Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
{
"_comment": "vae/config.json of every Studio image / video family's base repo, read by test_vae_tile_geometry.py (no weights). Refresh an entry when a family's base repo changes; keep the revision it was read at.",
"families": {
"flux.1": {
"kind": "image",
"repo": "unsloth/FLUX.1-schnell",
"revision": "9df3faa7ae3b6ddf0b2b69bb78616372897cc65c",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"flux.2-klein": {
"kind": "image",
"repo": "black-forest-labs/FLUX.2-klein-4B",
"revision": "e7b7dc27f91deacad38e78976d1f2b499d76a294",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.37.0.dev0",
"_name_or_path": "black-forest-labs/FLUX.2-dev",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"flux.2-dev": {
"kind": "image",
"repo": "unsloth/FLUX.2-dev",
"revision": "351bbb0ebab35d4dfec0445f67bcec34b383ddf9",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.36.0.dev0",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"flux.3-klein": {
"kind": "image",
"repo": "unsloth/flux-3-image-klein-FP8",
"revision": "0e7c103d8ffafb0d4ccd8d82122375c878cdaf4d",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.41.0.dev0",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"decoder_block_out_channels": null,
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"flux.3-klein-base": {
"kind": "image",
"repo": "unsloth/flux-3-image-klein-base-FP8",
"revision": "b96dfc4e77c3f4412183348f90fd9fd4901102a3",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.41.0.dev0",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"decoder_block_out_channels": null,
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"flux.1-kontext": {
"kind": "image",
"repo": "unsloth/FLUX.1-Kontext-dev",
"revision": "ed585f929575da3142d1cdd7a49ef25db6f12161",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.34.0.dev0",
"_name_or_path": "/raid/.cache/huggingface/models--black-forest-labs--FLUX.1-dev/snapshots/0ef5fff789c832c5c7f4e127f94c8b54bbcced44/vae",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"qwen-image-layered": {
"kind": "image",
"repo": "Qwen/Qwen-Image-Layered",
"revision": "8f0ca708dfff6ba1dd5f2d85d78f8c108a040bcf",
"config": {
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.36.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"input_channels": 4,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"qwen-image-edit": {
"kind": "image",
"repo": "Qwen/Qwen-Image-Edit-2511",
"revision": "6f3ccc0b56e431dc6a0c2b2039706d7d26f22cb9",
"config": {
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.36.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"qwen-image": {
"kind": "image",
"repo": "Qwen/Qwen-Image",
"revision": "75e0b4be04f60ec59a75f475837eced720f823b6",
"config": {
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.34.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"qwen-image-2.1": {
"kind": "image",
"repo": "Qwen/Qwen-Image-2.1",
"revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
"config": {
"_class_name": "AutoencoderKLQwenImage21",
"_diffusers_version": "0.37.0.dev0",
"attn_scales": [],
"base_dim": 96,
"decoder_base_dim": 144,
"dim_mult": [
1,
2,
4,
8,
8
],
"dropout": 0.0,
"in_channels": 4,
"is_residual": true,
"latents_mean": [
0.5126,
0.7721,
-0.0631,
1.3506,
-0.7855,
-2.1025,
-0.3458,
1.3722,
1.8873,
-1.7177,
-0.651,
0.2732,
0.7562,
-0.6163,
-1.0277,
3.8363,
2.021,
0.0472,
0.932,
2.0087,
2.4954,
-0.1391,
-1.4249,
1.8464,
-0.5236,
1.2826,
3.7046,
-1.3035,
2.7286,
-1.4518,
-1.9036,
-1.9955,
-0.0342,
-1.0265,
-0.7636,
3.0555,
0.0746,
-3.0751,
-0.1076,
1.7376,
-1.0914,
-1.9435,
-0.2784,
-1.368,
0.4809,
-0.4433,
0.3764,
0.5729,
-2.0595,
1.096,
-1.326,
-2.0211,
-5.0179,
0.5275,
4.0162,
1.8505,
0.3026,
1.9373,
1.4937,
0.2632,
0.5547,
-1.7121,
-0.1562,
0.0304
],
"latents_std": [
3.2001,
3.2936,
3.4321,
3.0091,
3.1061,
4.0379,
4.0705,
3.791,
3.0785,
3.65,
3.9308,
3.0904,
2.8778,
3.7675,
3.732,
5.0756,
3.2864,
4.0397,
3.1317,
4.0443,
2.9249,
3.9454,
3.0988,
4.2489,
3.4896,
3.8513,
3.9323,
3.4719,
3.7498,
4.283,
3.5694,
4.2467,
3.9037,
3.2947,
5.077,
3.5075,
3.27,
3.4767,
2.8063,
5.1125,
3.5327,
4.7833,
3.1286,
4.1819,
3.8527,
3.8312,
3.5605,
4.3875,
3.9624,
4.0168,
3.5643,
4.055,
5.5614,
4.2963,
4.408,
3.4959,
3.8747,
3.7608,
3.5735,
3.149,
3.7662,
3.6746,
3.4563,
3.8161
],
"num_res_blocks": 2,
"out_channels": 4,
"patch_size": null,
"scale_factor_spatial": 16,
"scale_factor_temporal": 8,
"temperal_downsample": [
false,
true,
true,
true
],
"z_dim": 64
}
},
"z-image": {
"kind": "image",
"repo": "Tongyi-MAI/Z-Image-Turbo",
"revision": "f332072aa78be7aecdf3ee76d5c247082da564a6",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.36.0.dev0",
"_name_or_path": "flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"krea-2": {
"kind": "image",
"repo": "unsloth/Krea-2-Turbo",
"revision": "2489d0f4cb200616c0b5410f96f64d8fdc611b06",
"config": {
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.39.0.dev0",
"_name_or_path": "Qwen/Qwen-Image",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"input_channels": 3,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"lumina-2": {
"kind": "image",
"repo": "Alpha-VLLM/Lumina-Image-2.0",
"revision": "53504abd8178b30685b6c4c7a4cd181ff78b73e9",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.33.0.dev0",
"_name_or_path": "black-forest-labs/FLUX.1-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"chroma": {
"kind": "image",
"repo": "lodestones/Chroma1-HD",
"revision": "0e0c60ece1e82b17cb7f77342d765ba5024c40c0",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.35.1",
"_name_or_path": "/home/ubuntu/FLUX.1-schnell",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"anima": {
"kind": "image",
"repo": "circlestone-labs/Anima-Base-v1.0-Diffusers",
"revision": "073c3a9db359c31ad0e8aa268d15775473c2176c",
"config": {
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.39.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"input_channels": 3,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"hunyuanimage-2.1": {
"kind": "image",
"repo": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers",
"revision": "7e7b7a177de58591aeaffca0929f4765003d7ced",
"config": {
"_class_name": "AutoencoderKLHunyuanImage",
"_diffusers_version": "0.36.0.dev0",
"block_out_channels": [
128,
256,
512,
512,
1024,
1024
],
"downsample_match_channel": true,
"in_channels": 3,
"latent_channels": 64,
"layers_per_block": 2,
"out_channels": 3,
"sample_size": 384,
"scaling_factor": 0.75289,
"spatial_compression_ratio": 32,
"upsample_match_channel": true
}
},
"hidream-i1": {
"kind": "image",
"repo": "HiDream-ai/HiDream-I1-Full",
"revision": "8ccbbfb270ccdae26d6bb0081df67dc81e4033bf",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}
},
"ideogram-4": {
"kind": "image",
"repo": "unsloth/ideogram-4-fp8",
"revision": "518e05e745736960acb56d8726138ffbc174f0a9",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.39.0.dev0",
"_name_or_path": "/home/jinli/.cache/huggingface/hub/models--ideogram-ai--debug-ideogram-v4/snapshots/41af6183c9fd9b6254864b0720319ef984535bfc/vae",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"decoder_block_out_channels": null,
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"moss-image": {
"kind": "image",
"repo": "OpenMOSS-Team/MOSS-Image-SFT",
"revision": "f972bd4b4b9e3852133cc5da954d87bc32cd8fb9",
"config": {
"_class_name": "AutoencoderKLFlux2",
"_diffusers_version": "0.38.0",
"act_fn": "silu",
"batch_norm_eps": 0.0001,
"batch_norm_momentum": 0.1,
"block_out_channels": [
128,
256,
512,
512
],
"decoder_block_out_channels": [
96,
192,
384,
384
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"patch_size": [
2,
2
],
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": true,
"use_quant_conv": true
}
},
"minimax-h3-image": {
"kind": "image",
"repo": "MiniMaxAI/MiniMax-H3-Image",
"revision": "fbde899fffb5c5225ee8dd7027680113746af42e",
"config": {
"_class_name": "AutoencoderKLMiniMaxH3Image",
"_diffusers_version": "0.42.0.dev0",
"in_channels": 3,
"out_channels": 3,
"latent_channels": 24,
"block_out_channels": [
128,
256,
256,
512,
512,
1024
],
"layers_per_block": 2,
"spatial_downsample_factors": [
2,
2,
2,
2,
1,
1
],
"temporal_downsample_factors": [
1,
2,
2,
1,
1,
1
],
"norm_num_groups": 32,
"norm_eps": 1e-06,
"spatial_padding_mode": "reflect",
"decoder_num_layers": 24,
"decoder_num_attention_heads": 16,
"decoder_attention_head_dim": 64,
"decoder_num_register_tokens": 4,
"decoder_ffn_mult": 4,
"decoder_rope_theta": 100.0,
"decoder_rope_dim_ratio": 0.5,
"decoder_norm_eps": 1e-05,
"latents_mean": [
0.858090341091156,
-0.9606591463088989,
1.0661640167236328,
-0.5090325474739075,
-0.2727581858634949,
-1.3675414323806763,
-0.2553254961967468,
-0.26907554268836975,
-0.5376840829849243,
-0.0464097298681736,
0.6657370328903198,
0.19690127670764923,
-0.5460608005523682,
-0.4035342037677765,
-0.23683024942874908,
0.25928452610969543,
-0.30133944749832153,
0.211341992020607,
-1.1206848621368408,
0.3581933379173279,
-0.04225143790245056,
0.2604829967021942,
0.22864092886447906,
0.7056031823158264
],
"latents_std": [
1.2223774194717407,
1.2767263650894165,
1.6831774711608887,
1.7549455165863037,
1.5636216402053833,
2.194143533706665,
0.9653137922286987,
1.0569885969161987,
0.841948926448822,
0.7729952931404114,
1.8955937623977661,
0.946841835975647,
0.7996809482574463,
0.44988900423049927,
0.7197399735450745,
0.6936293244361877,
2.961095094680786,
2.7694199085235596,
3.0496184825897217,
2.1088054180145264,
3.276226282119751,
3.1627357006073,
2.2816812992095947,
2.6127843856811523
]
}
},
"sdxl": {
"kind": "image",
"repo": "stabilityai/stable-diffusion-xl-base-1.0",
"revision": "462165984030d82259a11f4367a4eed129e94a7b",
"config": {
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.20.0.dev0",
"_name_or_path": "../sdxl-vae/",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}
},
"minimax-h3": {
"kind": "video",
"repo": "MiniMaxAI/MiniMax-H3",
"revision": "42ed227ee7df40d41602854ae760620d6eb651fe",
"config": {
"_class_name": "AutoencoderKLMiniMaxH3",
"_diffusers_version": "0.36.0.dev0",
"in_channels": 3,
"out_channels": 3,
"latent_channels": 24,
"block_out_channels": [
128,
256,
256,
512,
512,
1024
],
"layers_per_block": 2,
"spatial_downsample_factors": [
2,
2,
2,
2,
1,
1
],
"temporal_downsample_factors": [
1,
2,
2,
1,
1,
1
],
"norm_num_groups": 32,
"norm_eps": 1e-06,
"spatial_padding_mode": "reflect",
"decoder_num_layers": 36,
"decoder_num_attention_heads": 32,
"decoder_attention_head_dim": 64,
"decoder_num_register_tokens": 4,
"decoder_ffn_mult": 4,
"decoder_rope_theta": 100.0,
"decoder_rope_dim_ratio": 0.75,
"decoder_norm_eps": 1e-05,
"clip_length": 17,
"token_drop": 3,
"latents_mean": [
0.858090341091156,
-0.9606591463088989,
1.0661640167236328,
-0.5090325474739075,
-0.2727581858634949,
-1.3675414323806763,
-0.2553254961967468,
-0.26907554268836975,
-0.5376840829849243,
-0.0464097298681736,
0.6657370328903198,
0.19690127670764923,
-0.5460608005523682,
-0.4035342037677765,
-0.23683024942874908,
0.25928452610969543,
-0.30133944749832153,
0.211341992020607,
-1.1206848621368408,
0.3581933379173279,
-0.04225143790245056,
0.2604829967021942,
0.22864092886447906,
0.7056031823158264
],
"latents_std": [
1.2223774194717407,
1.2767263650894165,
1.6831774711608887,
1.7549455165863037,
1.5636216402053833,
2.194143533706665,
0.9653137922286987,
1.0569885969161987,
0.841948926448822,
0.7729952931404114,
1.8955937623977661,
0.946841835975647,
0.7996809482574463,
0.44988900423049927,
0.7197399735450745,
0.6936293244361877,
2.961095094680786,
2.7694199085235596,
3.0496184825897217,
2.1088054180145264,
3.276226282119751,
3.1627357006073,
2.2816812992095947,
2.6127843856811523
]
}
},
"ltx-2.5": {
"kind": "video",
"repo": "Lightricks/LTX-2.5-Diffusers",
"revision": "da0b690960026eab794b8ceaf841233cf7064478",
"config": {
"_class_name": "AutoencoderKLLTX2Video",
"_diffusers_version": "0.40.0.dev0",
"block_out_channels": [
256,
512,
1024,
1024
],
"decoder_block_out_channels": [
256,
512,
512,
1024
],
"decoder_causal": false,
"decoder_inject_noise": [
false,
false,
false,
false,
false
],
"decoder_layers_per_block": [
4,
6,
4,
2,
2
],
"decoder_spatial_padding_mode": "zeros",
"decoder_spatio_temporal_scaling": [
true,
true,
true,
true
],
"down_block_types": [
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D"
],
"downsample_type": [
"spatial",
"temporal",
"spatiotemporal",
"spatiotemporal"
],
"encoder_causal": true,
"encoder_spatial_padding_mode": "zeros",
"in_channels": 3,
"latent_channels": 128,
"layers_per_block": [
4,
6,
4,
2,
2
],
"out_channels": 3,
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-06,
"scaling_factor": 1.0,
"spatial_compression_ratio": 32,
"spatio_temporal_scaling": [
true,
true,
true,
true
],
"temporal_compression_ratio": 8,
"timestep_conditioning": false,
"upsample_factor": [
2,
2,
1,
2
],
"upsample_residual": [
false,
false,
false,
false
],
"upsample_type": [
"spatiotemporal",
"spatiotemporal",
"temporal",
"spatial"
]
}
},
"ltx-2": {
"kind": "video",
"repo": "Lightricks/LTX-2",
"revision": "dfcc2108383fe1aaa0584bdf55d368a4bdadd90c",
"config": {
"_class_name": "AutoencoderKLLTX2Video",
"_diffusers_version": "0.37.0.dev0",
"block_out_channels": [
256,
512,
1024,
2048
],
"decoder_block_out_channels": [
256,
512,
1024
],
"decoder_causal": false,
"decoder_inject_noise": [
false,
false,
false,
false
],
"decoder_layers_per_block": [
5,
5,
5,
5
],
"decoder_spatial_padding_mode": "reflect",
"decoder_spatio_temporal_scaling": [
true,
true,
true
],
"down_block_types": [
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D",
"LTX2VideoDownBlock3D"
],
"downsample_type": [
"spatial",
"temporal",
"spatiotemporal",
"spatiotemporal"
],
"encoder_causal": true,
"encoder_spatial_padding_mode": "zeros",
"in_channels": 3,
"latent_channels": 128,
"layers_per_block": [
4,
6,
6,
2,
2
],
"out_channels": 3,
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-06,
"scaling_factor": 1.0,
"spatial_compression_ratio": 32,
"spatio_temporal_scaling": [
true,
true,
true,
true
],
"temporal_compression_ratio": 8,
"timestep_conditioning": false,
"upsample_factor": [
2,
2,
2
],
"upsample_residual": [
true,
true,
true
]
}
},
"wan2.2-ti2v-5b": {
"kind": "video",
"repo": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
"revision": "b8fff7315c768468a5333511427288870b2e9635",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.35.0.dev0",
"attn_scales": [],
"base_dim": 160,
"clip_output": false,
"decoder_base_dim": 256,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"in_channels": 12,
"is_residual": true,
"latents_mean": [
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.157,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.123,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.052,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667
],
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.499,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.06,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744
],
"num_res_blocks": 2,
"out_channels": 12,
"patch_size": 2,
"scale_factor_spatial": 16,
"scale_factor_temporal": 4,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 48
}
},
"wan2.2-t2v-a14b": {
"kind": "video",
"repo": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
"revision": "5be7df9619b54f4e2667b2755bc6a756675b5cd7",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.35.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"wan2.1-t2v-1.3b": {
"kind": "video",
"repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
"revision": "0fad780a534b6463e45facd96134c9f345acfa5b",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.33.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"wan2.1-t2v-14b": {
"kind": "video",
"repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers",
"revision": "38ec498cb3208fb688890f8cc7e94ede2cbd7f68",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.33.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}
},
"hunyuanvideo-1.5": {
"kind": "video",
"repo": "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
"revision": "286be7ce72277246578a3e3cc2487e95ddae5bcf",
"config": {
"_class_name": "AutoencoderKLHunyuanVideo15",
"_diffusers_version": "0.36.0.dev0",
"block_out_channels": [
128,
256,
512,
1024,
1024
],
"downsample_match_channel": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"out_channels": 3,
"scaling_factor": 1.03682,
"spatial_compression_ratio": 16,
"temporal_compression_ratio": 4,
"upsample_match_channel": true
}
},
"hunyuanvideo-1.5-720p": {
"kind": "video",
"repo": "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v",
"revision": "f4dbc4a1efa4ac8ea56680cdf79d9f455105e814",
"config": {
"_class_name": "AutoencoderKLHunyuanVideo15",
"_diffusers_version": "0.36.0.dev0",
"block_out_channels": [
128,
256,
512,
1024,
1024
],
"downsample_match_channel": true,
"in_channels": 3,
"latent_channels": 32,
"layers_per_block": 2,
"out_channels": 3,
"scaling_factor": 1.03682,
"spatial_compression_ratio": 16,
"temporal_compression_ratio": 4,
"upsample_match_channel": true
}
},
"cosmos3-nano": {
"kind": "video",
"repo": "nvidia/Cosmos3-Nano",
"revision": "e59a53c25979a090fa8706c9acc0c254a6e89b92",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.37.1",
"_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
"attn_scales": [],
"base_dim": 160,
"clip_output": false,
"decoder_base_dim": 256,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"in_channels": 12,
"is_residual": true,
"latents_mean": [
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.157,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.123,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.052,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667
],
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.499,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.06,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744
],
"num_res_blocks": 2,
"out_channels": 12,
"patch_size": 2,
"scale_factor_spatial": 16,
"scale_factor_temporal": 4,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 48
}
},
"cosmos3-edge": {
"kind": "video",
"repo": "nvidia/Cosmos3-Edge",
"revision": "344d602b128d1bbdacb43b08d0a3626f46343e29",
"config": {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.40.0.dev0",
"_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
"attn_scales": [],
"base_dim": 160,
"clip_output": false,
"decoder_base_dim": 256,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"in_channels": 12,
"is_residual": true,
"latents_mean": [
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.157,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.123,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.052,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667
],
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.499,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.06,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744
],
"num_res_blocks": 2,
"out_channels": 12,
"patch_size": 2,
"scale_factor_spatial": 16,
"scale_factor_temporal": 4,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 48
}
}
}
}