model_index.json

{
  "_class_name": "BlipDiffusionPipeline",
  "_diffusers_version": "0.18.0.dev0",
  "ctx_begin_pos": 2,
  "image_processor": [
    "blip_diffusion",
    "BlipImageProcessor"
  ],
  "mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "qformer": [
    "blip_diffusion",
    "Blip2QFormerModel"
  ],
  "scheduler": [
    "diffusers",
    "PNDMScheduler"
  ],
  "std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "text_encoder": [
    "blip_diffusion",
    "ContextCLIPTextModel"
  ],
  "tokenizer": [
    "transformers",
    "CLIPTokenizer"
  ],
  "unet": [
    "diffusers",
    "UNet2DConditionModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKL"
  ]
}