Shoukanlabs
Models by this creator
🎲
OpenNiji
93
The OpenNiji model is a Stable Diffusion model fine-tuned by ShoukanLabs on images from the Nijijourney dataset. This model is capable of generating anime-style images based on text prompts, with a focus on characters from the Nijijourney universe. Compared to similar models like Cool Japan Diffusion 2.1.0, Japanese Stable Diffusion, and Anime Kawai Diffusion, the OpenNiji model has a more specialized training dataset and aims to capture the visual style of the Nijijourney series. Model inputs and outputs The OpenNiji model takes in text prompts and generates corresponding images. The text prompts can describe a wide range of scenes, characters, and objects, and the model will attempt to generate an image that matches the provided description. Inputs Text prompts**: Short or long descriptions of the desired image, including details about the scene, characters, and visual style. Outputs Generated images**: The model will output an image that matches the provided text prompt. The images are generated in a high-resolution, anime-inspired style. Capabilities The OpenNiji model excels at generating high-quality anime-style images based on detailed text prompts. It can create a wide variety of scenes, characters, and objects in the visual style of the Nijijourney universe. The model has been fine-tuned to handle prompts related to the Nijijourney series particularly well, generating images with accurate character designs, backgrounds, and other details. What can I use it for? The OpenNiji model can be a powerful tool for artists, content creators, and enthusiasts of the Nijijourney series. You can use it to quickly generate concept art, illustrations, and other visual assets based on your ideas and creative prompts. The model's ability to capture the unique aesthetic of the Nijijourney universe makes it especially useful for projects related to that fictional world, such as fan art, fan fiction, or even commercial products. Things to try One interesting aspect of the OpenNiji model is its ability to handle prompts that include specific details about Nijijourney characters, locations, and objects. Try experimenting with prompts that reference elements from the series, such as character names, landmark locations, or unique items and see how the model captures the details. You can also try combining the OpenNiji model with other text-to-image or image-to-image techniques, such as Dreambooth, to further customize and refine the generated images.
Updated 5/28/2024
🖼️
Vokan
54
Vokan is an advanced finetuned StyleTTS2 model designed for authentic and expressive zero-shot performance. It was created by ShoukanLabs, a prolific AI model developer. Vokan leverages a diverse dataset and extensive training to generate high-quality synthesized speech. It was trained on a combination of the AniSpeech, VCTK, and LibriTTS-R datasets, ensuring authenticity and naturalness across various accents and contexts. Model inputs and outputs Inputs Text to be converted to speech Outputs Synthesized speech audio Capabilities Vokan captures a wide range of vocal characteristics, contributing to its remarkable performance in generating expressive and natural-sounding speech. With over 6+ days worth of audio data and 672 diverse and expressive speakers, the model has learned to handle a broad array of accents and contexts. What can I use it for? Vokan can be used in a variety of applications that require high-quality text-to-speech (TTS) capabilities, such as audiobook production, voice assistants, and multimedia content creation. Its expressive and natural-sounding synthesis makes it a compelling choice for projects that require a human-like voice. Things to try Experiment with Vokan by providing it with different types of text, ranging from formal to informal, to see how it handles various styles and tones. Additionally, you can explore its potential by integrating it into your own projects and observing its performance in real-world scenarios.
Updated 7/18/2024
🖼️
Vokan
54
Vokan is an advanced finetuned StyleTTS2 model designed for authentic and expressive zero-shot performance. It was created by ShoukanLabs, a prolific AI model developer. Vokan leverages a diverse dataset and extensive training to generate high-quality synthesized speech. It was trained on a combination of the AniSpeech, VCTK, and LibriTTS-R datasets, ensuring authenticity and naturalness across various accents and contexts. Model inputs and outputs Inputs Text to be converted to speech Outputs Synthesized speech audio Capabilities Vokan captures a wide range of vocal characteristics, contributing to its remarkable performance in generating expressive and natural-sounding speech. With over 6+ days worth of audio data and 672 diverse and expressive speakers, the model has learned to handle a broad array of accents and contexts. What can I use it for? Vokan can be used in a variety of applications that require high-quality text-to-speech (TTS) capabilities, such as audiobook production, voice assistants, and multimedia content creation. Its expressive and natural-sounding synthesis makes it a compelling choice for projects that require a human-like voice. Things to try Experiment with Vokan by providing it with different types of text, ranging from formal to informal, to see how it handles various styles and tones. Additionally, you can explore its potential by integrating it into your own projects and observing its performance in real-world scenarios.
Updated 7/18/2024
🏅
OpenNiji-V2
46
OpenNiji-V2 is a Stable Diffusion model developed by ShoukanLabs that has been trained on 180,000 Nijijourney images. This model is a continuation of the original OpenNiji model, with improvements to the dataset and training process. The model has been fine-tuned on a dataset that includes a higher-quality version of the original Nijijourney images, resulting in improved performance in generating anime-style images. Compared to the original OpenNiji, this model is better at generating hands and other details. Model inputs and outputs OpenNiji-V2 is a text-to-image generation model that takes a text prompt as input and generates a corresponding image. The model can handle a wide range of prompts related to anime-style art, including character descriptions, scenes, and more. Inputs Text prompt**: A description of the image to be generated, such as "1girl, eyes closed, slight smile, underwater, water bubbles, reflection, long light brown hair, bloom, depth of field, bokeh". Outputs Generated image**: An image that corresponds to the input text prompt, in the style of anime artwork. Capabilities The OpenNiji-V2 model is capable of generating high-quality anime-style images with a level of detail and realism that is impressive for a Stable Diffusion model. The model excels at generating character portraits, scenes with detailed backgrounds, and even complex compositions with multiple elements. One of the key strengths of the model is its ability to generate hands and other fine details, which can be a challenge for some Stable Diffusion models. The "in01 trick" applied to the model helps improve its performance in this area. What can I use it for? The OpenNiji-V2 model is well-suited for a variety of projects and applications that involve the generation of anime-style artwork. Some potential use cases include: Illustration and artwork generation**: The model can be used to generate illustrations, character designs, and other anime-inspired artwork for a range of projects, such as games, animations, and digital art. Concept art and visualization**: The model can be used to quickly generate concept art or visual ideas for projects in the anime and manga industries. Educational and creative tools**: The model could be integrated into educational or creative tools that allow users to experiment with and generate anime-style artwork. Things to try One interesting thing to try with the OpenNiji-V2 model is experimenting with different prompts and prompt engineering techniques to see how the model responds. For example, you could try adding specific aesthetic tags or modifiers to the prompt to nudge the model towards a particular style or visual aesthetic. Additionally, you could explore the model's capabilities in generating more complex scenes or compositions, such as those involving multiple characters, detailed backgrounds, or fantastical elements. By pushing the boundaries of what the model can do, you may uncover new and unexpected creative possibilities.
Updated 9/6/2024