ArtiWaifu Diffusion

ArtiWaifu Diffusion We have released the ArtiWaifu Diffusion model, designed to generate aesthetically pleasing and faithfully restored anime-style illustrations. The AWA Diffusion is an iteration of the Stable Diffusion XL model, mastering over 9000 artistic styles and more than 6000 anime characters (version 2.0), generating images through trigger words. As a specialized image generation model for anime, it excels in producing high-quality anime images, especially in generating images with highly recognizable styles and characters while maintaining a consistently high-quality aesthetic expression. News - 2024/08/31: 📢 Announcement: Trigger words list of each version is now moved to the About This Version panel, which is on the right hand side of the model page. - 2024/08/30: ArtiWaifu Diffusion 2.0 version is released on , , () and . Model Details The AWA Diffusion model is fine-tuned from Stable Diffusion XL, with a selected dataset of 2.5M (version 2.0) high-quality anime images, covering a wide range of both popular and niche anime concepts. AWA Diffusion employs our most advanced training strategies, enabling users to easily induce the model to generate images of specific characters or styles while maintaining high image quality and aesthetic expression. Usage Guide This guide will (i) introduce the model's recommended usage methods and prompt writing strategies, aiming to provide suggestions for generation, and (ii) serve as a reference document for model usage, detailing the writing patterns and strategies for trigger words, quality tags, rating tags, style tags, and character tags. Basic Usage - CFG scale: 5-11. Recommended is 7.5. - Resolution: Area (= width x height) around 1024x1024. Not lower than 256x256, and resolutions where both length and width are multiples of 32. - Sampling method: Euler A (20+ steps) or DPM++ 2M Karras (~35 steps) Due to the special training method, AWA's optimal inference step count are higher than regular values. As the inference steps increase, the quality of the generated images can continue to improve... ❓ Question: Why not use the standard SDXL resolution? 💡 Answer: Because the bucketing algorithm used in training does not adhere to a fixed set of buckets. Although this does not conform to positional encoding, we have not observed any adverse effects. Prompting Strategies All text-to-image diffusion models have a notoriously high sensitivity to prompt, and AWA Diffusion is no exception. Even a misspelling in the prompt, or even replacing spaces with underscores, can affect the generated results. AWA Diffusion encourages users to write prompt in tags separated by comma + space ( ,). Although the model also supports natural language descriptions as prompt, or an intermix of both, the tag-by-tag format is more stable and user-friendly. When describing a specific ACG concept, such as a character, style, or scene, we recommend users choose tags from the and replace underscores in the Danbooru tags with spaces to ensure the model accurately understands your needs. For example, bishop_(chess) should be written as bishop (chess), and in inference tools like AUTOMATIC1111 WebUI that use parentheses to weight prompt, all parentheses within the tags should be escaped, i.e., bishop \(chess\). Tag Ordering Including AWA Diffusion, most diffusion models better understand logically ordered tags. While tag ordering is not mandatory, it can help the model better understand your needs. Generally, the earlier the tag in the order, the greater its impact on generation. Below is an example of tag ordering. The example organizes the order of tags, prepends and because style and subject are the most important to the image. Subsequently, other tags are added in order of importance. Lastly, aesthetic tags and quality tags are positioned at the end to further emphasize the aesthetics of the image: art style (by xxx) -> character (1 frieren (sousou no frieren)) -> race (elf) -> composition (cowboy shot) -> painting style (impasto) -> theme (fantasy theme) -> main environment (in the forest, at day) -> background (gradient background) -> action (sitting on ground) -> expression (expressionless) -> main characteristics (white hair) -> other characteristics (twintails, green eyes, parted lip) -> clothing (wearing a white dress) -> clothing accessories (frills) -> other items (holding a magic wand) -> secondary environment (grass, sunshine) -> aesthetics (beautiful color, detailed) -> quality (best quality) -> secondary description (birds, cloud, butterfly) Tag order is not set in stone. Flexibility in writing prompt can yield better results. For example, if the effect of a concept (such as style) is too strong and detracts from the aesthetic appeal of the image, you can move it to a later position to reduce its impact. Negative Prompt Negative prompt are not necessary for AWA Diffusion. If you use negative prompt, it is not the case that the more negative prompt, the better. They should be as concise as possible and easily recognizable by the model. Too many negative words may lead to poorer generation results. Here are some recommended scenarios for using negative prompt: - Watermark: signature, logo, artist name; - Quality: worst quality, lowres, ugly, abstract; - Style: real life, 3d, celluloid, sketch, draft; - Human anatomy: deformed hand, fused fingers, extra limbs, extra arms, missing arm, extra legs, missing leg, extra digits, fewer digits. Trigger Words Add trigger words to your prompts to inform the model about the concept you want to generate. Trigger words can include character names, artistic styles, scenes, actions, quality, etc. Attention: See the Model Details of each version for full lists of trigger words. Tips for Trigger Word - Typos: The model is very sensitive to the spelling of trigger words. Even a single letter difference can cause a trigger to fail or lead to unexpected results. - Bracket Escaping: Pay attention