ptx0
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
02b28ff
| { | |
| "_class_name": "StableDiffusionPipeline", | |
| "_diffusers_version": "0.17.0.dev0", | |
| "feature_extractor": [ | |
| "transformers", | |
| "CLIPImageProcessor" | |
| ], | |
| "requires_safety_checker": false, | |
| "safety_checker": [ | |
| null, | |
| null | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "DDPMScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "CLIPTextModel" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "CLIPTokenizer" | |
| ], | |
| "unet": [ | |
| "diffusers", | |
| "UNet2DConditionModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKL" | |
| ] | |
| } | |