--- library_name: diffusers pipeline_tag: text-to-image tags: - text-to-image - stable-diffusion - segmoe - merge - moe - sdxl --- This model is a segmoe merge of 4 models from civitAI: https://civitai.com/models/269232/aam-xl-anime-mix?modelVersionId=303526 https://civitai.com/models/194768/jib-mix-realistic-xl?modelVersionId=335740 https://civitai.com/models/118111/copax-timelessxl-sdxl10?modelVersionId=344540 https://civitai.com/models/119229/zavychromaxl?modelVersionId=320428 Merged using the great project at: https://github.com/segmind/segmoe To do something similar you can either follow the guide in readme or you can follow this blogpost: https://huggingface.co/blog/segmoe The setting I used: ``` base_model: https://civitai.com/api/download/models/320428 num_experts: 4 moe_layers: all num_experts_per_tok: 2 type: sdxl experts: - source_model: https://civitai.com/api/download/models/320428 positive_prompt: "RAW photo, photorealistic, film grain, candid camera, color graded cinematic, eye catchlights, atmospheric lighting, macro shot, skin pores, imperfections, natural." negative_prompt: " (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck" - source_model: https://civitai.com/api/download/models/303526?type=Model&format=SafeTensor&size=full&fp=fp16 positive_prompt: "1girl, mecha suit, samurai face mask, menpo, upper body, underboob, portrait, white orange armor, blonde shimmering hair, 8K, RAW, best quality, masterpiece, ultra high res, colorful, (medium wide shot), (dynamic perspective), sharp focus , (depth of field, bokeh:1.3), extremely detailed eyes and face, beautiful detailed eyes,large breasts,black gold, trimmed gear,In a futuristic weapons factory, ((masterpiece, best quality)), niji, from side, upper body, hips, anime style" negative_prompt: "(low quality, worst quality:1.4), negativeXL_D, cgi, text, signature, watermark, extra limbs" - source_model: https://civitai.com/api/download/models/335740?type=Model&format=SafeTensor&size=full&fp=fp32 positive_prompt: "cinematic photo Documentery Photo a brown bear in the Alaskan wilderness, discovery magazine, cinematic photorealistic, 8k uhd natural lighting, raw, rich, intricate details, key visual, atmospheric lighting, 35mm photograph, film, bokeh, professional, 4k, highly detailed . 35mm photograph, film, bokeh, professional, 4k, highly detailed" negative_prompt: "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, ((bokeh)) Deviantart, Deviantart, jpeg , (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)" - source_model: https://civitai.com/api/download/models/344540 positive_prompt: "a photo portrait of an aztec demon shaman zombie in the style of apocalypto" negative_prompt: "(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, long neck" ``` # Usage !pip install -U segmoe diffusers transformers from segmoe import SegMoEPipeline pipeline = SegMoEPipeline("eren23/sdxl-zavy-animemix-copax-jibmix-segmoe", device="cuda") prompt = "fantastic land canvas, knight cat standing next to a purple medieval village wall" negative_prompt = "nsfw, bad quality, worse quality" img = pipeline( prompt=prompt, negative_prompt=negative_prompt, height=512, width=512, num_inference_steps=30, guidance_scale=7.5, ).images[0] img.save("image.png") # Example Images ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6236052a12982296495f4674/uaPwC6ZLPSJVsKToni9qc.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6236052a12982296495f4674/aaLvgR2QB0o9EnPAYWO6B.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6236052a12982296495f4674/EOxG3c4C0NNWDZxXe3bGG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6236052a12982296495f4674/mXlVAJYEEcuG6V_TXBN8Q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6236052a12982296495f4674/um6kxh83Nxo7NcGvDoKme.png)