VAE

AuraFlow v0.1 is the fully open-sourced flow-based text-to-image generation model.AuraFlow v0.2 is the fully open-sourced flow-based text-to-image generation model. The model w...

The current model is based on flux.1[dev] for clip_l model merging.The clip_l model using the following model:https://civitai.com/models/338712/pvc-style-modelmovable-figure-mo...

Different art style, flat colors , anime based, and hard lines. i hope you like it. Any question, bug or everything you can ask me on discord as @wolf2725 El Wolfo ...

Lorafys Manga Mix is a Checkpoint Merge aiming to capture the typical manga style. This involves knowledge about popular Anime and Manga characters, aswell as Gaming characters...

Lorafys Manga Mix is a Checkpoint Merge aiming to capture the typical manga style. This involves knowledge about popular Anime and Manga characters, aswell as Gaming characters...

A series of specific use case VAEs to use for Pony (or SDXL) models.Standard: Found HereNothing new to see here, the same as the one released by StabilityAI. Included here so t...

A series of specific use case VAEs to use for Pony (or SDXL) models.Standard:Nothing new to see here, the same as the one released by StabilityAI. Included here so that it may ...

国内用户低配置6g显存可运行XL模型forge-Webui-整合包，本地使用进335010757Q群Users of the V3 version can consider the scope of use by themselves but are prohibited from merging mo...

・実験的VAE・エンコーダーは調整していません・画像にRefinerは使用していません・NansException 描述: ・茶色い！・ぼやける！！・アップスケール推奨！！！・使い難い...

Please post images to the model page; all buzz earned goes towards training LORA for the communityStruggling with flux prompts? try my flux prompt craft GPT botDo you use the G...

・実験的VAE・エンコーダーは調整していません・画像にRefinerは使用していません・NansException 描述: ・F1の特徴と不具合が減りました・コントラストが高い ...

Please post images to the model page; all buzz earned goes towards training LORA for the communityStruggling with flux prompts? try my flux prompt craft GPT botDo you use the G...

Sharing this realistic portrait model with excellent color and light control, iteratively enhancing realism from my previous ClearMIX version,The glossy and beautiful realistic...

RealisticMy fist checkpoint!Enjoy!!!- negative prompt:(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, vaginas in breasts, ((monoch...

Domenica!!!!Try your prompt!1girl, warrior, many muscles, muscular body, wielding a cold weapon, random time, sexy posture, random room, looking at viewer, random hair color, b...

Epponina!Basic version:CFG scale: 3-9Sampling Step: 30-60Sampling Method: DPM++ 2M SDE Karras or Euler aADetailer ONExample prompt: (masterpiece,best quality:1.2), ultra reali...

Standalone VAE for SD3 描述: 训练词语: 名称: sd3VAE_...

? IntroductionKolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, ...

? IntroductionKolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, ...

? IntroductionKolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, ...