Initial commit

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+license: other
+license_name: stabilityai-ai-community
+license_link: LICENSE.md
+language:
+- en
+base_model:
+- stabilityai/stable-diffusion-3.5-medium
+pipeline_tag: text-to-image
+---
+
+<div align="center">
+
+**Bokeh_Depth_Control**
+
+<img src="show.jpg"/>
+</div>
+
+## Description
+
+- Input Image: Depth information map generated by depth estimation model
+- Output Image: Base model integrates depth information for control, generating more realistic depth-of-field effects and spatial structure control.
+
+The depth map enables the model to better understand spatial relationships within images, achieving more precise depth-of-field control and three-dimensional effect generation.
+
+## Example
+| input | output | Prompt |
+|---|---|---|
+| ![input](./images/001_depth.png) | ![output](./images/001.png) | a old man |
+| ![input](./images/002_depth.png) | ![output](./images/002.png) | A lone astronaut in a white suit and helmet, with a backpack, strolls on a rocky, red landscape under a star galaxy |
+| ![input](./images/003_depth.png) | ![output](./images/003.png) | a eagle , black background |
+| ![input](./images/004_depth.png) | ![output](./images/004.png) | A crystal heart sits on a gnarly, moss-covered log, with a galaxy background. |
+
+## Use 
+We recommend using ComfyUI for local inference
+![input](./comfy.png)
+
+# With Bokeh
+```python
+import torch
+from diffusers import StableDiffusion3ControlNetPipeline
+from diffusers import SD3ControlNetModel
+from diffusers.utils import load_image
+
+controlnet = SD3ControlNetModel.from_pretrained("tensorart/Bokeh_Depth_Control")
+pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
+    "tensorart/bokeh_3.5_medium",
+    controlnet=controlnet
+)
+pipe.to("cuda", torch.float16)
+
+control_image = load_image("https://huggingface.co/tensorart/Bokeh_Depth_Control/resolve/main/images/001_depth.png")
+prompt = "A old man talking"
+negative_prompt ="anime,render,cartoon,3d"
+negative_prompt_3=""
+
+image = pipe(
+    prompt, 
+    num_inference_steps=30,
+    negative_prompt=negative_prompt, 
+    control_image=control_image, 
+    height=1440,
+    width=1440,
+    guidance_scale=4,
+    controlnet_conditioning_scale=0.8
+).images[0]
+image.save('image.jpg')
+```
+
+
+## Contact
+* Website: https://tensor.art  https://tusiart.com
+* Developed by: TensorArt
+* Api: https://tams.tensor.art/
+
+
+
+

bokeh_cn_workflow.json

@@ -0,0 +1,869 @@
+{
+  "last_node_id": 93,
+  "last_link_id": 370,
+  "nodes": [
+    {
+      "id": 17,
+      "type": "PrimitiveNode",
+      "pos": {
+        "0": 40,
+        "1": -202
+      },
+      "size": {
+        "0": 298.4656982421875,
+        "1": 99.21678161621094
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "INT",
+          "type": "INT",
+          "links": [
+            288
+          ],
+          "slot_index": 0,
+          "widget": {
+            "name": "seed"
+          }
+        }
+      ],
+      "title": "seed",
+      "properties": {
+        "Run widget replace on values": false
+      },
+      "widgets_values": [
+        349829797374617,
+        "increment"
+      ]
+    },
+    {
+      "id": 52,
+      "type": "PrimitiveNode",
+      "pos": {
+        "0": 37,
+        "1": -361
+      },
+      "size": {
+        "0": 309.40350341796875,
+        "1": 96.14453887939453
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "STRING",
+          "type": "STRING",
+          "links": [
+            222,
+            223
+          ],
+          "slot_index": 0,
+          "widget": {
+            "name": "clip_g"
+          }
+        }
+      ],
+      "title": "Negative_prompt",
+      "properties": {
+        "Run widget replace on values": false
+      },
+      "widgets_values": [
+        "anime,render,cartoon,3d"
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CLIPTextEncodeSD3",
+      "pos": {
+        "0": 462,
+        "1": -460
+      },
+      "size": {
+        "0": 346.1516418457031,
+        "1": 140
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 370
+        },
+        {
+          "name": "clip_g",
+          "type": "STRING",
+          "link": 222,
+          "widget": {
+            "name": "clip_g"
+          }
+        },
+        {
+          "name": "clip_l",
+          "type": "STRING",
+          "link": 223,
+          "widget": {
+            "name": "clip_l"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            347
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncodeSD3"
+      },
+      "widgets_values": [
+        "anime,render,cartoon,3d",
+        "anime,render,cartoon,3d",
+        "",
+        "none"
+      ]
+    },
+    {
+      "id": 32,
+      "type": "CLIPTextEncodeSD3",
+      "pos": {
+        "0": 462,
+        "1": -626
+      },
+      "size": {
+        "0": 344.10260009765625,
+        "1": 118
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 369
+        },
+        {
+          "name": "clip_g",
+          "type": "STRING",
+          "link": 122,
+          "widget": {
+            "name": "clip_g"
+          }
+        },
+        {
+          "name": "clip_l",
+          "type": "STRING",
+          "link": 123,
+          "widget": {
+            "name": "clip_l"
+          }
+        },
+        {
+          "name": "t5xxl",
+          "type": "STRING",
+          "link": 152,
+          "widget": {
+            "name": "t5xxl"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            346
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncodeSD3"
+      },
+      "widgets_values": [
+        "a eagle , black background",
+        "a eagle , black background",
+        "a eagle , black background",
+        "empty_prompt"
+      ]
+    },
+    {
+      "id": 13,
+      "type": "CheckpointLoaderSimple",
+      "pos": {
+        "0": -402,
+        "1": -686
+      },
+      "size": {
+        "0": 746.5433349609375,
+        "1": 98
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            368
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            369,
+            370
+          ],
+          "slot_index": 1
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            292,
+            351
+          ],
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "bokeh_medium_t5xxlfp8.safetensors"
+      ]
+    },
+    {
+      "id": 86,
+      "type": "LoadImage",
+      "pos": {
+        "0": -409,
+        "1": -537
+      },
+      "size": {
+        "0": 413.1280822753906,
+        "1": 623.165771484375
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            366
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "tmptiilbkl9 (2).png",
+        "image"
+      ]
+    },
+    {
+      "id": 88,
+      "type": "ImageScale",
+      "pos": {
+        "0": 24,
+        "1": -49
+      },
+      "size": {
+        "0": 315,
+        "1": 130
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 366
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            354,
+            355
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageScale"
+      },
+      "widgets_values": [
+        "nearest-exact",
+        1152,
+        1728,
+        "disabled"
+      ]
+    },
+    {
+      "id": 87,
+      "type": "EmptyLatentImage",
+      "pos": {
+        "0": 464,
+        "1": -140
+      },
+      "size": {
+        "0": 352.0178527832031,
+        "1": 106
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            367
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        1152,
+        1728,
+        1
+      ]
+    },
+    {
+      "id": 72,
+      "type": "PreviewImage",
+      "pos": {
+        "0": 1956,
+        "1": -611
+      },
+      "size": {
+        "0": 1634.2325439453125,
+        "1": 1421.76123046875
+      },
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 293
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 89,
+      "type": "PreviewImage",
+      "pos": {
+        "0": 473,
+        "1": 13
+      },
+      "size": {
+        "0": 1328.8507080078125,
+        "1": 952.4451904296875
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 355
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 85,
+      "type": "ControlNetApplyAdvanced",
+      "pos": {
+        "0": 949,
+        "1": -574
+      },
+      "size": {
+        "0": 268.9471435546875,
+        "1": 186
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 346
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 347
+        },
+        {
+          "name": "control_net",
+          "type": "CONTROL_NET",
+          "link": 345
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 354
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 351,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "links": [
+            348
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "links": [
+            349
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetApplyAdvanced"
+      },
+      "widgets_values": [
+        0.7000000000000001,
+        0,
+        1
+      ]
+    },
+    {
+      "id": 71,
+      "type": "VAEDecode",
+      "pos": {
+        "0": 1417,
+        "1": -312
+      },
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 291
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 292
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            293
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 70,
+      "type": "KSampler",
+      "pos": {
+        "0": 951,
+        "1": -341
+      },
+      "size": {
+        "0": 278.6439514160156,
+        "1": 234
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 368
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 348
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 349
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 367
+        },
+        {
+          "name": "seed",
+          "type": "INT",
+          "link": 288,
+          "widget": {
+            "name": "seed"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            291
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        349829797374617,
+        "randomize",
+        28,
+        4.5,
+        "dpmpp_2m",
+        "sgm_uniform",
+        1
+      ]
+    },
+    {
+      "id": 20,
+      "type": "PrimitiveNode",
+      "pos": {
+        "0": 32,
+        "1": -543
+      },
+      "size": {
+        "0": 314.90277099609375,
+        "1": 150.342529296875
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 5,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "STRING",
+          "type": "STRING",
+          "links": [
+            122,
+            123,
+            152
+          ],
+          "slot_index": 0,
+          "widget": {
+            "name": "clip_g"
+          }
+        }
+      ],
+      "title": "Positive_prompt",
+      "properties": {
+        "Run widget replace on values": false
+      },
+      "widgets_values": [
+        "a eagle , black background"
+      ]
+    },
+    {
+      "id": 84,
+      "type": "ControlNetLoader",
+      "pos": {
+        "0": 445,
+        "1": -268
+      },
+      "size": {
+        "0": 368.3169250488281,
+        "1": 78.63841247558594
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CONTROL_NET",
+          "type": "CONTROL_NET",
+          "links": [
+            345
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetLoader"
+      },
+      "widgets_values": [
+        "bokeh_depth_cn.safetensors"
+      ]
+    }
+  ],
+  "links": [
+    [
+      122,
+      20,
+      0,
+      32,
+      1,
+      "STRING"
+    ],
+    [
+      123,
+      20,
+      0,
+      32,
+      2,
+      "STRING"
+    ],
+    [
+      152,
+      20,
+      0,
+      32,
+      3,
+      "STRING"
+    ],
+    [
+      222,
+      52,
+      0,
+      30,
+      1,
+      "STRING"
+    ],
+    [
+      223,
+      52,
+      0,
+      30,
+      2,
+      "STRING"
+    ],
+    [
+      288,
+      17,
+      0,
+      70,
+      4,
+      "INT"
+    ],
+    [
+      291,
+      70,
+      0,
+      71,
+      0,
+      "LATENT"
+    ],
+    [
+      292,
+      13,
+      2,
+      71,
+      1,
+      "VAE"
+    ],
+    [
+      293,
+      71,
+      0,
+      72,
+      0,
+      "IMAGE"
+    ],
+    [
+      345,
+      84,
+      0,
+      85,
+      2,
+      "CONTROL_NET"
+    ],
+    [
+      346,
+      32,
+      0,
+      85,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      347,
+      30,
+      0,
+      85,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      348,
+      85,
+      0,
+      70,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      349,
+      85,
+      1,
+      70,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      351,
+      13,
+      2,
+      85,
+      4,
+      "VAE"
+    ],
+    [
+      354,
+      88,
+      0,
+      85,
+      3,
+      "IMAGE"
+    ],
+    [
+      355,
+      88,
+      0,
+      89,
+      0,
+      "IMAGE"
+    ],
+    [
+      366,
+      86,
+      0,
+      88,
+      0,
+      "IMAGE"
+    ],
+    [
+      367,
+      87,
+      0,
+      70,
+      3,
+      "LATENT"
+    ],
+    [
+      368,
+      13,
+      0,
+      70,
+      0,
+      "MODEL"
+    ],
+    [
+      369,
+      13,
+      1,
+      32,
+      0,
+      "CLIP"
+    ],
+    [
+      370,
+      13,
+      1,
+      30,
+      0,
+      "CLIP"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.4305676431343139,
+      "offset": [
+        636.7262178838369,
+        1199.3097356274905
+      ]
+    }
+  },
+  "version": 0.4
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "SD3ControlNetModel",
+  "_diffusers_version": "0.32.0.dev0",
+  "_name_or_path": "tensorart/bokeh_3.5_medium",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12
+  ],
+  "extra_conditioning_channels": 0,
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 23,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 384,
+  "qk_norm": "rms_norm",
+  "sample_size": 128
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737a877ad74bd8ad785ad7375e1bf2c2c5cd2f92863aafa4d2a06bbfe4d28793
+size 4930003400