Flux, Flux Lighting, 16/8 bits workflows

docs/Flows/Flux_1.rst

@@ -0,0 +1,56 @@
+.. _Flux1:
+
+Flux 1
+======
+
+**FLUX.1** is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read `blog post <https://blackforestlabs.ai/announcing-black-forest-labs/>`_.
+
+*The model is extremely demanding on hardware.*
+
+Even on 24 Gigabytes, the speed of the model in the full version leaves much to be desired, since this basic flow does not fit completely into the video card cache.
+
+Lightning versions are quite good and generate quite good pictures in 4 steps.
+
+.. note::
+    Totally with with model there are 4 different flows: Flux, Flux (Small), Flux Lighting, Flux Lighting (Small)
+
+**Supports various aspect ratios.**
+
+**Supports different number of steps for non-Lighting versions.**
+
+Hardware
+""""""""
+
+- **Required memory: 12 GB for Small versions, 24 GB for usual**
+
+Time to generate 1 image with default **Flux**:
+
+- AMD 7900 XTX: **86 sec** (25 steps) / **152 sec** (50 steps)
+- Apple M2 Max: **XX sec**
+
+Time to generate 1 image with default **Flux Lighting (Small)**:
+
+- AMD 7900 XTX: **8 sec**
+- NVIDIA RTX 3060 (12 GB): **XX sec**
+- Apple M2 Max: **XX sec**
+
+Flux Small Example
+""""""""""""""""""
+
+.. image:: /FlowsResults/Flux_1_1.png
+
+Prompt: "*photo-realistic portrait of a cute kitten in cyberpunk style holding sign "Visionatrix" in ultra quality with high details*"
+
+Flux Lighting Example
+"""""""""""""""""""""
+
+.. image:: /FlowsResults/Flux_1_2.png
+
+Prompt: "*A cool man is driving a luxury car through a night city. The scene captures the vibrant nightlife with glowing neon signs, tall skyscrapers, and bustling streets. The dad is stylishly dressed, exuding confidence and charisma. The luxury car, sleek and modern, reflects the city lights, enhancing the atmosphere of urban sophistication and adventure.*"
+
+Flux Example (50 steps)
+"""""""""""""""""""""""
+
+.. image:: /FlowsResults/Flux_1_3.png
+
+Prompt: "*Portrait of beautiful woman in a swimsuit is lounging under a palm tree on a tropical beach. The scene is photorealistic, capturing the serene and picturesque setting with clear blue skies, gentle waves, and white sandy shores. The palm tree provides shade, and the overall atmosphere is one of leisure and tropical paradise.*"

docs/Flows/index.rst

@@ -5,6 +5,7 @@ Available Flows
    :maxdepth: 1
 
    SDXL_Lighting
+   Flux_1
    Playground_2_5_aesthetic
    Playground_2_5_prometheus
    Juggernaut_Lite

flows/colorful_xl.json

@@ -287,7 +287,7 @@
       "homepage": "https://github.com/bigcat88",
       "documentation": "https://visionatrix.github.io/VixFlowsDocs/Flows/Colorful_XL.html",
       "license": "",
-      "tags": "[\"general\"]",
+      "tags": "[\"general\", \"simple\"]",
       "version": "1.0.0"
     },
     "class_type": "VixUiWorkflowMetadata",

flows/flux1_dev.json

@@ -0,0 +1,245 @@
+{
+  "6": {
+    "inputs": {
+      "text": [
+        "31",
+        0
+      ],
+      "clip": [
+        "11",
+        0
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Positive Prompt)"
+    }
+  },
+  "8": {
+    "inputs": {
+      "samples": [
+        "13",
+        0
+      ],
+      "vae": [
+        "10",
+        0
+      ]
+    },
+    "class_type": "VAEDecode",
+    "_meta": {
+      "title": "VAE Decode"
+    }
+  },
+  "9": {
+    "inputs": {
+      "filename_prefix": "ComfyUI",
+      "images": [
+        "8",
+        0
+      ]
+    },
+    "class_type": "SaveImage",
+    "_meta": {
+      "title": "Save Image"
+    }
+  },
+  "10": {
+    "inputs": {
+      "vae_name": "ae.sft"
+    },
+    "class_type": "VAELoader",
+    "_meta": {
+      "title": "Load VAE"
+    }
+  },
+  "11": {
+    "inputs": {
+      "clip_name1": "t5xxl_fp16.safetensors",
+      "clip_name2": "clip_l.safetensors",
+      "type": "flux"
+    },
+    "class_type": "DualCLIPLoader",
+    "_meta": {
+      "title": "DualCLIPLoader"
+    }
+  },
+  "12": {
+    "inputs": {
+      "unet_name": "flux1-dev.sft",
+      "weight_dtype": "default"
+    },
+    "class_type": "UNETLoader",
+    "_meta": {
+      "title": "Load Diffusion Model"
+    }
+  },
+  "13": {
+    "inputs": {
+      "noise": [
+        "25",
+        0
+      ],
+      "guider": [
+        "22",
+        0
+      ],
+      "sampler": [
+        "16",
+        0
+      ],
+      "sigmas": [
+        "17",
+        0
+      ],
+      "latent_image": [
+        "27",
+        0
+      ]
+    },
+    "class_type": "SamplerCustomAdvanced",
+    "_meta": {
+      "title": "SamplerCustomAdvanced"
+    }
+  },
+  "16": {
+    "inputs": {
+      "sampler_name": "euler"
+    },
+    "class_type": "KSamplerSelect",
+    "_meta": {
+      "title": "KSamplerSelect"
+    }
+  },
+  "17": {
+    "inputs": {
+      "scheduler": "simple",
+      "steps": [
+        "34",
+        0
+      ],
+      "denoise": 1,
+      "model": [
+        "12",
+        0
+      ]
+    },
+    "class_type": "BasicScheduler",
+    "_meta": {
+      "title": "BasicScheduler"
+    }
+  },
+  "22": {
+    "inputs": {
+      "model": [
+        "12",
+        0
+      ],
+      "conditioning": [
+        "26",
+        0
+      ]
+    },
+    "class_type": "BasicGuider",
+    "_meta": {
+      "title": "BasicGuider"
+    }
+  },
+  "25": {
+    "inputs": {
+      "noise_seed": 219670278747233
+    },
+    "class_type": "RandomNoise",
+    "_meta": {
+      "title": "RandomNoise"
+    }
+  },
+  "26": {
+    "inputs": {
+      "guidance": 3.5,
+      "conditioning": [
+        "6",
+        0
+      ]
+    },
+    "class_type": "FluxGuidance",
+    "_meta": {
+      "title": "FluxGuidance"
+    }
+  },
+  "27": {
+    "inputs": {
+      "width": [
+        "30",
+        1
+      ],
+      "height": [
+        "30",
+        2
+      ],
+      "batch_size": 1
+    },
+    "class_type": "EmptySD3LatentImage",
+    "_meta": {
+      "title": "EmptySD3LatentImage"
+    }
+  },
+  "30": {
+    "inputs": {
+      "aspect_ratio": "1:1"
+    },
+    "class_type": "SDXLAspectRatioSelector",
+    "_meta": {
+      "title": "input;Aspect Ratio;optional;advanced;order=2"
+    }
+  },
+  "31": {
+    "inputs": {
+      "text": "",
+      "display_name": "Prompt",
+      "optional": false,
+      "advanced": false,
+      "order": 1,
+      "custom_id": "prompt"
+    },
+    "class_type": "VixUiPrompt",
+    "_meta": {
+      "title": "VixUI-Prompt"
+    }
+  },
+  "32": {
+    "inputs": {
+      "name": "flux1_dev",
+      "display_name": "Flux",
+      "description": "Excellent model that perfectly generates not only the objects, but also the text",
+      "author": "ComfyOrg",
+      "homepage": "https://huggingface.co/black-forest-labs/FLUX.1-dev",
+      "documentation": "https://comfyanonymous.github.io/ComfyUI_examples/flux/#simple-to-use-fp8-checkpoint-version",
+      "license": "",
+      "tags": "[\"general\", \"simple\"]",
+      "version": "1.0.0",
+      "requires": "[]"
+    },
+    "class_type": "VixUiWorkflowMetadata",
+    "_meta": {
+      "title": "VixUI-WorkflowMetadata"
+    }
+  },
+  "34": {
+    "inputs": {
+      "value": 25,
+      "display_name": "Steps number to generate",
+      "optional": true,
+      "advanced": true,
+      "min": 20,
+      "max": 50,
+      "step": 1,
+      "order": 99,
+      "custom_id": "steps_count"
+    },
+    "class_type": "VixUiRangeInt",
+    "_meta": {
+      "title": "VixUI-RangeInt"
+    }
+  }
+}