wan2.2_i2v_animestyletransition_high.safetensors

146 MB · SafeTensor

Mitgliedschaft erforderlich

<switch-anime-style-high-wan>

Takes a realistic or 3D frame as the initial image, then converts it to an animated style. This LoRA by itself may yield a wide variety of anime-styled to semi-realistic cartoon appearances, but it can be directed to more reliably produce anime by pairing it with my . Example Use: - Strength: 1.5 (on both this LoRA and the Anime Style LoRA) - Length: 33 frames - Prompt: "a realistic person shuffles in place, later becoming An1meStyl3" - Steps: 4 (2 high, 2 low) California AB 2013 Training Data Disclosure - This LoRA was fine-tuned using visual data consisting of still images derived from animated works, along with photographs, game screenshots, and AI-generated images used as inputs for synthetic transformation. The training data includes copyrighted material owned by third parties, including animation studios, game publishers, and individual artists, as well as derivative synthetic content generated from those inputs. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution. - The dataset consists of over 100 images derived from anime-style sources, along with over 50 video clips. Each clip was created by taking an existing image, including photographs, game screenshots, or AI-generated images, generating an anime-style version of that image using AI, and producing an animated sequence in which both versions appear sequentially to introduce a deliberate style transition. Data was collected and generated between approximately 2024 and 2025. - Image data was processed through standard resizing, cropping, normalization, and labeling steps. Video clips were prepared and labeled for video-based training to support motion learning and style-transition behavior. Synthetic images and video were included as part of the training dataset. - This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.

SHA256

CA0482FAA66606EB61CD6387D99EA0241F65F0DABD6D16B0881CBF0A1500A3AC

ModelTrends.ai-Modell-ID

#24291

Sampler

DDIM

Schritte

10

Guidance

1

Größe

768x1024

Schritte

4

Größe

490x640