Sync 5 new model versions from Civitai (Batch 7/21)

Pixeldust_Z_turbo_refinery/ZImageTurbo/pixeldustZTurbo_alpha.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e65e01d41074ccee631d5e08837e8d512f43a79148e7b39e5bc1959cc86a36
+size 5641

Pixeldust_creative_chaos_workflow_for_ZIT/ZImageTurbo/pixeldustCreativeChaos_alpha.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3929bddfaa36cdc777d755f6fb14bf98047648339bf3aefc7998668d98c5e0d8
+size 16294

Pixeldust_creative_chaos_workflow_for_ZIT/ZImageTurbo/pixeldustCreativeChaos_beta.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8e37fe6fedffa299e217b6a13eb87f6514b92ddb814fdba5481eddba36c944
+size 26649

SeedVarianceEnhancer_optimized_for_Z-Image_Turbo/ZImageTurbo/seedvarianceenhancer_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40ad145d9a440e3541e3314606c3f4eab6a08c268322e46cb58890bd120619a
+size 4152

Simple_4in1_Prompt_Modes_For_ZImageTurbo_Workflow/ZImageTurbo/simple4in1PromptModes_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470515b5f67fc0b809ffff006c0d6de46d07b60d574ce3cb18b71df6d6d25ac4
+size 1314427

ZImageTurbo_info.md

@@ -1655,4 +1655,207 @@ A note: it looks like the model likes big prompts and can handle a lot of input.
 *   **Size**: 0.01 MB
 *   **Hash (AutoV2)**: `1A9406D1D8`
 *   **Hash (SHA256)**: `1A9406D1D8E09BD69DDBD13410ABEFF9347B2BE9F65DD31C9E22AEADF2360A0A`
+---
+
+---
+# Pixeldust Z turbo refinery (Version: alpha)
+**Creator**: [Stardeaf](https://civitai.com/user/Stardeaf)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-30
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2177724
+**Civitai Version ID**: 2452303
+**Stats (at time of fetch for this version)**:
+*   Downloads: 67
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+It's a ComfyUI workflow.
+This is my attempt at porting the SD 1.5 old idea to Z-image turbo. The idea is to use a model as a refiner, take image, add a bit of noise, diffuse and repeat a couple of times. It's a kind of gradual refinement... This way you can change overall image style while keeping the subject and composition somewhat intact. Like, for example, take your plasticky Illustrious render and make it a bit more real. Z-Image Turbo seems a perfect fit as it's fast and supports high resolution output.
+So far it's just an experiment. I'm not claiming it's successful, but looks promising to me.
+There are 6 instances of Ksampler in serial, with convenient on/off switches. rgthree nodes need to be installed. Mind the upscaler, bypass if not necessary.
+On sample images: input image is on the left, result on the right...
+A note: it looks like the model likes big prompts and can handle a lot of input. Use elaborated prompt to enforce desired style. You can use Qwen LLM to expand the prompts, it's good at it and also the TE for this model is based on it, so they should understand each other well. I guess. You can also use Qwen to create subject prompt from image, just feed it the input image and ask to make prompt out of it, then add a separate paragraph for the style.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2177724?modelVersionId=2452303)**
+*   [View Full Model Page →](https://civitai.com/models/2177724)
+*   [View Creator Profile →](https://civitai.com/user/Stardeaf)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `pixeldustZTurbo_alpha.zip`
+*   **Size**: 0.01 MB
+*   **Hash (AutoV2)**: `38E65E01D4`
+*   **Hash (SHA256)**: `38E65E01D41074CCEE631D5E08837E8D512F43A79148E7B39E5BC1959CC86A36`
+---
+
+---
+# Pixeldust creative chaos workflow for ZIT (Version: alpha)
+**Creator**: [Stardeaf](https://civitai.com/user/Stardeaf)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-02
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2188476
+**Civitai Version ID**: 2464131
+**Stats (at time of fetch for this version)**:
+*   Downloads: 75
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+This is ComfyUI experimental workflow.
+My impression is that Z-Image doesn't react to seed changes as much as earlier models. Side effect of having high adherence perhaps. For sake of experimentation, I'm looking to introduce a bit of chaos into generation process.
+If you experiment with CFG setting you may find out that lowering it below 0.5, result in pretty much random image - unrelated to prompt. What if we used a very low CFG but only for the first generation step?
+I made this workflow for easy adjustments of CFG, prompt and lora for each step of generation. So I could for example, apply a lora but skipping first two steps. Or use different prompt for given steps - start with one concept, establish image structure and then use it for something entirely different (which has similar effect as using low CFG). There's also preview for each generation step, so you can monitor what is happening where (if you do you may find that actually whole composition is set up in first step).
+Just an idea if you're keen to experiment. It requires rgthree nodes installed.
+BETA notes:
+I fixed steps 2-9 having randomized seed for no reason, as result it would always re-render from beginning, even if repeating last render. I also removed my (completely wrong) notes about CFG.
+It looks like CFG affects negative prompt the following way: at 1.0 negative prompt has no effect at all. More than 1.0 and it has impact, but at cost of increased generation time. Less than 1.0 and negative turns to positive with increased generation time again. At 0.0 CFG, negative acts as positive and positive is ignored. Interestingly, if you set CFG to 0.5 you get a blend of positive and negative prompt, as if both are treated as positive and results blend together. Something to abuse creatively.
+Also added latent transformation nodes which could be applied after step 1.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2188476?modelVersionId=2464131)**
+*   [View Full Model Page →](https://civitai.com/models/2188476)
+*   [View Creator Profile →](https://civitai.com/user/Stardeaf)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `pixeldustCreativeChaos_alpha.zip`
+*   **Size**: 0.02 MB
+*   **Hash (AutoV2)**: `3929BDDFAA`
+*   **Hash (SHA256)**: `3929BDDFAA36CDC777D755F6FB14BF98047648339BF3AEFC7998668D98C5E0D8`
+---
+
+---
+# Pixeldust creative chaos workflow for ZIT (Version: beta)
+**Creator**: [Stardeaf](https://civitai.com/user/Stardeaf)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-04
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2188476
+**Civitai Version ID**: 2468138
+**Stats (at time of fetch for this version)**:
+*   Downloads: 48
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+This is ComfyUI experimental workflow.
+My impression is that Z-Image doesn't react to seed changes as much as earlier models. Side effect of having high adherence perhaps. For sake of experimentation, I'm looking to introduce a bit of chaos into generation process.
+If you experiment with CFG setting you may find out that lowering it below 0.5, result in pretty much random image - unrelated to prompt. What if we used a very low CFG but only for the first generation step?
+I made this workflow for easy adjustments of CFG, prompt and lora for each step of generation. So I could for example, apply a lora but skipping first two steps. Or use different prompt for given steps - start with one concept, establish image structure and then use it for something entirely different (which has similar effect as using low CFG). There's also preview for each generation step, so you can monitor what is happening where (if you do you may find that actually whole composition is set up in first step).
+Just an idea if you're keen to experiment. It requires rgthree nodes installed.
+BETA notes:
+I fixed steps 2-9 having randomized seed for no reason, as result it would always re-render from beginning, even if repeating last render. I also removed my (completely wrong) notes about CFG.
+It looks like CFG affects negative prompt the following way: at 1.0 negative prompt has no effect at all. More than 1.0 and it has impact, but at cost of increased generation time. Less than 1.0 and negative turns to positive with increased generation time again. At 0.0 CFG, negative acts as positive and positive is ignored. Interestingly, if you set CFG to 0.5 you get a blend of positive and negative prompt, as if both are treated as positive and results blend together. Something to abuse creatively.
+Also added latent transformation nodes which could be applied after step 1.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2188476?modelVersionId=2468138)**
+*   [View Full Model Page →](https://civitai.com/models/2188476)
+*   [View Creator Profile →](https://civitai.com/user/Stardeaf)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `pixeldustCreativeChaos_beta.zip`
+*   **Size**: 0.03 MB
+*   **Hash (AutoV2)**: `5C8E37FE6F`
+*   **Hash (SHA256)**: `5C8E37FE6FEDFFA299E217B6A13EB87F6514B92DDB814FDBA5481EDDBA36C944`
+---
+
+---
+# SeedVarianceEnhancer (optimized for Z-Image Turbo) (Version: v1.0)
+**Creator**: [ChangeTheConstants](https://civitai.com/user/ChangeTheConstants)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-01
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2184867
+**Civitai Version ID**: 2460090
+**Stats (at time of fetch for this version)**:
+*   Downloads: 949
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+SeedVarianceEnhancer is a ComfyUI node that adds randomness to the text embedding, resulting in more diverse, and sometimes surprising image outputs. It is optimized for use with Z-Image Turbo.
+You can now find the project on GitHub:
+https://github.com/ChangeTheConstants/SeedVarianceEnhancer
+As impressed as I was with the release of Z-Image Turbo, I was frustrated by the low diversity of its outputs. So I created SeedVarianceEnhancer as a clever hack to add a bit of chaos into the generation process. It adds random noise to the text embedding, altering the model's understanding of the prompt. When used with the default settings, you should get much greater variety in outputs without having to manually change the prompt. If you want to have some fun, turn up the settings and you will get outputs you wouldn't even think to ask for. SeedVarianceEnhancer trades prompt adherence for diversity. Some outputs will be failures, but if you generate numerous outputs with different seeds, you may find you like many of them more than what you would have gotten without SeedVarianceEnhancer. If you have prompts you want to let run for multiple generations, and you want a low effort way to get a variety of outputs, you should try SeedVarianceEnhancer.
+Just place the SeedVarianceEnhancer node between the positive prompt and the sampler.
+The default settings should add noticeable diversity without too much compromise in prompt adherence. Errors in text rendering will probably be the most noticeable compromise. Strength settings in the range from 15 to 30 while leaving the other settings default is a good place to start experimenting. There are also a few other settings for tweaking. Randomize_percent controls how much of the embedding is altered by noise. By default, noise will only be used in the beginning steps of generation. The noise_insert setting also lets you choose to use the noisy embedding for the entire generation process or just the end. The steps_switchover_percent adjust the timing of the switch between noisy and original embeddings if noise_insert is not set to all steps.
+For those that are interested, more detailed technical information about usage, capabilities, and limitation are within the readme included in the zip file.
+SeedVarianceEnhancer will work for other models
+, but the optimal settings for those models may be very different. Chroma HD works with strength settings less the 1.
+Installation:
+Extract the contents of the zip file and place the SeedVarianceEnhancer directory in your ComfyUI/custom_nodes directory. Launch or restart ComfyUI. You will find the SeedVarianceEnhancer inside the conditioning node group.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2184867?modelVersionId=2460090)**
+*   [View Full Model Page →](https://civitai.com/models/2184867)
+*   [View Creator Profile →](https://civitai.com/user/ChangeTheConstants)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `seedvarianceenhancer_v10.zip`
+*   **Size**: 0.00 MB
+*   **Hash (AutoV2)**: `E40AD145D9`
+*   **Hash (SHA256)**: `E40AD145D9A440E3541E3314606C3F4EAB6A08C268322E46CB58890BD120619A`
+---
+
+---
+# Simple 4in1 Prompt Modes For ZImageTurbo Workflow (Version: v1.0)
+**Creator**: [torc007689](https://civitai.com/user/torc007689)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-05
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2196254
+**Civitai Version ID**: 2472905
+**Stats (at time of fetch for this version)**:
+*   Downloads: 143
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+This Workflow allows to get prompts from 4 different methods:
+From a generated image.
+Manually writing one.
+Auto Prompt generation using QwenVL: a) Giving QwenVL via an Image, b) Describing an idea to QwenVL via text.
+::IMPORTANT (Installation instructions for "SD Prompt Reader" node, DO NOT INSTALL IT USING COMFY MANAGER, I had an issue using manger but you can try, if failed then delete the "comfyui-prompt-reader-node" in customs node folder and follow these instructions. )::
+Open File Explorer and navigate to: ComfyUI\custom_nodes\
+Open Command Prompt in Custom Nodes: In the same custom_nodes folder window, click the address bar at the top. Type cmd and press Enter. A black terminal window will open.
+Run the Recursive Clone Command:
+Copy and paste the following command into the terminal and press Enter:
+git clone --recursive
+https://github.com/receyuki/comfyui-prompt-reader-node.git
+Why this works: The --recursive flag tells Git to automatically download the "submodule" (the missing folder) that the standard Manager install often skips.
+Install Requirements:
+Once the download finishes, run these commands one by one in the same terminal:
+cd comfyui-prompt-reader-node
+..\..\..\python_embeded\python.exe -m pip install -r requirements.txt
+Note: If you get a "path not found" error for python, try just: pip install -r requirements.txt
+Restart ComfyUI:
+Close the terminal and restart ComfyUI. The node should now load correctly without the import error.
+Verification: After restart, if you check the comfyui-prompt-reader-node folder, you should now see a subfolder named stable_diffusion_prompt_reader that is not empty (it contains python files). If it's there, the fix worked.
+HOW TO USE:
+Select an option from "Switch Prompt Modes"
+If selected "Picture Prompt": Click "Choose a file to upload" or Drag and drop a generated image onto the "SD Prompt Reader" node, it will load the prompts from the image and then click Run in ComfyUI to generate image based on that prompt.
+if selected "Manual Prompt": Click in the "Manual Prompt TextBox" node and write your Positive prompt in it, then click Run to generate your image based on this prompt.
+If selected "Auto Prompt": Then you have two options to instruct QwenVL to generate prompts for you, first choose an option from the "Switch Prompt Input" node to instruct QwenVL with an image or text instruction,
+a) if you enabled "Image", then click "choose file to upload" or drag and drop an image file into the "Load Image" node and then click Run, QwenVL will generate a prompt based on the image you gave and the instructions written in the "Instructions to QwenVL" node (which you can modify as you wish) and then an image will be generated based on this prompt.
+b) If you enabled "Text", then give a short description of what you want QwenVL to give an Prompt for, like say I want a prompt for a car, just mention 'Car' in that description box and hit Run, QwenVL will generate a prompt for a car and an image will be generated based on that prompt.
+For the Negative prompt write it in the "Negative Prompt" node.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2196254?modelVersionId=2472905)**
+*   [View Full Model Page →](https://civitai.com/models/2196254)
+*   [View Creator Profile →](https://civitai.com/user/torc007689)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `simple4in1PromptModes_v10.zip`
+*   **Size**: 1.25 MB
+*   **Hash (AutoV2)**: `470515B5F6`
+*   **Hash (SHA256)**: `470515B5F67FC0B809FFFF006C0D6DE46D07B60D574CE3CB18B71DF6D6D25AC4`
 ---

civitai_tracker.json

@@ -137,7 +137,27 @@
     "2177724": {
       "name": "Pixeldust Z turbo refinery",
       "versions": [
-        "2457134"
+        "2457134",
+        "2452303"
+      ]
+    },
+    "2188476": {
+      "name": "Pixeldust creative chaos workflow for ZIT",
+      "versions": [
+        "2464131",
+        "2468138"
+      ]
+    },
+    "2184867": {
+      "name": "SeedVarianceEnhancer (optimized for Z-Image Turbo)",
+      "versions": [
+        "2460090"
+      ]
+    },
+    "2196254": {
+      "name": "Simple 4in1 Prompt Modes For ZImageTurbo Workflow",
+      "versions": [
+        "2472905"
       ]
     }
   },
@@ -171,6 +191,11 @@
     "2465823",
     "2474060",
     "2466638",
-    "2457134"
+    "2457134",
+    "2452303",
+    "2464131",
+    "2468138",
+    "2460090",
+    "2472905"
   ]
 }