Concept Costume Designer is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user ivangarciafilho. Derived from the powerful Stable Diffusion (SD 1.5) model, Concept Costume Designer 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 Concept Costume Designer is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, character, girl.With a rating of 4.75 and over 4 ratings, Concept Costume Designer is a popular choice among users for generating high-quality images from text prompts.

Concept Charactor V1.02

conceptCharactorV102_v102.safetensors

v1.02

Model trained with 100 images ( 50 + 50 fliped ) using the Seek Art Mega model as a base model before training and later used to "fix" the damage caused by dreamboothing through multiple merges: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1315/seekart-mega">https://civarchive.com/models/1315/seekart-mega</a> Workflow and more samples with according tested artists: <a target="_blank" rel="ugc" href="https://www.artstation.com/artwork/2qPoAx">https://www.artstation.com/artwork/2qPoAx</a><ul><li>Trained with some empty backgrounds with different solid colors to easily produce removable backgrounds;</li><li>Stacked training with stacked merges using the base model to avoid loss of other artstyles;</li><li>Most of the trained images contains tattoos, jewelry, stamps, and detailed equipment of scifi fantasy fashion;</li><li>Trained with micro crops of large compositions and according original compositions to easyly insert the characters within scenarios;</li></ul>

CCDHT - Concept Character Designer - Oriental

The raw file already merged with <a target="_blank" rel="ugc" href="https://civitai.com/models/4398/protogen-infinity-official-release">Protogen</a> ( just for ease of use if you don't know how to merge models ), then, after that, another dreambooth training session to restore the lost artstyle.<ul><li>Inherited a bias towards anime style or comic book stylization, looks like an entire model trained on WLOP or Stanley Lau Artgerm;</li><li>Inherited triggering keywords from Protogen model;</li><li>Pretty resilient to incoherent anatomy features;</li><li>Pretty resilient to motifs/ tiling before reaching 864x864;</li></ul>

Files with SHA256: 08ee170f15cbdce53cad5ddaa1b3cee8fd4fce63498cbf43483c2138d80f888e