Support☕ https://ko-fi.com/sfa837348
hugging face https://huggingface.co/gsdf/CounterfeitXL-V2.0
Negative Embedding https://civarchive.com/models/118418/negativexl
Official hosting for online AI image generator.
A small update.
V2.5 is a revised version of V2.0.
This version has been retrained for style tags.
Tips
By inserting 'flat color, anime style' into negative prompts, you can achieve results with higher detail.
CounterfeitXL-V2.0 has been primarily trained on the latest illustrations but encounters a recurring issue with the appearance of halos. In such cases, please include 'halo' in negative prompts.
I have incorporated style tags into some of the training images. By describing these tags in the prompt, various effects can be achieved. Additionally, inserting style tags into negative prompts or combining them allows for the generation of images that align with your imagined.
Style Tags
masterpiece: Beautifully and intricately drawn illustrations.
cinematic style: Stunning illustrations with detailed backgrounds and lighting.
aesthetic style: Illustrations featuring beautiful color schemes.
cute style: Cute.
flat color: Illustrations with strong lines and a minimal color palette.
anime style: Anime.
comic style: Illustrations characterized by bold color choices and abstract representations.
Description
FAQ
Comments (8)
btw what did you revise between 2 and 2.5? Just curious
Good day, Any chance to get a hand on the tag set used in this model? (I mean the large list) i don´t care if its unsorted/raw.
i´s like to filter character names/Tags out of it and collect it in a central tag index for easy usage.
see here if you are interessted:
https://civitai.com/articles/5106/tagging-listsindex-bring-order-into-chaos
Will there be Counterfeit for AuraFlow Pony or Flux derivatives in the near future?
Can you do this checkpoint for PonyXl also?
the old SD1 Counterfeit was much better for some reason.
Agree, i can't get the same images with this one, it seems to always try for that generic close up vibe while the SD1 got a broad image of events that i really liked, however the quality on this is quite good, hands are proper mostly, don't like that i had to put black and white on the negatives to actually get color in the image though
@Lonmine specifically "black" and "white"? Monochrome doesn't work? That tends to work for most checkpoints, SDXL or SD1.5, in order to avoid grayscale and otherwise monochromatic images.
ポジ:masterpiece,aesthetic style,
ネガ: (low quality, worst quality:1.2), bad anatomy, fewer digits, extra fingrers,flat color, anime style,
が実質的な推奨設定だろう。あとはcomic style,とcinematic style,くらいしか実用レベルにない。
プロンプトは結構無視されるので、使い勝手はあまりよくない。
Details
Files
counterfeitxl_v25.safetensors
Mirrors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
CounterfeitXL_V2.5.safetensors
counterfeitxl_v25.safetensors
CounterfeitXL-V2.5.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
CounterfeitXL-V2.5.safetensors
counterfeitxl_v25.safetensors
counterfeitxl_v25.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



