Sync 5 new model versions from Civitai (Batch 4/5)

Z-Image-Turbo-AIO-Workflow/ZImageTurbo/zImageTurboAIO_zImageTruboAIOV10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9b5a46ce95804ff984f4950c86b9b344ba84b4f9eb2b9ba8c6a7ce844d66db
+size 478204

Z-image-hires_Workflow/ZImageTurbo/zImageHiresWorkflow_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26df5cce44c682340c1339552d19349a053ceb034c034909ff0af1a9a4ce2e1
+size 3796

Z-image_Creation_-Text_To_image_the_strongest_realistic_portrait/ZImageTurbo/zImageCreationTextToImage_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a983a8e071d5e44a4493c2ef729e9e2ebb04805f3e69b46e1d701130292a5d04
+size 2653

Z-image_image_generation_image_washing_workflow/ZImageTurbo/zImageImageGeneration_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e394513377f282f60cab16797b70716475105bb2ca9a0e93349706930ca6f78f
+size 8396

Z-image_turbo_workflow__CivitAI_metadata_upscaling_FaceDetailer_indexing_elements_inpainting_ComfyUI_beginner_friendly/ZImageTurbo/zImageTurboWorkflowCivitaiMetadata_v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81be10e29a1a0727dff32078431b9ade985a6ee858dc654e43345c8893e81cd
+size 12190

ZImageTurbo_info.md

@@ -6343,4 +6343,377 @@ Feeds back the last output back into the input and shuffles it to change the lat
 *   **Size**: 1.18 MB
 *   **Hash (AutoV2)**: `82021E38DA`
 *   **Hash (SHA256)**: `82021E38DA100C26DADAC25AB2D0941060F544395F3D11C971A0B078DA5F1567`
+---
+
+---
+# Z-Image-Turbo-AIO-Workflow (Version: Z-Image-Trubo-AIO-v1.0)
+**Creator**: [SeeSeeLP](https://civitai.com/user/SeeSeeLP)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-28
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2174008
+**Civitai Version ID**: 2448186
+**Stats (at time of fetch for this version)**:
+*   Downloads: 449
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+🚀 Official ComfyUI Workflow for Z-Image-Turbo-AIO
+Works with both FP8 (10GB) and BF16 (20GB) versions!
+✨ What's Special About This Workflow?
+Optimized specifically for
+Z-Image-Turbo-AIO
+models:
+✅
+Pre-configured settings
+- 8/9 steps, CFG 1.0, res_multistep
+✅
+All-in-One ready
+- No separate VAE/encoder needed
+✅
+Bilingual support
+- EN/CN text rendering
+✅
+RTX 4060 tested
+- Works on 8GB VRAM
+✅
+Simple setup
+- Just load and go!
+📦 What's Included
+Complete Workflow:
+📦
+Model loading
+- Single checkpoint
+✍️
+Prompt input
+- Natural language optimized
+📐
+Resolution presets
+- 1920×1088 and more
+🎨
+Generation
+- 8-step configured
+🔍
+Settings
+- All pre-configured
+Pre-Configured:
+Steps:
+8/9 (perfect for Turbo)
+CFG:
+1.0 (optimal setting)
+Sampler:
+res_multistep (tested best)
+Scheduler:
+simple (clean results)
+Resolution:
+1920×1088 (tested)
+⚙️ Requirements
+Essential:
+✅
+ComfyUI
+(latest version)
+✅
+Z-Image-Turbo-AIO
+(FP8 or BF16)
+Custom Nodes:
+✅
+rgthree-comfy
+-
+https://github.com/rgthree/rgthree-comfy
+NOT Needed:
+❌ Separate VAE
+❌ Separate Text Encoder
+❌ Lightning LoRAs
+❌ Negative prompts
+🚀 Quick Start
+Installation:
+Download Z-Image-Turbo-AIO (FP8 or BF16)
+Place in
+ComfyUI/models/checkpoints/
+Download this workflow JSON
+Drag into ComfyUI
+Generate!
+First Generation:
+Model: Z-Image-Turbo-AIO (FP8 or BF16)
+Steps: 9
+CFG: 1.0
+Sampler: res_multistep
+Scheduler: simple
+Resolution: 1920×1088
+Example Prompt:
+Professional food photography of artisan breakfast plate. 
+Golden poached eggs on sourdough toast, crispy bacon, fresh 
+avocado slices, cherry tomatoes. White ceramic plate on rustic 
+wood table. Morning sunlight from window creating warm glow. 
+Shallow depth of field, appetizing presentation, magazine quality.
+💡 Prompting Tips
+Natural Language:
+✅ GOOD: A cozy bookstore with floor-to-ceiling wooden 
+shelves, comfortable reading nooks, warm lighting, 
+peaceful afternoon atmosphere, professional photography
+Bilingual Text:
+✅ English: "Neon sign reading 'OPEN 24/7' in bright blue"
+✅ Chinese: "Sign with '咖啡店' in gold calligraphy"
+Tips:
+✅ Natural language (not tags)
+✅ Detailed (100-300 words)
+✅ Include lighting & mood
+❌ No negative prompts
+❓ FAQ
+Q: FP8 or BF16 workflow?
+A: Same workflow works for both!
+Q: Can I change CFG?
+A: Keep at 1.0 for best results.
+Q: Why res_multistep?
+A: Works best with Z-Image-Turbo.
+Q: Need negative prompts?
+A: No! Not used.
+Q: Works on 8GB VRAM?
+A: Yes! Both versions tested on RTX 4060.
+Q: Can I render Chinese?
+A: Yes! Describe in prompt.
+Version:
+1.0
+Updated:
+November 2025
+Compatibility:
+Both FP8 & BF16
+Download and start creating!
+🚀
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2174008?modelVersionId=2448186)**
+*   [View Full Model Page →](https://civitai.com/models/2174008)
+*   [View Creator Profile →](https://civitai.com/user/SeeSeeLP)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTurboAIO_zImageTruboAIOV10.zip`
+*   **Size**: 0.46 MB
+*   **Hash (AutoV2)**: `5E9B5A46CE`
+*   **Hash (SHA256)**: `5E9B5A46CE95804FF984F4950C86B9B344BA84B4F9EB2B9BA8C6A7CE844D66DB`
+---
+
+---
+# Z-image Creation -Text To image (the strongest realistic portrait) (Version: v1.0)
+**Creator**: [AIGC_Singularity](https://civitai.com/user/AIGC_Singularity)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-28
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2173992
+**Civitai Version ID**: 2448156
+**Stats (at time of fetch for this version)**:
+*   Downloads: 117
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+You can click on the link below to try it out directly. If the effect is good, you can deploy it locally
+https://www.runninghub.ai/post/1994314682653671425/?inviteCode=sdhs0trb
+Fan benefits,register to get 1000 points,daily login 100 points,play 4090!  Experience the super power of 48G.
+This is Qwen's latest Wenshengtu model workflow focused on portrait generation, which can generate realistic portraits far superior to Flux2. To use the workflow, the following models need to be downloaded:
+1.z_image_turbo_bf16
+2.qwen_3_4b
+3.diffusion_pytorch_model
+Cloud storage download:
+https://pan.quark.cn/s/fa65cc7a125d
+Download link:
+https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2173992?modelVersionId=2448156)**
+*   [View Full Model Page →](https://civitai.com/models/2173992)
+*   [View Creator Profile →](https://civitai.com/user/AIGC_Singularity)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageCreationTextToImage_v10.zip`
+*   **Size**: 0.00 MB
+*   **Hash (AutoV2)**: `A983A8E071`
+*   **Hash (SHA256)**: `A983A8E071D5E44A4493C2EF729E9E2EBB04805F3E69B46E1D701130292A5D04`
+---
+
+---
+# Z-image image generation (image washing workflow) (Version: v1.0)
+**Creator**: [AIGC_Singularity](https://civitai.com/user/AIGC_Singularity)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-28
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2173996
+**Civitai Version ID**: 2448164
+**Stats (at time of fetch for this version)**:
+*   Downloads: 66
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+You can click on the link below to try it out directly. If the effect is good, you can deploy it locally
+https://www.runninghub.ai/post/1994322368636059649/?inviteCode=sdhs0trb
+Fan benefits,register to get 1000 points,daily login 100 points,play 4090!  Experience the super power of 48G.
+This is Qwen's latest Wenshengtu model workflow focused on portrait generation, which can generate realistic portraits far superior to Flux2. To use the workflow, the following models need to be downloaded:
+1.z_image_turbo_bf16
+2.qwen_3_4b
+3.diffusion_pytorch_model
+4.qinglong_detailedeye_z-image
+Cloud storage download:
+https://pan.quark.cn/s/fa65cc7a125d
+Download link:
+https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files
+Lora：
+huggingface.co
+/ bdsqlsz/qinglong_DetailedEyes_Z-Image · Hugging Face
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2173996?modelVersionId=2448164)**
+*   [View Full Model Page →](https://civitai.com/models/2173996)
+*   [View Creator Profile →](https://civitai.com/user/AIGC_Singularity)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageImageGeneration_v10.zip`
+*   **Size**: 0.01 MB
+*   **Hash (AutoV2)**: `E394513377`
+*   **Hash (SHA256)**: `E394513377F282F60CAB16797B70716475105BB2CA9A0E93349706930CA6F78F`
+---
+
+---
+# Z-image turbo workflow | CivitAI metadata, upscaling, FaceDetailer (+indexing elements), inpainting ComfyUI beginner friendly (Version: v1)
+**Creator**: [blinkdotleh](https://civitai.com/user/blinkdotleh)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-29
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2176468
+**Civitai Version ID**: 2450937
+**Stats (at time of fetch for this version)**:
+*   Downloads: 176
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+It has a ControlNet as well, so when someone trains that it's just a plug and play.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2176468?modelVersionId=2450937)**
+*   [View Full Model Page →](https://civitai.com/models/2176468)
+*   [View Creator Profile →](https://civitai.com/user/blinkdotleh)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTurboWorkflowCivitaiMetadata_v1.zip`
+*   **Size**: 0.01 MB
+*   **Hash (AutoV2)**: `E81BE10E29`
+*   **Hash (SHA256)**: `E81BE10E29A1A0727DFF32078431B9ADE985A6EE858DC654E43345C8893E81CD`
+---
+
+---
+# Z-image-hires Workflow (Version: v1.0)
+**Creator**: [oosayam](https://civitai.com/user/oosayam)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-29
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2175863
+**Civitai Version ID**: 2450271
+**Stats (at time of fetch for this version)**:
+*   Downloads: 376
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+🚀 Z-Image Turbo FP8 Hires Workflow (Low VRAM Optimized)
+This is a high-efficiency ComfyUI workflow designed specifically for
+Low VRAM
+users. By utilizing
+FP8 Quantized Models
+and
+Latent Upscale
+technology, it generates high-resolution images (1024x1792) rapidly while maintaining minimal resource usage.
+✨ Key Features
+Extreme Low VRAM Usage
+: Full FP8 pipeline (Model & Text Encoder) to drastically reduce memory footprint.
+Lightning Fast
+: Optimized for Turbo models and efficient sampling steps.
+Hires Fix Pipeline
+: Utilizes
+Latent Upscale
++
+2nd Pass KSampler
+to ensure crisp details without heavy VRAM cost.
+AuraFlow Architecture
+: Optimized using the
+ModelSamplingAuraFlow
+node.
+📂 Models Required & Downloads
+To ensure the workflow functions correctly, please download the following models and place them in your respective ComfyUI folders:
+1. UNet Model (Place in
+models/unet/
+)
+File Name
+:
+z-image-turbo-fp8-e4m3fn.safetensors
+Download
+:
+HuggingFace - Z-Image-Turbo-FP8
+2. CLIP / Text Encoder (Place in
+models/clip/
+)
+File Name
+:
+qwen3-4b-fp8-scaled.safetensors
+Download
+:
+HuggingFace - Qwen3-4B-FP8
+⚙️ Key Settings & Configuration
+This workflow operates on a 2-Pass system. Please adhere to the following settings for the best results:
+🔹 Phase 1: Base Generation
+Latent Size
+: Generates at a lower initial resolution (e.g., 512x896) to save compute resources.
+🔹 Phase 2: Latent Upscale
+Upscale Method
+: Uses
+LatentUpscaleBy
+.
+Scale Factor
+: Default is
+2
+(resulting in a final output of 1024x1792).
+🔹 Phase 3: Hires Fix (Refiner)
+This step is crucial for image clarity and detail:
+Sampler
+:
+res_multistep
+(Highly Recommended).
+Denoise
+: Recommended range
+0.5 - 0.6
+.
+< 0.5
+: Changes are minimal; the image may remain slightly blurry.
+> 0.6
+: Adds more detail, but setting this too high may alter the image structure or cause hallucinations.
+📊 Performance Benchmark
+Data based on actual testing:
+GPUOutput ResolutionTime
+NVIDIA RTX 5070 Ti1024 x 17928 ~ 9 sec
+📝 Usage Tips
+Memory Management
+: If you are extremely limited on VRAM, ensure no other large models are loaded in the background.
+Prompting
+: Since this uses the Qwen text encoder, it has strong natural language understanding. Detailed, sentence-based prompts work very well.
+Troubleshooting
+: If you notice the image details breaking or looking "burnt," try slightly lowering the
+denoise
+value in the second KSampler.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2175863?modelVersionId=2450271)**
+*   [View Full Model Page →](https://civitai.com/models/2175863)
+*   [View Creator Profile →](https://civitai.com/user/oosayam)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageHiresWorkflow_v10.zip`
+*   **Size**: 0.00 MB
+*   **Hash (AutoV2)**: `E26DF5CCE4`
+*   **Hash (SHA256)**: `E26DF5CCE44C682340C1339552D19349A053CEB034C034909FF0AF1A9A4CE2E1`
 ---

civitai_tracker.json

@@ -577,6 +577,36 @@
       "versions": [
         "2449361"
       ]
+    },
+    "2174008": {
+      "name": "Z-Image-Turbo-AIO-Workflow",
+      "versions": [
+        "2448186"
+      ]
+    },
+    "2173992": {
+      "name": "Z-image Creation -Text To image (the strongest realistic portrait)",
+      "versions": [
+        "2448156"
+      ]
+    },
+    "2173996": {
+      "name": "Z-image image generation (image washing workflow)",
+      "versions": [
+        "2448164"
+      ]
+    },
+    "2176468": {
+      "name": "Z-image turbo workflow | CivitAI metadata, upscaling, FaceDetailer (+indexing elements), inpainting ComfyUI beginner friendly",
+      "versions": [
+        "2450937"
+      ]
+    },
+    "2175863": {
+      "name": "Z-image-hires Workflow",
+      "versions": [
+        "2450271"
+      ]
     }
   },
   "versions": [
@@ -697,6 +727,11 @@
     "2445949",
     "2447054",
     "2448762",
-    "2449361"
+    "2449361",
+    "2448186",
+    "2448156",
+    "2448164",
+    "2450937",
+    "2450271"
   ]
 }