diff --git a/README.md b/README.md index 412374fae3e17e90adbe3f1e6757606be3ac288a..690722461c11e8f4ae8ffe5eb816a57c6ff060a1 100644 --- a/README.md +++ b/README.md @@ -21,6 +21,12 @@ You can find some example images in the following. ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) +![img_4](./image_4.png) +![img_5](./image_5.png) +![img_6](./image_6.png) +![img_7](./image_7.png) +![img_8](./image_8.png) +![img_9](./image_9.png) DreamBooth for the text encoder was enabled: True. diff --git a/checkpoint-100/optimizer.bin b/checkpoint-100/optimizer.bin index b2a6041841c6c4ad474f38e4f27fa9bf1d0eded6..e0d6383b7cf34404fa71027fc3f840f7be1268d3 100644 --- a/checkpoint-100/optimizer.bin +++ b/checkpoint-100/optimizer.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6c9b3b82125543ab364428942b0a5360d6672c8483745c87fdcf9acd13a9e3be +oid sha256:b9cdcae9c34a21495cac86b8eb7599be05f57f0f12b2ac4deac669a16e051e05 size 7861518391 diff --git a/checkpoint-100/random_states_0.pkl b/checkpoint-100/random_states_0.pkl index 40fa82384c3f7758633e78ce5cd4bda36c4d5ba1..3d69b2c04ffd235ae54279512a47f578c8c381b3 100644 --- a/checkpoint-100/random_states_0.pkl +++ b/checkpoint-100/random_states_0.pkl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c5b9f5a2fb795ba4a2cf81b8d19e3bcd792b93040bf9ae2836100f21429ccd80 -size 21795 +oid sha256:bbfc74749906d54d818bef7a60934cdc4525a56a1ff463e2df8cbc30e5cb10ec +size 21731 diff --git a/checkpoint-100/text_encoder/pytorch_model.bin b/checkpoint-100/text_encoder/pytorch_model.bin index 5c2a9a4f7bd2e625e41eabd515f5e3f6342cc892..e835c19f085e64e27139b20bc569dc0a6e204d37 100644 --- a/checkpoint-100/text_encoder/pytorch_model.bin +++ b/checkpoint-100/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fd552c9f282683c39f4b318582f8d935140303dc0a001571f4d8894c55f9be64 +oid sha256:033c6ea978fcc70b541774674a52813d06915a3f83c7da13546d385795a4ae1b size 492309793 diff --git a/checkpoint-100/unet/diffusion_pytorch_model.bin b/checkpoint-100/unet/diffusion_pytorch_model.bin index fee74515a574fb1567db1f47bbf2e77501c45d98..94a0a9f1d6fb4fcfe782a690b226ab52e96bf414 100644 --- a/checkpoint-100/unet/diffusion_pytorch_model.bin +++ b/checkpoint-100/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f96850a9b968005f74357e621562e3d244c777dc842310494c019d3e37583320 +oid sha256:f9eb34bceeb92eafd0f115395319aee0768bac1b7015f07c2ba7363c5bd59d65 size 3438433573 diff --git a/checkpoint-1000/optimizer.bin b/checkpoint-1000/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c393c6c60fc29fb0706c373738e5836f29f4a92 --- /dev/null +++ b/checkpoint-1000/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf159df8572044f2ae20979ec0e54acee4cd6944d595a752445fdf3673b3458 +size 7861518391 diff --git a/checkpoint-1000/random_states_0.pkl b/checkpoint-1000/random_states_0.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e325815d69b7fb5599a111b0cf8cd563bb916501 --- /dev/null +++ b/checkpoint-1000/random_states_0.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b421b6ee1f79e46631a2d74f79bc92ff3e404ea899e85d52e80220f249354d5 +size 21795 diff --git a/checkpoint-1000/scheduler.bin b/checkpoint-1000/scheduler.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bd9cb24d167f6026aae34f46dc35b5a87306982 --- /dev/null +++ b/checkpoint-1000/scheduler.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0644a1ab1e0778793c834ae4d669074454997c3ac30db77676a2acc6f518e66f +size 563 diff --git a/checkpoint-1000/text_encoder/config.json b/checkpoint-1000/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a0d52dd3090bcfd11033449974b11b3c153219b8 --- /dev/null +++ b/checkpoint-1000/text_encoder/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "eos_token_id": 2, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 1, + "projection_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.30.1", + "vocab_size": 49408 +} diff --git a/checkpoint-1000/text_encoder/pytorch_model.bin b/checkpoint-1000/text_encoder/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6ccd5226077798954844bbea2835cede6ca74cf --- /dev/null +++ b/checkpoint-1000/text_encoder/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ccf6b0d381a81f4d13b5650a7e4506781983813935a4bd8dfc593045aa9b70 +size 492309793 diff --git a/checkpoint-1000/unet/config.json b/checkpoint-1000/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bad8981ac814db95d72182ea5de86ffac85019d --- /dev/null +++ b/checkpoint-1000/unet/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.18.0.dev0", + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "attention_head_dim": 8, + "block_out_channels": [ + 320, + 640, + 1280, + 1280 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 768, + "cross_attention_norm": null, + "down_block_types": [ + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "DownBlock2D" + ], + "downsample_padding": 1, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 9, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "up_block_types": [ + "UpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/checkpoint-1000/unet/diffusion_pytorch_model.bin b/checkpoint-1000/unet/diffusion_pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..a982651271f4cedad70b8d4613b3f18bb5d9305e --- /dev/null +++ b/checkpoint-1000/unet/diffusion_pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edd4fb7a7b34fea07bbb3de0b66451b356eb9c4d5f715fc68c219ce6bc87475 +size 3438433573 diff --git a/checkpoint-200/optimizer.bin b/checkpoint-200/optimizer.bin index ffce04560147e6b68c5c62f8a3183ca518e07331..1175f966f3d3a0b8935f9d404071e0f44f222204 100644 --- a/checkpoint-200/optimizer.bin +++ b/checkpoint-200/optimizer.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b1c016295540a60925db2f33028a26a9175589cbbc38fd31d24fb89e0e0208d0 +oid sha256:a79546b1b9ba1630a60cd5d20a8e08c50e25d8e9b63dc06c9e50266a149b2ed2 size 7861518391 diff --git a/checkpoint-200/random_states_0.pkl b/checkpoint-200/random_states_0.pkl index f357def5eea33ff51f63fb444172bc8aaea5d631..92bd584d6c828d80e100e33e04322eb066b5be00 100644 --- a/checkpoint-200/random_states_0.pkl +++ b/checkpoint-200/random_states_0.pkl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:08177a6cf65cc86e2015e7e8c234dc583c565fba84e587fe309f7ddb156c65c4 +oid sha256:584cedf11f1c72258f4ebfff8dc60a71de7735dff304b3923af5472c6f23edab size 21731 diff --git a/checkpoint-200/text_encoder/pytorch_model.bin b/checkpoint-200/text_encoder/pytorch_model.bin index f73e582016b21ebe86b1329972383b2c371c5d10..ae93d5f6dc3ce1e50b15eb95d96112a08dc9066a 100644 --- a/checkpoint-200/text_encoder/pytorch_model.bin +++ b/checkpoint-200/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:55835fadfd90eed805878c02168ad574122bb5911614f54983931e59a978fc1a +oid sha256:c91fb227408b8f58ac0b3cc670c237be68d9463e21606b289e6281cf30586ceb size 492309793 diff --git a/checkpoint-200/unet/diffusion_pytorch_model.bin b/checkpoint-200/unet/diffusion_pytorch_model.bin index d0032d1c52bb653a5acc5c120abbea99b6379f71..c9c58bc2166d0105b4feb4d223cb217b07443553 100644 --- a/checkpoint-200/unet/diffusion_pytorch_model.bin +++ b/checkpoint-200/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:47cd68e54cb3f9b514335c9296ba4e4d797dacc5fb47390f50a06869509295c1 +oid sha256:e7d8e02d69a3e0fc7f2ac6a105509b68fa42c9bb559d35968403c8d2d93bf94a size 3438433573 diff --git a/checkpoint-300/optimizer.bin b/checkpoint-300/optimizer.bin index e63656adde03e20f0e327f92b85ba5de1ea205fb..9f0ed5026b69b6903d2f1bd996bb22197077a4e4 100644 --- a/checkpoint-300/optimizer.bin +++ b/checkpoint-300/optimizer.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5c55634d84d128a98cd7530deac21ac2b5354ca2c81835384fbf75a80df3379b +oid sha256:7ac151612b879371436ed814793b63462617ecb98b24ea5d83e4b673f69f1ffa size 7861518391 diff --git a/checkpoint-300/random_states_0.pkl b/checkpoint-300/random_states_0.pkl index b343ebeb98b9cf4b16270d4fa32ae04a312bedc4..204f6835eaf76fc735f51c70a2d59350950242ac 100644 --- a/checkpoint-300/random_states_0.pkl +++ b/checkpoint-300/random_states_0.pkl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7bfe3c5fddcfd0ff47f8cb33cb506699ca86a3e1c392ce9da2386af5d4d46725 -size 21795 +oid sha256:51e804180346038280eb6dd96d31b024283a2943deb6eac5318a6d71469e5e13 +size 21731 diff --git a/checkpoint-300/text_encoder/pytorch_model.bin b/checkpoint-300/text_encoder/pytorch_model.bin index 9701c85e1bf2db9d620e54804fb20f723a05aada..ad8116cd8db6132a914afe1a1d001583e1828295 100644 --- a/checkpoint-300/text_encoder/pytorch_model.bin +++ b/checkpoint-300/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e6624e48f8e2e300e937cdd7712f516eee247b0c679fbea0fd86c2917c765e9e +oid sha256:8fee07ec736d56a0a20faafe8ae6ab8aca66744e73ce359adbf1f991c5e3df47 size 492309793 diff --git a/checkpoint-300/unet/diffusion_pytorch_model.bin b/checkpoint-300/unet/diffusion_pytorch_model.bin index 0a236b3164c3e9c1a5ea035cfda0f893daf5e964..2e6c4ff7ef44e1beb7e1c343cc4f0502b0d315c8 100644 --- a/checkpoint-300/unet/diffusion_pytorch_model.bin +++ b/checkpoint-300/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f7d2d0c269bb73cf942e91b867715ede397e886ecc9098697633fb7a6a33cca2 +oid sha256:ffc2cc0675d4313d69c8861d4cb21be1bc86e335a7f4eb17fc256f832e4f4ce6 size 3438433573 diff --git a/checkpoint-400/optimizer.bin b/checkpoint-400/optimizer.bin index 543f76f5079edfc95b1406cf9eef459cce0c8504..d5b56c31b6cc7dd771e7746f7a4220a4cefe4d65 100644 --- a/checkpoint-400/optimizer.bin +++ b/checkpoint-400/optimizer.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:430bbf9e0cacd0ed856518612101115b110077a51f1baaea208bae6fbf3fd66a +oid sha256:d777be159ac0f017aff182179198c695905a6a73ebc07c1ff2e70653ee2d8463 size 7861518391 diff --git a/checkpoint-400/random_states_0.pkl b/checkpoint-400/random_states_0.pkl index 406fc0ca4679b9785688ef8ee4b3707ea377d42b..6c6e3043589b2832434b02bb7b3203833b5f4716 100644 --- a/checkpoint-400/random_states_0.pkl +++ b/checkpoint-400/random_states_0.pkl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a45068c69542fa72ffab89a34037f9690e1e4e42dd546d4f68466c015c061d86 +oid sha256:c32de1cc1cf365d9fb8e115d73b57f61f82b781f2d1ec1a6ac5ce3be768a72d5 size 21731 diff --git a/checkpoint-400/text_encoder/pytorch_model.bin b/checkpoint-400/text_encoder/pytorch_model.bin index fde5217fee428d68b7ecf9bad12c0151f498d2ca..4d14f45b36df65e0469ba0679b91ad68a0d12741 100644 --- a/checkpoint-400/text_encoder/pytorch_model.bin +++ b/checkpoint-400/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:50796fc47c474e9d34aceaa44b3a7b7a1009d1984912595e806e0bca14df1668 +oid sha256:6ea1ae6cc7fe6b23ce6da4452ab310ced154932f1435db219d6102766aff05ce size 492309793 diff --git a/checkpoint-400/unet/diffusion_pytorch_model.bin b/checkpoint-400/unet/diffusion_pytorch_model.bin index 319917ed66f89824d1a5dc0a479259f5d1d37d35..50c5cd8e3fb97fd99c3dbf5987acf619a507a053 100644 --- a/checkpoint-400/unet/diffusion_pytorch_model.bin +++ b/checkpoint-400/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3b720846458693d5e95aaa9a8c6119f7d32478a270d112e9777db51ad50978a6 +oid sha256:707c1b0765d912417ea9481270e6df87f1e6612bf6539c47a89efc0119ac5483 size 3438433573 diff --git a/checkpoint-500/optimizer.bin b/checkpoint-500/optimizer.bin index 996038566eda43eeb16a87955ed5d7481a58fe52..b85dcebecc3c3eae9a82a657cd41ea957562e0a6 100644 --- a/checkpoint-500/optimizer.bin +++ b/checkpoint-500/optimizer.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2e97a49435a846ef22e1da0052d893c1b8a42115fcfe5c2342e34f51ce05b02b +oid sha256:0bd67142d40a8c0ca9373ff651e4f584fa80607a785bc88055e7633841023fab size 7861518391 diff --git a/checkpoint-500/random_states_0.pkl b/checkpoint-500/random_states_0.pkl index fdea58dd2270afa9ea6f032a4fe92bd59f78fd2a..6c892ede5c499bed31587bc5afdc6d98db576175 100644 --- a/checkpoint-500/random_states_0.pkl +++ b/checkpoint-500/random_states_0.pkl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d3b4fd577f3950349a1f96ca5c869e0dd9db4d8d7c7ef1395e40fe548d539898 -size 21795 +oid sha256:44f13ea7ce01798ae7e9b381f92a2e7e65f689583a8be7732e649d429e2eee52 +size 21731 diff --git a/checkpoint-500/text_encoder/pytorch_model.bin b/checkpoint-500/text_encoder/pytorch_model.bin index ec0719d72c9891a0e4134769e30efd91fa53e285..c8bab895c53b7e5d89ef82019e55cddb1c966d98 100644 --- a/checkpoint-500/text_encoder/pytorch_model.bin +++ b/checkpoint-500/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9df435e6783b543f04a80a8c72430ccaab9fe3c70e5ad8290866e00a2539fdf0 +oid sha256:029c0bc08b89174c45170be3dd82a128b7fcf2ef8715c751adc66b138aee4117 size 492309793 diff --git a/checkpoint-500/unet/diffusion_pytorch_model.bin b/checkpoint-500/unet/diffusion_pytorch_model.bin index 655f15d16f117249fb6426f9b4d3315f64688dab..a1761becdacb374568e3d3a5fc9fb81f3f8c8e64 100644 --- a/checkpoint-500/unet/diffusion_pytorch_model.bin +++ b/checkpoint-500/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c752dd51ab0ec448c91b8ed4bedba496153f698feeb473c23fccfa0cc9ec92b3 +oid sha256:e17d0543a86776e4f219c034680d4b9c3d659e6bacb08bfb82fedb37866c3319 size 3438433573 diff --git a/checkpoint-600/optimizer.bin b/checkpoint-600/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..8110ee685fc60b30389023df1e16b7921fa1e1fd --- /dev/null +++ b/checkpoint-600/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8e6aaeae69d823d2837450a0309e7b649a0f3d2ae833fb8e686319eb4c9db9 +size 7861518391 diff --git a/checkpoint-600/random_states_0.pkl b/checkpoint-600/random_states_0.pkl new file mode 100644 index 0000000000000000000000000000000000000000..def33689b54fda95e687b413423c600535e6094f --- /dev/null +++ b/checkpoint-600/random_states_0.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5b9ce1499e35f27a791352754605ca3fe45e7a262ba334f23edf4cdbd3dff0 +size 21731 diff --git a/checkpoint-600/scheduler.bin b/checkpoint-600/scheduler.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c02e30366192aaef47f03294de9a4541ea1be13 --- /dev/null +++ b/checkpoint-600/scheduler.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6492fd78beea4599bf12b314f0ab36e8c96cbdf0cb6227ce67135a6c16c2134e +size 563 diff --git a/checkpoint-600/text_encoder/config.json b/checkpoint-600/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a0d52dd3090bcfd11033449974b11b3c153219b8 --- /dev/null +++ b/checkpoint-600/text_encoder/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "eos_token_id": 2, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 1, + "projection_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.30.1", + "vocab_size": 49408 +} diff --git a/checkpoint-600/text_encoder/pytorch_model.bin b/checkpoint-600/text_encoder/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfcc93dfb13a5d6afc42f5fd161e4a2bcb1d0b68 --- /dev/null +++ b/checkpoint-600/text_encoder/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df363d8325ab4adf02a871347f6f0df99e4905ed1e4fba950f6de0158ef791b9 +size 492309793 diff --git a/checkpoint-600/unet/config.json b/checkpoint-600/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bad8981ac814db95d72182ea5de86ffac85019d --- /dev/null +++ b/checkpoint-600/unet/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.18.0.dev0", + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "attention_head_dim": 8, + "block_out_channels": [ + 320, + 640, + 1280, + 1280 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 768, + "cross_attention_norm": null, + "down_block_types": [ + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "DownBlock2D" + ], + "downsample_padding": 1, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 9, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "up_block_types": [ + "UpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/checkpoint-600/unet/diffusion_pytorch_model.bin b/checkpoint-600/unet/diffusion_pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..54840947b3ce221abe5ef9970c6cc8f28213513e --- /dev/null +++ b/checkpoint-600/unet/diffusion_pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b39eff10ad3646e7293b1dd243d646a8c38eadc424ff6c0314b4acd410a8e8 +size 3438433573 diff --git a/checkpoint-700/optimizer.bin b/checkpoint-700/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f81567aa5841e8a7c3e0b8f3b563fcbe56badcb --- /dev/null +++ b/checkpoint-700/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a79168a85af65bebe36c3d2bed57375115baa16075d3b5b36f1015f430c450 +size 7861518391 diff --git a/checkpoint-700/random_states_0.pkl b/checkpoint-700/random_states_0.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6bc4829069bb26c7ddde5e25765c9b58ec7e9040 --- /dev/null +++ b/checkpoint-700/random_states_0.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1dd3e3d2b9f5282df0eecd17a923d63ab5567bb239c34321df61903d1d3724 +size 21731 diff --git a/checkpoint-700/scheduler.bin b/checkpoint-700/scheduler.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2a39fdcfe204004fc730ac3aa073fc3527afb65 --- /dev/null +++ b/checkpoint-700/scheduler.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7de2bf12d7f35e364254cf2c5c33dc4f0c5a8c385dab199bfe71f5960f4ea4f +size 563 diff --git a/checkpoint-700/text_encoder/config.json b/checkpoint-700/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a0d52dd3090bcfd11033449974b11b3c153219b8 --- /dev/null +++ b/checkpoint-700/text_encoder/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "eos_token_id": 2, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 1, + "projection_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.30.1", + "vocab_size": 49408 +} diff --git a/checkpoint-700/text_encoder/pytorch_model.bin b/checkpoint-700/text_encoder/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..413138609bcb7f7d6620f9a8594a59b45b34684f --- /dev/null +++ b/checkpoint-700/text_encoder/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41621c793d55a2ab9b18196f42b14bfca2551eb43f615b0c7ee4811f2234ccf7 +size 492309793 diff --git a/checkpoint-700/unet/config.json b/checkpoint-700/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bad8981ac814db95d72182ea5de86ffac85019d --- /dev/null +++ b/checkpoint-700/unet/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.18.0.dev0", + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "attention_head_dim": 8, + "block_out_channels": [ + 320, + 640, + 1280, + 1280 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 768, + "cross_attention_norm": null, + "down_block_types": [ + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "DownBlock2D" + ], + "downsample_padding": 1, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 9, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "up_block_types": [ + "UpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/checkpoint-700/unet/diffusion_pytorch_model.bin b/checkpoint-700/unet/diffusion_pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..4239d283ede857cc2e67202be21ad004478e1c6e --- /dev/null +++ b/checkpoint-700/unet/diffusion_pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614d811899a0ad5f0fceb2d6aaf1227e592f0cc54aad47a9d19f6babab1931bf +size 3438433573 diff --git a/checkpoint-800/optimizer.bin b/checkpoint-800/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..6793766c0ef03ca955e8435842c51395423257e6 --- /dev/null +++ b/checkpoint-800/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71dc3c5223c71567da0beb895fe79c4367f5928beb7f036d0fbbf5bc419560d9 +size 7861518391 diff --git a/checkpoint-800/random_states_0.pkl b/checkpoint-800/random_states_0.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dd66abca3867e270eb9d41eecd6d7fb7b94dfa63 --- /dev/null +++ b/checkpoint-800/random_states_0.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21291a3fd7810625c6be6574a07c24e552d2d8b114f69b550c78890494952cf +size 21731 diff --git a/checkpoint-800/scheduler.bin b/checkpoint-800/scheduler.bin new file mode 100644 index 0000000000000000000000000000000000000000..97daa6c71a214931ef142a3005fa225f87f6b020 --- /dev/null +++ b/checkpoint-800/scheduler.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16047bd3cd0ff3474061593250d9ba035f493769125882fc3cd97e41a887654b +size 563 diff --git a/checkpoint-800/text_encoder/config.json b/checkpoint-800/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a0d52dd3090bcfd11033449974b11b3c153219b8 --- /dev/null +++ b/checkpoint-800/text_encoder/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "eos_token_id": 2, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 1, + "projection_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.30.1", + "vocab_size": 49408 +} diff --git a/checkpoint-800/text_encoder/pytorch_model.bin b/checkpoint-800/text_encoder/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..a03cb80554a115b832a5bbfb4e35f4508e60de96 --- /dev/null +++ b/checkpoint-800/text_encoder/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a5a9c2450564f21333731a3efb752b2647375a0a98affdcf1e39bcfe67405a +size 492309793 diff --git a/checkpoint-800/unet/config.json b/checkpoint-800/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bad8981ac814db95d72182ea5de86ffac85019d --- /dev/null +++ b/checkpoint-800/unet/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.18.0.dev0", + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "attention_head_dim": 8, + "block_out_channels": [ + 320, + 640, + 1280, + 1280 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 768, + "cross_attention_norm": null, + "down_block_types": [ + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "DownBlock2D" + ], + "downsample_padding": 1, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 9, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "up_block_types": [ + "UpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/checkpoint-800/unet/diffusion_pytorch_model.bin b/checkpoint-800/unet/diffusion_pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..b65f3c2e8d3ade6cde2e3d0a065f965cdcac9c2f --- /dev/null +++ b/checkpoint-800/unet/diffusion_pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489f6ceb0526ece8dea7121405998812f2184341c8a8379e68885a7f194c1e53 +size 3438433573 diff --git a/checkpoint-900/optimizer.bin b/checkpoint-900/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..c4a5cc110ae15f4b4ae78bce8a52bfc11f2ab3eb --- /dev/null +++ b/checkpoint-900/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3673b29f8d19e5b1aa0c07193bf51fb1bf249e079d6bb834b7b03a32ba6ff137 +size 7861518391 diff --git a/checkpoint-900/random_states_0.pkl b/checkpoint-900/random_states_0.pkl new file mode 100644 index 0000000000000000000000000000000000000000..da97e7ac4331cf505543b2aae7467250cecab19c --- /dev/null +++ b/checkpoint-900/random_states_0.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a1f14cd33dd9826f013220f5c9f55f14454c571d78f73cf0e37c8da2b2728f +size 21731 diff --git a/checkpoint-900/scheduler.bin b/checkpoint-900/scheduler.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a7e4b20e62dd70242919fd6db94ac7ab6be9ca1 --- /dev/null +++ b/checkpoint-900/scheduler.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec4b03d1981adf2f87c20e4d7a3c7f9b7801311c9456b3177757362205c779e +size 563 diff --git a/checkpoint-900/text_encoder/config.json b/checkpoint-900/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a0d52dd3090bcfd11033449974b11b3c153219b8 --- /dev/null +++ b/checkpoint-900/text_encoder/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "eos_token_id": 2, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 1, + "projection_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.30.1", + "vocab_size": 49408 +} diff --git a/checkpoint-900/text_encoder/pytorch_model.bin b/checkpoint-900/text_encoder/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..a217fdf1d29a66e8b8606a7ca75fa4e212920fed --- /dev/null +++ b/checkpoint-900/text_encoder/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d6b0d537a88afff3da6462c054883f38b71451ea8d89bce2a60c65a0f62576e +size 492309793 diff --git a/checkpoint-900/unet/config.json b/checkpoint-900/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bad8981ac814db95d72182ea5de86ffac85019d --- /dev/null +++ b/checkpoint-900/unet/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.18.0.dev0", + "_name_or_path": "runwayml/stable-diffusion-inpainting", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "attention_head_dim": 8, + "block_out_channels": [ + 320, + 640, + 1280, + 1280 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 768, + "cross_attention_norm": null, + "down_block_types": [ + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "CrossAttnDownBlock2D", + "DownBlock2D" + ], + "downsample_padding": 1, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 9, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "up_block_types": [ + "UpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D", + "CrossAttnUpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/checkpoint-900/unet/diffusion_pytorch_model.bin b/checkpoint-900/unet/diffusion_pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..615d576c586027409a77a45d736971546ee3a4cf --- /dev/null +++ b/checkpoint-900/unet/diffusion_pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dea4e67ec109a489fb6fd238393b147fad88a1f44553af13188743f9c6bffcf1 +size 3438433573 diff --git a/image_0.png b/image_0.png index eceb84d26e7e5c0c81a3207a5b2baebbdb0829db..82df49c09106d86061457c7119acdfba7bb76ca5 100644 Binary files a/image_0.png and b/image_0.png differ diff --git a/image_1.png b/image_1.png index 6003c47414ec990a67c3c018ae4e729323bcb530..cadb6e25cf7d51418425098143a67e07156a70b7 100644 Binary files a/image_1.png and b/image_1.png differ diff --git a/image_2.png b/image_2.png index 07e9915fb8475ac208733335b9793cf02dd86e69..7f04ae98c3fb04e71532f75ec593a779523bdc25 100644 Binary files a/image_2.png and b/image_2.png differ diff --git a/image_3.png b/image_3.png index 55dc946d82d97ba5fe3947338a90ba48685f189c..f25ce768016a79f2a270741311bfffc589594abb 100644 Binary files a/image_3.png and b/image_3.png differ diff --git a/image_4.png b/image_4.png new file mode 100644 index 0000000000000000000000000000000000000000..6bed7668c9cc2dd64fe85a9082baaafc64821f27 Binary files /dev/null and b/image_4.png differ diff --git a/image_5.png b/image_5.png new file mode 100644 index 0000000000000000000000000000000000000000..a9608eb7c5d1d6164d92b8a760b7115ed8b7ff3f Binary files /dev/null and b/image_5.png differ diff --git a/image_6.png b/image_6.png new file mode 100644 index 0000000000000000000000000000000000000000..b9099be5051aa76081347553550592a514836d25 Binary files /dev/null and b/image_6.png differ diff --git a/image_7.png b/image_7.png new file mode 100644 index 0000000000000000000000000000000000000000..7e652e79cd7f771b507eca80d26f453a8849c2ef Binary files /dev/null and b/image_7.png differ diff --git a/image_8.png b/image_8.png new file mode 100644 index 0000000000000000000000000000000000000000..8688adf4c8cbb60c34873761b87af30f3788ac9d Binary files /dev/null and b/image_8.png differ diff --git a/image_9.png b/image_9.png new file mode 100644 index 0000000000000000000000000000000000000000..24189239b89bd354e9e354cac659c312133d7d55 Binary files /dev/null and b/image_9.png differ diff --git a/model_index.json b/model_index.json index c575ea874dccfe718a5ad380b2d61b63bf459608..067a8940c5ae81fcdc81ca111469c36f62ba31c7 100644 --- a/model_index.json +++ b/model_index.json @@ -7,8 +7,8 @@ ], "requires_safety_checker": true, "safety_checker": [ - "stable_diffusion", - "StableDiffusionSafetyChecker" + null, + null ], "scheduler": [ "diffusers", diff --git a/text_encoder/pytorch_model.bin b/text_encoder/pytorch_model.bin index ec0719d72c9891a0e4134769e30efd91fa53e285..f6ccd5226077798954844bbea2835cede6ca74cf 100644 --- a/text_encoder/pytorch_model.bin +++ b/text_encoder/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9df435e6783b543f04a80a8c72430ccaab9fe3c70e5ad8290866e00a2539fdf0 +oid sha256:f9ccf6b0d381a81f4d13b5650a7e4506781983813935a4bd8dfc593045aa9b70 size 492309793 diff --git a/unet/diffusion_pytorch_model.bin b/unet/diffusion_pytorch_model.bin index 655f15d16f117249fb6426f9b4d3315f64688dab..a982651271f4cedad70b8d4613b3f18bb5d9305e 100644 --- a/unet/diffusion_pytorch_model.bin +++ b/unet/diffusion_pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c752dd51ab0ec448c91b8ed4bedba496153f698feeb473c23fccfa0cc9ec92b3 +oid sha256:6edd4fb7a7b34fea07bbb3de0b66451b356eb9c4d5f715fc68c219ce6bc87475 size 3438433573