segmind / segmoe

Apache License 2.0
409 stars 24 forks source link

Support Colab and Local Storage #11

Open g29times opened 9 months ago

g29times commented 9 months ago

When I'm using a V100 GPU Google Colab ENV, here are two main problems:

ENV: image

  1. There is no way to cache for model files, so every time has to download very large model files, so as local env users. similar problem: https://github.com/segmind/segmoe/issues/10 image

  2. Finally, the official script run failed, with the information: The config attributes {'segmoe_config': {'base_model': 'SG161222/RealVisXL_V3.0', 'down_idx_start': 1, 'down_idx_end': 3, 'experts': [{'negative_prompt': '(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)', 'positive_prompt': 'aesthetic, cinematic, hands, portrait, photo, illustration, 8K, hyperdetailed, origami, man, woman, supercar', 'source_model': 'frankjoshua/juggernautXL_v8Rundiffusion'}, {'negative_prompt': '(octane render, render, drawing, anime, bad photo, bad photography:1.3), (worst quality, low quality, blurry:1.2), (bad teeth, deformed teeth, deformed lips), (bad anatomy, bad proportions:1.1), (deformed iris, deformed pupils), (deformed eyes, bad eyes), (deformed face, ugly face, bad face), (deformed hands, bad hands, fused fingers), morbid, mutilated, mutation, disfigured', 'positive_prompt': 'cinematic, portrait, photograph, instagram, fashion, movie, macro shot, 8K, RAW, hyperrealistic, ultra realistic,', 'source_model': 'SG161222/RealVisXL_V3.0'}, {'negative_prompt': 'Compression artifacts, bad art, worst quality, low quality, plastic, fake, bad limbs, conjoined, featureless, bad features, incorrect objects, watermark, ((signature):1.25), logo', 'positive_prompt': 'minimalist, illustration, award winning art, painting, impressionist, comic, colors, sketch, pencil drawing,', 'source_model': 'albertushka/albertushka_DynaVisionXL'}, {'negative_prompt': 'nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, blurry', 'positive_prompt': 'photograph f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K', 'source_model': 'frankjoshua/albedobaseXL_v13'}], 'moe_layers': 'all', 'num_experts': 4, 'num_experts_per_tok': 2, 'up_idx_end': 2, 'up_idx_start': 0}} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file. image

Vargol commented 9 months ago

Hi.

Colabs don't really have persistent storage. you can use a Google Drive if you've got the space You just need to mount it in the Colab make diffusers use the Google Drive for the transformers and hugginface cache How to do that can be googled easy enough.