Upload HunyuanVideoPipeline

model_index.json

@@ -1,9 +1,10 @@
 {
   "_class_name": "HunyuanVideoPipeline",
   "_diffusers_version": "0.31.0",
+  "_name_or_path": "magespace/hyvideo-diffusers",
   "scheduler": [
-    "hyvideo",
-    "FlowMatchDiscreteScheduler"
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",
@@ -22,11 +23,11 @@
     "CLIPTokenizer"
   ],
   "transformer": [
-    "hyvideo",
+    "hyvideo.modules.models",
     "HYVideoDiffusionTransformer"
   ],
   "vae": [
-    "hyvideo",
+    "hyvideo.vae.autoencoder_kl_causal_3d",
     "AutoencoderKLCausal3D"
   ]
 }

scheduler/scheduler_config.json

@@ -1,9 +1,11 @@
 {
-  "_class_name": "FlowMatchDiscreteScheduler",
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
   "_diffusers_version": "0.31.0",
-  "n_tokens": null,
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
   "num_train_timesteps": 1000,
-  "reverse": false,
   "shift": 7.0,
-  "solver": "euler"
+  "use_dynamic_shifting": false
 }

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/root/.cache/huggingface/hub/models--magespace--hyvideo-diffusers/snapshots/ae09a3d1e5306c922f86a6aaf8db5b691947d204/text_encoder",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -23,7 +24,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 128320
 }

text_encoder/generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.47.0"
 }

text_encoder_2/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--magespace--hyvideo-diffusers/snapshots/ae09a3d1e5306c922f86a6aaf8db5b691947d204/text_encoder_2",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "vocab_size": 49408
 }

tokenizer/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c593db4aa75b17a42c1f74d7cc38e257eaeed222e6a52674c65544165dcbaa
-size 17210098
+oid sha256:d1cb63338521d084aba234e273e56a3a0bb0e41f6438e205a2cbc1db8f02fd1f
+size 17210368

tokenizer/tokenizer_config.json

@@ -2080,6 +2080,7 @@
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
   "legacy": true,
   "model_input_names": [
     "input_ids",

tokenizer_2/tokenizer_config.json

@@ -23,6 +23,7 @@
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "max_length": 77,
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",

transformer/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "HYVideoDiffusionTransformer",
   "_diffusers_version": "0.31.0",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--magespace--hyvideo-diffusers/snapshots/ae09a3d1e5306c922f86a6aaf8db5b691947d204/transformer",
   "guidance_embed": true,
   "heads_num": 24,
   "hidden_size": 3072,

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKLCausal3D",
   "_diffusers_version": "0.31.0",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--magespace--hyvideo-diffusers/snapshots/ae09a3d1e5306c922f86a6aaf8db5b691947d204/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,