Hugging Face's logo

chenguolin
/
DiffSplat

Diffusers
Safetensors
Model card Files Community
1
linchenguo commited on
Commit
8ced305
·
1 Parent(s): 49d95ba

upload all ckpts

Browse files
Files changed (24) hide show
  1. README.md +9 -0
  2. elevest_gobj265k_b_C25/checkpoints/062160/model.safetensors +3 -0
  3. gsdiff_gobj83k_pas_fp16__render/checkpoints/013020/transformer_ema/config.json +40 -0
  4. gsdiff_gobj83k_pas_fp16__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors +3 -0
  5. gsdiff_gobj83k_pas_fp16_image__render/checkpoints/013020/transformer_ema/config.json +40 -0
  6. gsdiff_gobj83k_pas_fp16_image__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors +3 -0
  7. gsdiff_gobj83k_sd15__render/checkpoints/013020/unet_ema/config.json +78 -0
  8. gsdiff_gobj83k_sd15__render/checkpoints/013020/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. gsdiff_gobj83k_sd15__render__canny/checkpoints/065100/controlnet/config.json +51 -0
  10. gsdiff_gobj83k_sd15__render__canny/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors +3 -0
  11. gsdiff_gobj83k_sd15__render__depth/checkpoints/065100/controlnet/config.json +51 -0
  12. gsdiff_gobj83k_sd15__render__depth/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors +3 -0
  13. gsdiff_gobj83k_sd15__render__normal/checkpoints/065100/controlnet/config.json +51 -0
  14. gsdiff_gobj83k_sd15__render__normal/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors +3 -0
  15. gsdiff_gobj83k_sd15_image__render/checkpoints/013020/unet_ema/config.json +78 -0
  16. gsdiff_gobj83k_sd15_image__render/checkpoints/013020/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  17. gsdiff_gobj83k_sd35m__render/checkpoints/013020/transformer_ema/config.json +42 -0
  18. gsdiff_gobj83k_sd35m__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors +3 -0
  19. gsdiff_gobj83k_sd35m_image__render/checkpoints/013020/transformer_ema/config.json +42 -0
  20. gsdiff_gobj83k_sd35m_image__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors +3 -0
  21. gsrecon_gobj265k_cnp_even4/checkpoints/124320/model.safetensors +3 -0
  22. gsvae_gobj265k_sd/checkpoints/039030/model.safetensors +3 -0
  23. gsvae_gobj265k_sd3/checkpoints/039030/model.safetensors +3 -0
  24. gsvae_gobj265k_sdxl_fp16/checkpoints/039030/model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,12 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+ # [[ICLR 2025] DiffSplat](https://chenguolin.github.io/projects/DiffSplat)
5
+
6
+ This HuggingFace🤗 repo stores all pretrained model weights for the ICLR 2025 paper: "DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation".
7
+
8
+ For more details about usage, please refer to the [official GitHub repo](https://github.com/chenguolin/DiffSplat).
9
+
10
+ - Project page: https://chenguolin.github.io/projects/DiffSplat
11
+ - Code: https://github.com/chenguolin/DiffSplat
12
+ - Paper: https://arxiv.org/abs/2501.xxxxx
elevest_gobj265k_b_C25/checkpoints/062160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d9fc525eee9aabf9a125dba88345c2f3f74c567699dc8382ffd8856b508564
3
+ size 351157620
gsdiff_gobj83k_pas_fp16__render/checkpoints/013020/transformer_ema/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PixArtTransformerMV2DModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_pas_fp16/checkpoints/065100",
5
+ "activation_fn": "gelu-approximate",
6
+ "attention_bias": true,
7
+ "attention_head_dim": 72,
8
+ "attention_type": "default",
9
+ "caption_channels": 4096,
10
+ "cross_attention_dim": 1152,
11
+ "decay": 0.9999,
12
+ "double_self_attention": false,
13
+ "dropout": 0.0,
14
+ "in_channels": 10,
15
+ "input_concat_binary_mask": false,
16
+ "input_concat_plucker": true,
17
+ "interpolation_scale": 1,
18
+ "inv_gamma": 1.0,
19
+ "min_decay": 0.0,
20
+ "norm_elementwise_affine": false,
21
+ "norm_eps": 1e-06,
22
+ "norm_num_groups": 32,
23
+ "norm_type": "ada_norm_single",
24
+ "num_attention_heads": 16,
25
+ "num_embeds_ada_norm": 1000,
26
+ "num_layers": 28,
27
+ "num_vector_embeds": null,
28
+ "only_cross_attention": false,
29
+ "optimization_step": 13020,
30
+ "out_channels": 8,
31
+ "patch_size": 2,
32
+ "power": 0.75,
33
+ "sample_size": 32,
34
+ "upcast_attention": false,
35
+ "update_after_step": 0,
36
+ "use_additional_conditions": null,
37
+ "use_ema_warmup": true,
38
+ "use_linear_projection": false,
39
+ "view_concat_condition": false
40
+ }
gsdiff_gobj83k_pas_fp16__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3ec1d846638c432200551753fed719d4b580c1d20b86ada2d10b45c145dabb
3
+ size 2443603080
gsdiff_gobj83k_pas_fp16_image__render/checkpoints/013020/transformer_ema/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PixArtTransformerMV2DModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_pas_fp16_image_v/checkpoints/065100",
5
+ "activation_fn": "gelu-approximate",
6
+ "attention_bias": true,
7
+ "attention_head_dim": 72,
8
+ "attention_type": "default",
9
+ "caption_channels": 4096,
10
+ "cross_attention_dim": 1152,
11
+ "decay": 0.9999,
12
+ "double_self_attention": false,
13
+ "dropout": 0.0,
14
+ "in_channels": 11,
15
+ "input_concat_binary_mask": true,
16
+ "input_concat_plucker": true,
17
+ "interpolation_scale": 1,
18
+ "inv_gamma": 1.0,
19
+ "min_decay": 0.0,
20
+ "norm_elementwise_affine": false,
21
+ "norm_eps": 1e-06,
22
+ "norm_num_groups": 32,
23
+ "norm_type": "ada_norm_single",
24
+ "num_attention_heads": 16,
25
+ "num_embeds_ada_norm": 1000,
26
+ "num_layers": 28,
27
+ "num_vector_embeds": null,
28
+ "only_cross_attention": false,
29
+ "optimization_step": 13020,
30
+ "out_channels": 8,
31
+ "patch_size": 2,
32
+ "power": 0.75,
33
+ "sample_size": 32,
34
+ "upcast_attention": false,
35
+ "update_after_step": 0,
36
+ "use_additional_conditions": null,
37
+ "use_ema_warmup": true,
38
+ "use_linear_projection": false,
39
+ "view_concat_condition": true
40
+ }
gsdiff_gobj83k_pas_fp16_image__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b11efdea33128bef6a2688b3344da22ee6f2e91d0a47a2ebb0a6f1310186bd
3
+ size 2443621512
gsdiff_gobj83k_sd15__render/checkpoints/013020/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetMV2DConditionModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_sd15/checkpoints/065100",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlockMV2D",
27
+ "CrossAttnDownBlockMV2D",
28
+ "CrossAttnDownBlockMV2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 10,
39
+ "input_concat_binary_mask": false,
40
+ "input_concat_plucker": true,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlockMV2DCrossAttn",
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "optimization_step": 13020,
53
+ "out_channels": 4,
54
+ "power": 0.75,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 32,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": 1,
67
+ "up_block_types": [
68
+ "UpBlock2D",
69
+ "CrossAttnUpBlockMV2D",
70
+ "CrossAttnUpBlockMV2D",
71
+ "CrossAttnUpBlockMV2D"
72
+ ],
73
+ "upcast_attention": false,
74
+ "update_after_step": 0,
75
+ "use_ema_warmup": false,
76
+ "use_linear_projection": false,
77
+ "view_concat_condition": false
78
+ }
gsdiff_gobj83k_sd15__render/checkpoints/013020/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d16772e42cefaba28600a847d0571995f3751c0b88e41a2af9bf4e695dc805
3
+ size 3438236672
gsdiff_gobj83k_sd15__render__canny/checkpoints/065100/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MVControlNetModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 1280,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
gsdiff_gobj83k_sd15__render__canny/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af657421617a2513857447492a748b5e1d2d9e4053d604a9cc71746359d6c946
3
+ size 1445226240
gsdiff_gobj83k_sd15__render__depth/checkpoints/065100/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MVControlNetModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 1280,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
gsdiff_gobj83k_sd15__render__depth/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5b41a85a91893f28cc70a24685524901bdf0f5905712f0d50c163e0c77284a
3
+ size 1445226240
gsdiff_gobj83k_sd15__render__normal/checkpoints/065100/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MVControlNetModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 1280,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
gsdiff_gobj83k_sd15__render__normal/checkpoints/065100/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd8af43f41e43418e1d4db5b6188dda4a77aec95b1fb5d62a1fe6b99bcd0eb4
3
+ size 1445226240
gsdiff_gobj83k_sd15_image__render/checkpoints/013020/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetMV2DConditionModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_sd15_image_v/checkpoints/065100",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlockMV2D",
27
+ "CrossAttnDownBlockMV2D",
28
+ "CrossAttnDownBlockMV2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 11,
39
+ "input_concat_binary_mask": true,
40
+ "input_concat_plucker": true,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlockMV2DCrossAttn",
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "optimization_step": 13020,
53
+ "out_channels": 4,
54
+ "power": 0.75,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 32,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": 1,
67
+ "up_block_types": [
68
+ "UpBlock2D",
69
+ "CrossAttnUpBlockMV2D",
70
+ "CrossAttnUpBlockMV2D",
71
+ "CrossAttnUpBlockMV2D"
72
+ ],
73
+ "upcast_attention": false,
74
+ "update_after_step": 0,
75
+ "use_ema_warmup": true,
76
+ "use_linear_projection": false,
77
+ "view_concat_condition": true
78
+ }
gsdiff_gobj83k_sd15_image__render/checkpoints/013020/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e7ef7a425cd22dc908134da74e36567e65e52cf8dc0bc0120d54625e240a15
3
+ size 3438248200
gsdiff_gobj83k_sd35m__render/checkpoints/013020/transformer_ema/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "SD3TransformerMV2DModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_sd35m/checkpoints/065100",
5
+ "attention_head_dim": 64,
6
+ "caption_projection_dim": 1536,
7
+ "decay": 0.9999,
8
+ "dual_attention_layers": [
9
+ 0,
10
+ 1,
11
+ 2,
12
+ 3,
13
+ 4,
14
+ 5,
15
+ 6,
16
+ 7,
17
+ 8,
18
+ 9,
19
+ 10,
20
+ 11,
21
+ 12
22
+ ],
23
+ "in_channels": 22,
24
+ "input_concat_binary_mask": false,
25
+ "input_concat_plucker": true,
26
+ "inv_gamma": 1.0,
27
+ "joint_attention_dim": 4096,
28
+ "min_decay": 0.0,
29
+ "num_attention_heads": 24,
30
+ "num_layers": 24,
31
+ "optimization_step": 13020,
32
+ "out_channels": 16,
33
+ "patch_size": 2,
34
+ "pooled_projection_dim": 2048,
35
+ "pos_embed_max_size": 384,
36
+ "power": 0.75,
37
+ "qk_norm": "rms_norm",
38
+ "sample_size": 32,
39
+ "update_after_step": 0,
40
+ "use_ema_warmup": true,
41
+ "view_concat_condition": false
42
+ }
gsdiff_gobj83k_sd35m__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cdfe0e941a6798df34b6628dd36a9ab652466c73f2cfd95248f4d7f9ffcc76
3
+ size 9878908320
gsdiff_gobj83k_sd35m_image__render/checkpoints/013020/transformer_ema/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "SD3TransformerMV2DModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "out/gsdiff_gobj83k_sd35m_image/checkpoints/065100",
5
+ "attention_head_dim": 64,
6
+ "caption_projection_dim": 1536,
7
+ "decay": 0.9999,
8
+ "dual_attention_layers": [
9
+ 0,
10
+ 1,
11
+ 2,
12
+ 3,
13
+ 4,
14
+ 5,
15
+ 6,
16
+ 7,
17
+ 8,
18
+ 9,
19
+ 10,
20
+ 11,
21
+ 12
22
+ ],
23
+ "in_channels": 23,
24
+ "input_concat_binary_mask": true,
25
+ "input_concat_plucker": true,
26
+ "inv_gamma": 1.0,
27
+ "joint_attention_dim": 4096,
28
+ "min_decay": 0.0,
29
+ "num_attention_heads": 24,
30
+ "num_layers": 24,
31
+ "optimization_step": 13020,
32
+ "out_channels": 16,
33
+ "patch_size": 2,
34
+ "pooled_projection_dim": 2048,
35
+ "pos_embed_max_size": 384,
36
+ "power": 0.75,
37
+ "qk_norm": "rms_norm",
38
+ "sample_size": 32,
39
+ "update_after_step": 0,
40
+ "use_ema_warmup": true,
41
+ "view_concat_condition": true
42
+ }
gsdiff_gobj83k_sd35m_image__render/checkpoints/013020/transformer_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82712f4cc8b6d994eeeca42bb695e609cf96b440ee5b8eb416bb38a4c6ff22c9
3
+ size 9878932896
gsrecon_gobj265k_cnp_even4/checkpoints/124320/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e3b9a01fc08c09cd4911460c7809a6709a3d5b67377afe62d1a31b63181942
3
+ size 167287808
gsvae_gobj265k_sd/checkpoints/039030/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d69a31610ac55f6e48985a0f2b7c0904f7c9eef81a300ee31c98ea72b5d2e80
3
+ size 339645016
gsvae_gobj265k_sd3/checkpoints/039030/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad7d697f48eda5ffd944abf0e54471aeb3dc57d81e5c28a392120f9c7b0741c8
3
+ size 340335576
gsvae_gobj265k_sdxl_fp16/checkpoints/039030/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f4257d5f804cd0a32cbe5635e34d95652794c248b964271425a7330d5539fa
3
+ size 339645016