise (1)

  • - VAELoader (1)

  • - LoraLoaderModelOnly (1)

  • - StyleModelLoader (1)

  • - ConditioningConcat (1)

  • - StyleModelApply (1)

  • - CLIPVisionLoader (1)

  • - CLIPVisionEncode (1)

  • - CLIPTextEncode (2)

  • - LoadAndResizeImage (1)

Checkpoints (0)

LoRAs (1)

studiochatgpt-ghibli-v1.safetensors