| {"target": "ldm.modules.diffusionmodules.openaimodel3d.UNetModel3D", "params": {"image_size": 64, "in_channels": 4, "out_channels": 4, "model_channels": 320, "attention_resolutions": [4, 2, 1], "num_res_blocks": 2, "channel_mult": [1, 2, 4, 4], "num_heads": 8, "transformer_depth": 1, "context_dim": 768, "fuser_type": "gatedSA", "use_checkpoint": true, "grounding_tokenizer": {"target": "ldm.modules.diffusionmodules.text_grounding_net.PositionNet", "params": {"in_dim": 768, "out_dim": 768}}, "inpaint_mode": true}} |