Upload folder using huggingface_hub

VITON-HD-1024-res/README.md

@@ -0,0 +1,42 @@
+---
+license: other
+library_name: diffusers
+pipeline_tag: image-to-image
+tags:
+  - virtual-try-off
+  - garment-reconstruction
+  - viton-hd
+---
+
+# FlowGR VITON-HD garment reconstruction
+
+FlowGR reconstructs a canonical frontal garment image from a person image and
+a binary mask of the garment region. This release contains separate 512 x 384
+and 1024 x 768 checkpoints. It is intended for research and development.
+
+The checkpoints were trained for the VITON-HD domain. Performance outside that
+domain, across garment categories, body types, image conditions, and demographic
+groups has not been systematically characterized in this release. Generated
+images can contain incorrect texture, shape, text, logos, or color. Users should
+validate outputs for their application and should not use them as evidence of
+real products or people.
+
+Recommended inference is fp16 CUDA, 30 denoising steps, guidance scale 2.0,
+and seed 42. Inputs are resized directly to the chosen native resolution. The
+mask uses white for the source garment and black elsewhere. See `README.md` for
+commands and `VERIFICATION.md` for completed release checks.
+
+## Training data and metrics
+
+The model is associated with VITON-HD. Exact training split composition,
+quantitative metrics, and paper metadata have not yet been supplied for this
+public card. Add these details before announcing a formal research release.
+
+## Licenses
+
+Repository-authored code is distributed under `LICENSE`. Vendored Diffusers and
+IP-Adapter-derived files retain their upstream Apache-2.0 headers/terms. SDXL
+base components are subject to CreativeML Open RAIL++-M. This repository does
+not assert that the MIT code license grants rights to the checkpoint weights;
+the publisher must attach the final applicable weight license before upload.
+

VITON-HD-1024-res/SHA256SUMS

@@ -0,0 +1,22 @@
+367249a700f56c5a3e3cdce9364e2850aa6c3f21d20a7395c21ea1c1e6060173  model_index.json
+8b2baa22ae84b65d8c908837b2da36d3708f3899f491e3051f8c46ad5e30cc77  scheduler/scheduler_config.json
+9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a  tokenizer/merges.txt
+a46982c1c09487f4ba4118d4d491a01d7e1b3a9e457662aa93f7c7159f11eaf7  tokenizer/special_tokens_map.json
+7eb36a76a02551ce8583dbee08d062e672997a5fe1db82ebc642d88c7e79cc96  tokenizer/tokenizer_config.json
+e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349  tokenizer/vocab.json
+9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a  tokenizer_2/merges.txt
+c2d0fb8b86ad86b1f46134d4a5f93fd1e688c932a78efc8d149087c33a53ad06  tokenizer_2/special_tokens_map.json
+516314ccab66918d7cb647480ac27abd3520d14e1e5825aac99f50c851c16071  tokenizer_2/tokenizer_config.json
+e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349  tokenizer_2/vocab.json
+4338d66548b4f1e82b8e3d4cfdb77ec356d1a715eb6508f3242224ad8900e4ab  text_encoder/config.json
+03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120  text_encoder/model.safetensors
+b210d3cd6f1706435cc0b3ac4275768bb06752ad8e85c390c52fd63028f64541  text_encoder_2/config.json
+c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c  text_encoder_2/model.safetensors
+0720b184dbebf154a4d56e25ed8b3f308ca9719b0c62430c8c1aa8c1b74aa9ac  image_encoder/config.json
+f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72  image_encoder/model.safetensors
+63b81166b18825de1d715ffff4fcd0fe70a705fb34483e07e7e7f675173ddd40  unet/config.json
+1e2ea0443f7f386cbc6a18e5cb710e64e63eec8539848bc82669720043fb5e95  unet/diffusion_pytorch_model.safetensors
+70ee7071770a9345ea74526ac46a1b7224690177ee725b09747f1815c955392f  unet_encoder/config.json
+b313d17c1059bf12378f6ea75116815892b861d299aab9a16f19979420aabc9a  unet_encoder/diffusion_pytorch_model.safetensors
+c92901808231163b11d0499736838381217667dfad72b6f95266a4c6964300c8  vae/config.json
+6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48  vae/diffusion_pytorch_model.safetensors

VITON-HD-1024-res/image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "ckpt/image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2"
+}

VITON-HD-1024-res/image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72
+size 1264217760

VITON-HD-1024-res/manifest.json

@@ -0,0 +1,122 @@
+{
+  "format_version": 1,
+  "model": "VITON-HD-1024-res",
+  "created_utc": "2026-09-06T08:29:55.001346+00:00",
+  "source_checkpoint": "/storage/FlowGR/result/HD_final_from_incomplete_leffa/checkpoint-372450",
+  "excluded_training_artifacts": [
+    "optimizer.pt",
+    "leffa_attn.pt"
+  ],
+  "files": [
+    {
+      "path": "model_index.json",
+      "size": 932,
+      "sha256": "367249a700f56c5a3e3cdce9364e2850aa6c3f21d20a7395c21ea1c1e6060173"
+    },
+    {
+      "path": "scheduler/scheduler_config.json",
+      "size": 625,
+      "sha256": "8b2baa22ae84b65d8c908837b2da36d3708f3899f491e3051f8c46ad5e30cc77"
+    },
+    {
+      "path": "tokenizer/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer/special_tokens_map.json",
+      "size": 585,
+      "sha256": "a46982c1c09487f4ba4118d4d491a01d7e1b3a9e457662aa93f7c7159f11eaf7"
+    },
+    {
+      "path": "tokenizer/tokenizer_config.json",
+      "size": 704,
+      "sha256": "7eb36a76a02551ce8583dbee08d062e672997a5fe1db82ebc642d88c7e79cc96"
+    },
+    {
+      "path": "tokenizer/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "tokenizer_2/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer_2/special_tokens_map.json",
+      "size": 574,
+      "sha256": "c2d0fb8b86ad86b1f46134d4a5f93fd1e688c932a78efc8d149087c33a53ad06"
+    },
+    {
+      "path": "tokenizer_2/tokenizer_config.json",
+      "size": 855,
+      "sha256": "516314ccab66918d7cb647480ac27abd3520d14e1e5825aac99f50c851c16071"
+    },
+    {
+      "path": "tokenizer_2/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "text_encoder/config.json",
+      "size": 647,
+      "sha256": "4338d66548b4f1e82b8e3d4cfdb77ec356d1a715eb6508f3242224ad8900e4ab"
+    },
+    {
+      "path": "text_encoder/model.safetensors",
+      "size": 246144352,
+      "sha256": "03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120"
+    },
+    {
+      "path": "text_encoder_2/config.json",
+      "size": 657,
+      "sha256": "b210d3cd6f1706435cc0b3ac4275768bb06752ad8e85c390c52fd63028f64541"
+    },
+    {
+      "path": "text_encoder_2/model.safetensors",
+      "size": 1389382688,
+      "sha256": "c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c"
+    },
+    {
+      "path": "image_encoder/config.json",
+      "size": 559,
+      "sha256": "0720b184dbebf154a4d56e25ed8b3f308ca9719b0c62430c8c1aa8c1b74aa9ac"
+    },
+    {
+      "path": "image_encoder/model.safetensors",
+      "size": 1264217760,
+      "sha256": "f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72"
+    },
+    {
+      "path": "unet/config.json",
+      "size": 1869,
+      "sha256": "63b81166b18825de1d715ffff4fcd0fe70a705fb34483e07e7e7f675173ddd40"
+    },
+    {
+      "path": "unet/diffusion_pytorch_model.safetensors",
+      "size": 5982676720,
+      "sha256": "1e2ea0443f7f386cbc6a18e5cb710e64e63eec8539848bc82669720043fb5e95"
+    },
+    {
+      "path": "unet_encoder/config.json",
+      "size": 2024,
+      "sha256": "70ee7071770a9345ea74526ac46a1b7224690177ee725b09747f1815c955392f"
+    },
+    {
+      "path": "unet_encoder/diffusion_pytorch_model.safetensors",
+      "size": 10249153104,
+      "sha256": "b313d17c1059bf12378f6ea75116815892b861d299aab9a16f19979420aabc9a"
+    },
+    {
+      "path": "vae/config.json",
+      "size": 688,
+      "sha256": "c92901808231163b11d0499736838381217667dfad72b6f95266a4c6964300c8"
+    },
+    {
+      "path": "vae/diffusion_pytorch_model.safetensors",
+      "size": 167335342,
+      "sha256": "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48"
+    }
+  ]
+}

VITON-HD-1024-res/model_index.json

@@ -0,0 +1,46 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "model.diffusion.unet_hacked_gennet",
+    "UNet2DConditionModel"
+  ],
+  "unet_encoder": [
+    "model.diffusion.unet_hacked_refnet",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "model.diffusion.autoencoder_kl_hacked",
+    "AutoencoderKL"
+  ]
+}

VITON-HD-1024-res/scheduler/scheduler_config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.25.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false,
+  "variance_type": "fixed_small"
+}

VITON-HD-1024-res/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "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": "bfloat16",
+  "transformers_version": "4.37.2",
+  "vocab_size": 49408
+}

VITON-HD-1024-res/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120
+size 246144352

VITON-HD-1024-res/text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "vocab_size": 49408
+}

VITON-HD-1024-res/text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c
+size 1389382688

VITON-HD-1024-res/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

VITON-HD-1024-res/tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

VITON-HD-1024-res/tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

VITON-HD-1024-res/tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

VITON-HD-1024-res/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": 1280,
+  "encoder_hid_dim_type": "ip_image_proj",
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "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_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

VITON-HD-1024-res/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2ea0443f7f386cbc6a18e5cb710e64e63eec8539848bc82669720043fb5e95
+size 5982676720

VITON-HD-1024-res/unet_encoder/config.json

@@ -0,0 +1,80 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 9,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 37000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": true
+}

VITON-HD-1024-res/unet_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b313d17c1059bf12378f6ea75116815892b861d299aab9a16f19979420aabc9a
+size 10249153104

VITON-HD-1024-res/vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/home/u1732910/my_data/result/20250912-162214/checkpoint-170000",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

VITON-HD-1024-res/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342

VITON-HD-512-res/README.md

@@ -0,0 +1,42 @@
+---
+license: other
+library_name: diffusers
+pipeline_tag: image-to-image
+tags:
+  - virtual-try-off
+  - garment-reconstruction
+  - viton-hd
+---
+
+# FlowGR VITON-HD garment reconstruction
+
+FlowGR reconstructs a canonical frontal garment image from a person image and
+a binary mask of the garment region. This release contains separate 512 x 384
+and 1024 x 768 checkpoints. It is intended for research and development.
+
+The checkpoints were trained for the VITON-HD domain. Performance outside that
+domain, across garment categories, body types, image conditions, and demographic
+groups has not been systematically characterized in this release. Generated
+images can contain incorrect texture, shape, text, logos, or color. Users should
+validate outputs for their application and should not use them as evidence of
+real products or people.
+
+Recommended inference is fp16 CUDA, 30 denoising steps, guidance scale 2.0,
+and seed 42. Inputs are resized directly to the chosen native resolution. The
+mask uses white for the source garment and black elsewhere. See `README.md` for
+commands and `VERIFICATION.md` for completed release checks.
+
+## Training data and metrics
+
+The model is associated with VITON-HD. Exact training split composition,
+quantitative metrics, and paper metadata have not yet been supplied for this
+public card. Add these details before announcing a formal research release.
+
+## Licenses
+
+Repository-authored code is distributed under `LICENSE`. Vendored Diffusers and
+IP-Adapter-derived files retain their upstream Apache-2.0 headers/terms. SDXL
+base components are subject to CreativeML Open RAIL++-M. This repository does
+not assert that the MIT code license grants rights to the checkpoint weights;
+the publisher must attach the final applicable weight license before upload.
+

VITON-HD-512-res/SHA256SUMS

@@ -0,0 +1,22 @@
+fc6495a5a8f42fccca1f68b052c4ecd3aff60fad953f99698801ef505f98008f  model_index.json
+8b2baa22ae84b65d8c908837b2da36d3708f3899f491e3051f8c46ad5e30cc77  scheduler/scheduler_config.json
+9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a  tokenizer/merges.txt
+a46982c1c09487f4ba4118d4d491a01d7e1b3a9e457662aa93f7c7159f11eaf7  tokenizer/special_tokens_map.json
+7eb36a76a02551ce8583dbee08d062e672997a5fe1db82ebc642d88c7e79cc96  tokenizer/tokenizer_config.json
+e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349  tokenizer/vocab.json
+9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a  tokenizer_2/merges.txt
+c2d0fb8b86ad86b1f46134d4a5f93fd1e688c932a78efc8d149087c33a53ad06  tokenizer_2/special_tokens_map.json
+516314ccab66918d7cb647480ac27abd3520d14e1e5825aac99f50c851c16071  tokenizer_2/tokenizer_config.json
+e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349  tokenizer_2/vocab.json
+b4727d46c7b8f8483f6ebb5ab5adf4b7148daf44ec0f439df3f93708b7d82059  text_encoder/config.json
+03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120  text_encoder/model.safetensors
+90c4818a9f4bf808ba45170f941a5720177f5251f67365ee5baa9ce63cb934f7  text_encoder_2/config.json
+c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c  text_encoder_2/model.safetensors
+0720b184dbebf154a4d56e25ed8b3f308ca9719b0c62430c8c1aa8c1b74aa9ac  image_encoder/config.json
+f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72  image_encoder/model.safetensors
+15b2b4c9c201d5213e88d5180df7708a1d54598542acf33ac48e345923fb4515  unet/config.json
+dbd7c72f00ee6ed06bb0c02f2fbf0483a654ed8fb9d714667fd016d5daeb1714  unet/diffusion_pytorch_model.safetensors
+a14671684fdea6c11aca55f1d7b77f3f7388b8e5b0924f2d1f18959495fd0dea  unet_encoder/config.json
+d5cbb19b03b02429de8ac81d244ff2aa8dcf7d7c95f69a5e247871bf7579f3bc  unet_encoder/diffusion_pytorch_model.safetensors
+428067cd407968f15e05d930c45cf3373e10ba1b45e5659dec83bff128592d1a  vae/config.json
+6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48  vae/diffusion_pytorch_model.safetensors

VITON-HD-512-res/image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "ckpt/image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2"
+}

VITON-HD-512-res/image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72
+size 1264217760

VITON-HD-512-res/manifest.json

@@ -0,0 +1,122 @@
+{
+  "format_version": 1,
+  "model": "VITON-HD-512-res",
+  "created_utc": "2026-09-06T08:27:37.169188+00:00",
+  "source_checkpoint": "/storage/FlowGR/result/20250904-095534/checkpoint",
+  "excluded_training_artifacts": [
+    "optimizer.pt",
+    "leffa_attn.pt"
+  ],
+  "files": [
+    {
+      "path": "model_index.json",
+      "size": 897,
+      "sha256": "fc6495a5a8f42fccca1f68b052c4ecd3aff60fad953f99698801ef505f98008f"
+    },
+    {
+      "path": "scheduler/scheduler_config.json",
+      "size": 625,
+      "sha256": "8b2baa22ae84b65d8c908837b2da36d3708f3899f491e3051f8c46ad5e30cc77"
+    },
+    {
+      "path": "tokenizer/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer/special_tokens_map.json",
+      "size": 585,
+      "sha256": "a46982c1c09487f4ba4118d4d491a01d7e1b3a9e457662aa93f7c7159f11eaf7"
+    },
+    {
+      "path": "tokenizer/tokenizer_config.json",
+      "size": 704,
+      "sha256": "7eb36a76a02551ce8583dbee08d062e672997a5fe1db82ebc642d88c7e79cc96"
+    },
+    {
+      "path": "tokenizer/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "tokenizer_2/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer_2/special_tokens_map.json",
+      "size": 574,
+      "sha256": "c2d0fb8b86ad86b1f46134d4a5f93fd1e688c932a78efc8d149087c33a53ad06"
+    },
+    {
+      "path": "tokenizer_2/tokenizer_config.json",
+      "size": 855,
+      "sha256": "516314ccab66918d7cb647480ac27abd3520d14e1e5825aac99f50c851c16071"
+    },
+    {
+      "path": "tokenizer_2/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "text_encoder/config.json",
+      "size": 640,
+      "sha256": "b4727d46c7b8f8483f6ebb5ab5adf4b7148daf44ec0f439df3f93708b7d82059"
+    },
+    {
+      "path": "text_encoder/model.safetensors",
+      "size": 246144352,
+      "sha256": "03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120"
+    },
+    {
+      "path": "text_encoder_2/config.json",
+      "size": 650,
+      "sha256": "90c4818a9f4bf808ba45170f941a5720177f5251f67365ee5baa9ce63cb934f7"
+    },
+    {
+      "path": "text_encoder_2/model.safetensors",
+      "size": 1389382688,
+      "sha256": "c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c"
+    },
+    {
+      "path": "image_encoder/config.json",
+      "size": 559,
+      "sha256": "0720b184dbebf154a4d56e25ed8b3f308ca9719b0c62430c8c1aa8c1b74aa9ac"
+    },
+    {
+      "path": "image_encoder/model.safetensors",
+      "size": 1264217760,
+      "sha256": "f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72"
+    },
+    {
+      "path": "unet/config.json",
+      "size": 1862,
+      "sha256": "15b2b4c9c201d5213e88d5180df7708a1d54598542acf33ac48e345923fb4515"
+    },
+    {
+      "path": "unet/diffusion_pytorch_model.safetensors",
+      "size": 5982676720,
+      "sha256": "dbd7c72f00ee6ed06bb0c02f2fbf0483a654ed8fb9d714667fd016d5daeb1714"
+    },
+    {
+      "path": "unet_encoder/config.json",
+      "size": 2017,
+      "sha256": "a14671684fdea6c11aca55f1d7b77f3f7388b8e5b0924f2d1f18959495fd0dea"
+    },
+    {
+      "path": "unet_encoder/diffusion_pytorch_model.safetensors",
+      "size": 10249153104,
+      "sha256": "d5cbb19b03b02429de8ac81d244ff2aa8dcf7d7c95f69a5e247871bf7579f3bc"
+    },
+    {
+      "path": "vae/config.json",
+      "size": 681,
+      "sha256": "428067cd407968f15e05d930c45cf3373e10ba1b45e5659dec83bff128592d1a"
+    },
+    {
+      "path": "vae/diffusion_pytorch_model.safetensors",
+      "size": 167335342,
+      "sha256": "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48"
+    }
+  ]
+}

VITON-HD-512-res/model_index.json

@@ -0,0 +1,46 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "model.diffusion.unet_hacked_gennet",
+    "UNet2DConditionModel"
+  ],
+  "unet_encoder": [
+    "model.diffusion.unet_hacked_refnet",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

VITON-HD-512-res/scheduler/scheduler_config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.25.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false,
+  "variance_type": "fixed_small"
+}

VITON-HD-512-res/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "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": "bfloat16",
+  "transformers_version": "4.37.2",
+  "vocab_size": 49408
+}

VITON-HD-512-res/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120
+size 246144352

VITON-HD-512-res/text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "vocab_size": 49408
+}

VITON-HD-512-res/text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c
+size 1389382688

VITON-HD-512-res/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

VITON-HD-512-res/tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

VITON-HD-512-res/tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

VITON-HD-512-res/tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

VITON-HD-512-res/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": 1280,
+  "encoder_hid_dim_type": "ip_image_proj",
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "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_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

VITON-HD-512-res/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd7c72f00ee6ed06bb0c02f2fbf0483a654ed8fb9d714667fd016d5daeb1714
+size 5982676720

VITON-HD-512-res/unet_encoder/config.json

@@ -0,0 +1,80 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 9,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 37000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": true
+}

VITON-HD-512-res/unet_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5cbb19b03b02429de8ac81d244ff2aa8dcf7d7c95f69a5e247871bf7579f3bc
+size 10249153104

VITON-HD-512-res/vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "/storage/FlowGR/result/20250831-182657/checkpoint-744770",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

VITON-HD-512-res/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342