Cornflower is a comprehensive painting model based on StableDiffusion, trained with specific styles of illustration and merged with multiple models, which is theoretically somewhat different from real-life human painters.
Since the Cornflower model contains multiple files, you need to place all the files in the appropriate locations.
The Cornflower model consists of three parts: Checkpoint, Hypernetwork, and Embedding.
Starting with v8, Hypernetwork and Embedding files for the current version will be given in the release notes as a direct link.
You need to put the three files in the corresponding locations and enable them after the installation is complete.
The following parameters are recommended, and the recommended sampler for the current release is DPM++ SDE Karras.
Steps: 20+ (12+ for preview)
Sampler: DPM++ SDE Karras
CFG scale: 7
Size: 640x960
Clip skip: 2
ENSD: 31337
art by Cornflower, dreamy, full body
(1girl, (long golden wavy hair),(red and white frilled bikini:1.2),(the girl is floating in the water),(seaweeds,fish,sunlight),shiny eyes,beautiful detailed eyes,elegant eyelashes,beautiful detailed face,(an extremely delicate and beautiful) , studio photography, extremely detailed wallpaper ,hair hangs down to the shoulder, eyes visible through hair ,eyelashes covered by hair,(small breasts))
Negative prompt: (worst quality, low quality:1.4) ,lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, username,blurry,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,mutated hands,polar lowres,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, ((Intricate clothes, too much lace, too much dacoration on clothes, ))
Cornflower X Feat. Offset Noise - Stylized Anime Model is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Toooajk. Derived from the powerful Stable Diffusion (SD 1.5) model, Cornflower X Feat. Offset Noise - Stylized Anime Model has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Cornflower X Feat. Offset Noise - Stylized Anime Model is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, mix, style.
With a rating of 4.95 and over 19 ratings, Cornflower X Feat. Offset Noise - Stylized Anime Model is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Cornflower X Feat. Offset Noise - Stylized Anime Model from here.
To use Cornflower X Feat. Offset Noise - Stylized Anime Model, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Cornflower X Feat. Offset Noise - Stylized Anime Model, check out our crash course in AI image generation.
Please download both the Hypernetwork file and the Embedding file for this version.
DPM2 a Karras is recommended.
Changelog:
As we all know, recently there were two new models of BasilMix and Abyss2 that greatly exceeded the previous level, so I mixed the Cornflower V6 basemodel and BasilMix model based on Abyss2's Block Merge method, with remarkable results.
You can now mount vae files without oversaturation issues, and v7 uses OrangeMix's vae by default.
The Phantom branch incorporates the style of the artist スイミン based on the V4 version of Hypernetwork. https://www.pixiv.net/users/78274245
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.