Instructions to use nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload v2 fused checkpoint: ov_to_nvpcb_solderlight_ic_updated_v2_aug_2511
Browse filesReplaces v1 at root. v1 retained at tag `v1` (commit f600e88f8512).
Base model: Qwen/Qwen-Image-Edit-2511
Source LoRA: ic_landscape_aug_2511_2000_v3 / lora-step-01500
Pipeline class: QwenImageEditPlusPipeline
Canonical inference parameters (per qwen-edit-nvpcb-FT/infer_fused_10samples.py):
num_inference_steps=30
true_cfg_scale=4.0
negative_prompt=' ' (single space; required to enable CFG)
seed=0
- .gitattributes +1 -0
- model_index.json +3 -3
- processor/processor_config.json +63 -0
- processor/tokenizer.json +2 -2
- processor/tokenizer_config.json +3 -195
- scheduler/scheduler_config.json +1 -1
- text_encoder/config.json +11 -36
- text_encoder/generation_config.json +4 -11
- text_encoder/model.safetensors +3 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +3 -195
- transformer/config.json +3 -3
- transformer/diffusion_pytorch_model-00001-of-00005.safetensors +1 -1
- transformer/diffusion_pytorch_model-00002-of-00005.safetensors +1 -1
- transformer/diffusion_pytorch_model-00003-of-00005.safetensors +1 -1
- transformer/diffusion_pytorch_model-00004-of-00005.safetensors +1 -1
- transformer/diffusion_pytorch_model-00005-of-00005.safetensors +1 -1
- vae/config.json +2 -2
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
model_index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_class_name": "
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
-
"_name_or_path": "Qwen/Qwen-Image-Edit",
|
| 5 |
"processor": [
|
| 6 |
"transformers",
|
| 7 |
"Qwen2VLProcessor"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_class_name": "QwenImageEditPlusPipeline",
|
| 3 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 4 |
+
"_name_or_path": "Qwen/Qwen-Image-Edit-2511",
|
| 5 |
"processor": [
|
| 6 |
"transformers",
|
| 7 |
"Qwen2VLProcessor"
|
processor/processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"do_convert_rgb": true,
|
| 6 |
+
"do_normalize": true,
|
| 7 |
+
"do_rescale": true,
|
| 8 |
+
"do_resize": true,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.48145466,
|
| 11 |
+
0.4578275,
|
| 12 |
+
0.40821073
|
| 13 |
+
],
|
| 14 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 15 |
+
"image_std": [
|
| 16 |
+
0.26862954,
|
| 17 |
+
0.26130258,
|
| 18 |
+
0.27577711
|
| 19 |
+
],
|
| 20 |
+
"merge_size": 2,
|
| 21 |
+
"patch_size": 14,
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
},
|
| 30 |
+
"processor_class": "Qwen2VLProcessor",
|
| 31 |
+
"video_processor": {
|
| 32 |
+
"data_format": "channels_first",
|
| 33 |
+
"default_to_square": true,
|
| 34 |
+
"do_convert_rgb": true,
|
| 35 |
+
"do_normalize": true,
|
| 36 |
+
"do_rescale": true,
|
| 37 |
+
"do_resize": true,
|
| 38 |
+
"do_sample_frames": false,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.48145466,
|
| 41 |
+
0.4578275,
|
| 42 |
+
0.40821073
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.26862954,
|
| 46 |
+
0.26130258,
|
| 47 |
+
0.27577711
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 14,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 12845056,
|
| 58 |
+
"shortest_edge": 3136
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
processor/tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
processor/tokenizer_config.json
CHANGED
|
@@ -1,204 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
}
|
| 181 |
-
},
|
| 182 |
-
"additional_special_tokens": [
|
| 183 |
-
"<|im_start|>",
|
| 184 |
-
"<|im_end|>",
|
| 185 |
-
"<|object_ref_start|>",
|
| 186 |
-
"<|object_ref_end|>",
|
| 187 |
-
"<|box_start|>",
|
| 188 |
-
"<|box_end|>",
|
| 189 |
-
"<|quad_start|>",
|
| 190 |
-
"<|quad_end|>",
|
| 191 |
-
"<|vision_start|>",
|
| 192 |
-
"<|vision_end|>",
|
| 193 |
-
"<|vision_pad|>",
|
| 194 |
-
"<|image_pad|>",
|
| 195 |
-
"<|video_pad|>"
|
| 196 |
-
],
|
| 197 |
"bos_token": null,
|
| 198 |
"clean_up_tokenization_spaces": false,
|
| 199 |
"eos_token": "<|im_end|>",
|
| 200 |
"errors": "replace",
|
| 201 |
-
"
|
|
|
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
| 204 |
"processor_class": "Qwen2VLProcessor",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": null,
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|im_end|>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
"model_max_length": 131072,
|
| 11 |
"pad_token": "<|endoftext|>",
|
| 12 |
"processor_class": "Qwen2VLProcessor",
|
scheduler/scheduler_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"base_image_seq_len": 256,
|
| 5 |
"base_shift": 0.5,
|
| 6 |
"invert_sigmas": false,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 4 |
"base_image_seq_len": 256,
|
| 5 |
"base_shift": 0.5,
|
| 6 |
"invert_sigmas": false,
|
text_encoder/config.json
CHANGED
|
@@ -2,33 +2,11 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"attention_dropout": 0.0,
|
| 6 |
-
"bos_token_id": 151643,
|
| 7 |
"dtype": "bfloat16",
|
| 8 |
-
"
|
| 9 |
-
"hidden_act": "silu",
|
| 10 |
-
"hidden_size": 3584,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 18944,
|
| 13 |
-
"max_position_embeddings": 128000,
|
| 14 |
-
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen2_5_vl",
|
| 16 |
-
"num_attention_heads": 28,
|
| 17 |
-
"num_hidden_layers": 28,
|
| 18 |
-
"num_key_value_heads": 4,
|
| 19 |
-
"rms_norm_eps": 1e-06,
|
| 20 |
-
"rope_scaling": {
|
| 21 |
-
"mrope_section": [
|
| 22 |
-
16,
|
| 23 |
-
24,
|
| 24 |
-
24
|
| 25 |
-
],
|
| 26 |
-
"rope_type": "default",
|
| 27 |
-
"type": "default"
|
| 28 |
-
},
|
| 29 |
-
"rope_theta": 1000000.0,
|
| 30 |
-
"sliding_window": 32768,
|
| 31 |
"text_config": {
|
|
|
|
| 32 |
"architectures": [
|
| 33 |
"Qwen2_5_VLForConditionalGeneration"
|
| 34 |
],
|
|
@@ -38,7 +16,6 @@
|
|
| 38 |
"eos_token_id": 151645,
|
| 39 |
"hidden_act": "silu",
|
| 40 |
"hidden_size": 3584,
|
| 41 |
-
"image_token_id": 151655,
|
| 42 |
"initializer_range": 0.02,
|
| 43 |
"intermediate_size": 18944,
|
| 44 |
"layer_types": [
|
|
@@ -77,30 +54,27 @@
|
|
| 77 |
"num_attention_heads": 28,
|
| 78 |
"num_hidden_layers": 28,
|
| 79 |
"num_key_value_heads": 4,
|
|
|
|
| 80 |
"rms_norm_eps": 1e-06,
|
| 81 |
-
"
|
| 82 |
"mrope_section": [
|
| 83 |
16,
|
| 84 |
24,
|
| 85 |
24
|
| 86 |
],
|
|
|
|
| 87 |
"rope_type": "default",
|
| 88 |
"type": "default"
|
| 89 |
},
|
| 90 |
-
"rope_theta": 1000000.0,
|
| 91 |
"sliding_window": null,
|
| 92 |
"use_cache": true,
|
| 93 |
"use_sliding_window": false,
|
| 94 |
-
"video_token_id": 151656,
|
| 95 |
-
"vision_end_token_id": 151653,
|
| 96 |
-
"vision_start_token_id": 151652,
|
| 97 |
"vision_token_id": 151654,
|
| 98 |
"vocab_size": 152064
|
| 99 |
},
|
| 100 |
"tie_word_embeddings": false,
|
| 101 |
-
"transformers_version": "
|
| 102 |
-
"
|
| 103 |
-
"use_sliding_window": false,
|
| 104 |
"vision_config": {
|
| 105 |
"depth": 32,
|
| 106 |
"dtype": "bfloat16",
|
|
@@ -116,7 +90,7 @@
|
|
| 116 |
"in_chans": 3,
|
| 117 |
"initializer_range": 0.02,
|
| 118 |
"intermediate_size": 3420,
|
| 119 |
-
"model_type": "
|
| 120 |
"num_heads": 16,
|
| 121 |
"out_hidden_size": 3584,
|
| 122 |
"patch_size": 14,
|
|
@@ -126,6 +100,7 @@
|
|
| 126 |
"tokens_per_second": 2,
|
| 127 |
"window_size": 112
|
| 128 |
},
|
| 129 |
-
"
|
| 130 |
-
"
|
|
|
|
| 131 |
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
| 5 |
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"model_type": "qwen2_5_vl",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"text_config": {
|
| 9 |
+
"_name_or_path": "/cpfs01/haoyangzhang/pretrained_weights/Qwen2.5-VL",
|
| 10 |
"architectures": [
|
| 11 |
"Qwen2_5_VLForConditionalGeneration"
|
| 12 |
],
|
|
|
|
| 16 |
"eos_token_id": 151645,
|
| 17 |
"hidden_act": "silu",
|
| 18 |
"hidden_size": 3584,
|
|
|
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
"intermediate_size": 18944,
|
| 21 |
"layer_types": [
|
|
|
|
| 54 |
"num_attention_heads": 28,
|
| 55 |
"num_hidden_layers": 28,
|
| 56 |
"num_key_value_heads": 4,
|
| 57 |
+
"pad_token_id": null,
|
| 58 |
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_parameters": {
|
| 60 |
"mrope_section": [
|
| 61 |
16,
|
| 62 |
24,
|
| 63 |
24
|
| 64 |
],
|
| 65 |
+
"rope_theta": 1000000.0,
|
| 66 |
"rope_type": "default",
|
| 67 |
"type": "default"
|
| 68 |
},
|
|
|
|
| 69 |
"sliding_window": null,
|
| 70 |
"use_cache": true,
|
| 71 |
"use_sliding_window": false,
|
|
|
|
|
|
|
|
|
|
| 72 |
"vision_token_id": 151654,
|
| 73 |
"vocab_size": 152064
|
| 74 |
},
|
| 75 |
"tie_word_embeddings": false,
|
| 76 |
+
"transformers_version": "5.8.0",
|
| 77 |
+
"video_token_id": 151656,
|
|
|
|
| 78 |
"vision_config": {
|
| 79 |
"depth": 32,
|
| 80 |
"dtype": "bfloat16",
|
|
|
|
| 90 |
"in_chans": 3,
|
| 91 |
"initializer_range": 0.02,
|
| 92 |
"intermediate_size": 3420,
|
| 93 |
+
"model_type": "qwen2_5_vl_vision",
|
| 94 |
"num_heads": 16,
|
| 95 |
"out_hidden_size": 3584,
|
| 96 |
"patch_size": 14,
|
|
|
|
| 100 |
"tokens_per_second": 2,
|
| 101 |
"window_size": 112
|
| 102 |
},
|
| 103 |
+
"vision_end_token_id": 151653,
|
| 104 |
+
"vision_start_token_id": 151652,
|
| 105 |
+
"vision_token_id": 151654
|
| 106 |
}
|
text_encoder/generation_config.json
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 151643,
|
| 9 |
-
"repetition_penalty": 1.05,
|
| 10 |
-
"temperature": 0.1,
|
| 11 |
-
"top_k": 1,
|
| 12 |
-
"top_p": 0.001,
|
| 13 |
-
"transformers_version": "4.57.6"
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "5.8.0",
|
| 6 |
+
"use_cache": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26fa644c8e61aa8185da5055b61aa28d6897fee102c2f43173acab657c4257a1
|
| 3 |
+
size 16584415608
|
tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
|
| 3 |
+
size 11422166
|
tokenizer/tokenizer_config.json
CHANGED
|
@@ -1,204 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
}
|
| 181 |
-
},
|
| 182 |
-
"additional_special_tokens": [
|
| 183 |
-
"<|im_start|>",
|
| 184 |
-
"<|im_end|>",
|
| 185 |
-
"<|object_ref_start|>",
|
| 186 |
-
"<|object_ref_end|>",
|
| 187 |
-
"<|box_start|>",
|
| 188 |
-
"<|box_end|>",
|
| 189 |
-
"<|quad_start|>",
|
| 190 |
-
"<|quad_end|>",
|
| 191 |
-
"<|vision_start|>",
|
| 192 |
-
"<|vision_end|>",
|
| 193 |
-
"<|vision_pad|>",
|
| 194 |
-
"<|image_pad|>",
|
| 195 |
-
"<|video_pad|>"
|
| 196 |
-
],
|
| 197 |
"bos_token": null,
|
| 198 |
"clean_up_tokenization_spaces": false,
|
| 199 |
"eos_token": "<|im_end|>",
|
| 200 |
"errors": "replace",
|
| 201 |
-
"
|
|
|
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
| 204 |
"split_special_tokens": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": null,
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|im_end|>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
"model_max_length": 131072,
|
| 11 |
"pad_token": "<|endoftext|>",
|
| 12 |
"split_special_tokens": false,
|
transformer/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "QwenImageTransformer2DModel",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
-
"_name_or_path": "/
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"axes_dims_rope": [
|
| 7 |
16,
|
|
@@ -17,5 +17,5 @@
|
|
| 17 |
"patch_size": 2,
|
| 18 |
"use_additional_t_cond": false,
|
| 19 |
"use_layer3d_rope": false,
|
| 20 |
-
"zero_cond_t":
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "QwenImageTransformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 4 |
+
"_name_or_path": "/home/anichiu/.cache/huggingface/hub/models--Qwen--Qwen-Image-Edit-2511/snapshots/6f3ccc0b56e431dc6a0c2b2039706d7d26f22cb9/transformer",
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"axes_dims_rope": [
|
| 7 |
16,
|
|
|
|
| 17 |
"patch_size": 2,
|
| 18 |
"use_additional_t_cond": false,
|
| 19 |
"use_layer3d_rope": false,
|
| 20 |
+
"zero_cond_t": true
|
| 21 |
}
|
transformer/diffusion_pytorch_model-00001-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9973578592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31a1741bc2327b56d12038a813fc346679d78ba2ba73ede9d37f314395dd99f0
|
| 3 |
size 9973578592
|
transformer/diffusion_pytorch_model-00002-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9987326072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d50b01199da4f32074c71ce48ae341e6dc80d9510ca6db2f60c23e2710b7973
|
| 3 |
size 9987326072
|
transformer/diffusion_pytorch_model-00003-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9987307440
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b8f32b6a3494efa3ffd5334ace99c517fc76918e0342e1fa8ebaba9659e30cb
|
| 3 |
size 9987307440
|
transformer/diffusion_pytorch_model-00004-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9930685712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:538e985f17e59039a2cd47b8e0d166388b304f2e05035f6a5d9a02900844390f
|
| 3 |
size 9930685712
|
transformer/diffusion_pytorch_model-00005-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 982130472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec3c290a94356690fb4a521f8941bfe308864387024f39d010c77efb4a21cda3
|
| 3 |
size 982130472
|
vae/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKLQwenImage",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
-
"_name_or_path": "/
|
| 5 |
"attn_scales": [],
|
| 6 |
"base_dim": 96,
|
| 7 |
"dim_mult": [
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKLQwenImage",
|
| 3 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 4 |
+
"_name_or_path": "/home/anichiu/.cache/huggingface/hub/models--Qwen--Qwen-Image-Edit-2511/snapshots/6f3ccc0b56e431dc6a0c2b2039706d7d26f22cb9/vae",
|
| 5 |
"attn_scales": [],
|
| 6 |
"base_dim": 96,
|
| 7 |
"dim_mult": [
|