Tensor.Art
Create

FeMix_HassakuXL

CHECKPOINT
Reprint

Updated:

v2.5
v2.4
v2.3
v2.2
v2.1
v2.0
v1.8
v1.7
v1.6
v1.5
v1.4
v1.3
v1.2
v1.1
v1.0
images1
v2.10
v2.9
v2.8
v2.7
v2.6

creator: Koal2

FeMix_HassakuXL: Exploring Blended Styles with the FeMix

FeMix_HassakuXL is a model series built upon base HassakuXL series, pushing creative boundaries with the FeMix blending system. It allows you to generate anime-style images with varying characteristics, all within a single, versatile model family.

FeMix Blending System:

FeMix_HassakuXL introduces different model variants based on the FeMix blending system, offering a spectrum of stylistic nuances. Each version combines two core styles, "A" and "B," in different ratios:

  • Style A: This style provides great lighting and composition. It retains a solid base and is LoRA-Friendly.

  • Style B: Style B is purely unique, it can have many flaws like artifacts. Highres fix or Adetailer is recommended.

Version Breakdown:

  • v1.0: FeMix_HassakuXL_A5B5 (50% A, 50% B): This is a balanced blend, combining the stability and lighting of Style A with the experimental style of Style B. Expect a noticeable influence from both styles, with a moderate risk of artifacts inherited from Style B.

  • v1.1: FeMix_HassakuXL_A7B3 (70% A, 30% B): This blend prioritizes the strengths of Style A, including good LoRA compatibility, while adding a subtle touch of Style B's unique aesthetics. Artifact risk is reduced compared to v1.0.

  • v1.2: FeMix_HassakuXL_A3B7 (30% A, 70% B): This experimental blend leans heavily towards Style B's distinctive style. Be prepared for a higher chance of artifacts and potentially less predictable results with LoRA models. This version is best for exploring unique visuals and accepting potential imperfections.

General Recommendations:

  • Experiment with different prompts and negative prompts to fine-tune the results and control the influence of each style.

  • Use highres fix or Adetailer (or similar tools) to mitigate potential artifacts, especially when using versions with a higher percentage of Style B.

  • The effectiveness of LoRA models may vary depending on the blend ratio. Versions with more Style A will generally provide more predictable LoRA results.

  • Excluded metadata and franchise tags, don't use them. meta data -> something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".

Recommended Resolutions (SDXL):

  • 1024 x 1024

  • 1152 x 896

  • 896 x 1152

  • 1216 x 832

  • 832 x 1216 (most recommended)

  • 1344 x 768

  • 768 x 1344

  • 1536 x 640

  • 640 x 1536

FeMix_HassakuXL provides a unique way to explore blended styles. Choose the version that aligns with your creative goals and enjoy the journey!

Version Detail

Illustrious
Model Description: Style A+B (50/50 Blend) This model is a fusion of Style A and Style B, offering a unique blend of characteristics from both. It aims to strike a balance between the anime-influenced aesthetic of Style A and the experimental style of Style B. Key Features: Brightness and Anime Influence: Inherits the brighter overall image appearance and the tendency towards a more anime-style aesthetic from Style A. Expect fewer highly-detailed/realistic noses and faces (especially without prompting), leaning towards a smoother, anime-inspired look. LORA Compatibility: Maintains good compatibility with LoRA models thanks to the Style A influence. LoRAs should be able to significantly impact the style and details of your generations, including pony LoRAs. Interesting Style with Potential Flaws: Incorporates the interesting and potentially flawed style of Style B. Be aware of potential artifacts (especially around the eyes) and possible composition issues. Highres fix or Adetailer is recommended to mitigate these flaws. Balance of Styles: Aims to provide a middle ground between the cinematic lighting potential of Style A and the unique style of Style B. Results may vary, and experimentation is encouraged. Recommendations: Use highres fix or Adetailer to address potential artifacts and composition issues, inherited from Style B. Experiment with different samplers to find one that minimizes artifact susceptibility. Leverage LoRA models to further customize the style and details of your generations. Consider using artist tags to refine the desired style, as the Style A base retains a good level of tag responsiveness. Please Note: This is a merged model, and results may be unpredictable. Experimentation is key to discovering its full potential and understanding its limitations. The future development of a refined "Style B" variant depends on the popularity and feedback received for this merged model.

Project Permissions

Model reprinted from : https://civitai.com/models/1384794

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts