Sync 5 new model versions from Civitai (Batch 13/21)

Z-Image_T2I_Compact/ZImageTurbo/zImageT2ICompact_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f03843842c4aea42e732a2b741df2b7793f296daccb63e6a2d25dd885599e9
+size 141219

Z-Image_Text-to-Image_High-Definition_Workflow_No_Magnification/ZImageTurbo/zImageTextToImageHigh_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9985b7ec413a111de1b91fe1d7d35664f44aa46bb9c32790a642441b759842ef
+size 7270

Z-Image_Turbo_-_T2I_Workflow__Detailer__Upscaler__Color_Grading/ZImageTurbo/zImageTurboT2IWorkflow_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e265083616cb17413e515886ce0eac4bdc259c51236f9d865e55efe7238be004
+size 3148599

Z-Image_Turbo_-_T2I_Workflow__Detailer__Upscaler__Color_Grading/ZImageTurbo/zImageTurboT2IWorkflow_v30.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a454088d35b7f96d99d28cbf31fb47d51c0740cc96fcd51a1673d1fbd2f3bbec
+size 4291604

Z-Image_Turbo__Ultimate_SD_Upscale__Face_Detailer_Workflow/ZImageTurbo/zImageTurboUltimateSD_v10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e59b7a1cf2b4beec8768c78b0f487f87ac59702c7dcf571c8e439222448123
+size 6752

ZImageTurbo_info.md

@@ -3200,4 +3200,463 @@ This tutorial is absolutely essential—skipping it will inevitably cause numero
 *   **Size**: 0.00 MB
 *   **Hash (AutoV2)**: `2F8324FFA7`
 *   **Hash (SHA256)**: `2F8324FFA78FA55ECD294519CCF700B64FC48BAF7147C2B966C0767471643AB4`
+---
+
+---
+# Z-Image T2I Compact (Version: v1.0)
+**Creator**: [plk](https://civitai.com/user/plk)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-30
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2181602
+**Civitai Version ID**: 2456549
+**Stats (at time of fetch for this version)**:
+*   Downloads: 25
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+A compact basic workflow for Z-Image Turbo.
+_________
+Tested best Sampler / Scheduler combinations:
+ResMultiStep - SGM Uniform (smoother skin), Beta (more detailed)
+Euler - SGM Uniform, Normal (very good), KL Optimal, Beta, Bong Tangent
+LCM - Beta, Bong Tangent
+UniPC - KL Optimal, DDIM
+Heun - Linear Quadratic, Beta
+DPM2 - DDIM, Bong Tangent
+DPM++ 2M - Linear Quadratic, Beta (better)
+DPM++ 2s - Karras (very good), Normal, Linear Quadratic, KL Optimal, Beta, Bong Tangent (very good)
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2181602?modelVersionId=2456549)**
+*   [View Full Model Page →](https://civitai.com/models/2181602)
+*   [View Creator Profile →](https://civitai.com/user/plk)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageT2ICompact_v10.zip`
+*   **Size**: 0.13 MB
+*   **Hash (AutoV2)**: `C6F0384384`
+*   **Hash (SHA256)**: `C6F03843842C4AEA42E732A2B741DF2B7793F296DACCB63E6A2D25DD885599E9`
+---
+
+---
+# Z-Image Text-to-Image High-Definition Workflow (No Magnification) (Version: v1.0)
+**Creator**: [shadowsii](https://civitai.com/user/shadowsii)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-05
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2197289
+**Civitai Version ID**: 2474056
+**Stats (at time of fetch for this version)**:
+*   Downloads: 52
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+You can click the link below to run this workflow in the cloud, or download it to run locally,
+Click the link below to register and instantly receive 1000 points. Enjoy the 4090 graphics card and get 48GB of VRAM as a bonus!
+https://www.runninghub.cn/post/1996889371469049858/?inviteCode=rh-v1041
+The workflow is extremely simple to operate. I've uploaded a tutorial on YouTube demonstrating its use. You can try it yourself and easily replicate the results by following the tutorial and Civitai's workflow. Thank you for your attention. If you have any further questions, please leave a comment below.
+This tutorial is absolutely essential—skipping it will inevitably cause numerous problems! You MUST watch the video tutorial before proceeding!!!! This is critically important! Especially the key points at the end!
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2197289?modelVersionId=2474056)**
+*   [View Full Model Page →](https://civitai.com/models/2197289)
+*   [View Creator Profile →](https://civitai.com/user/shadowsii)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTextToImageHigh_v10.zip`
+*   **Size**: 0.01 MB
+*   **Hash (AutoV2)**: `9985B7EC41`
+*   **Hash (SHA256)**: `9985B7EC413A111DE1B91FE1D7D35664F44AA46BB9C32790A642441B759842EF`
+---
+
+---
+# Z-Image Turbo + Ultimate SD Upscale + Face Detailer Workflow (Version: v1.0)
+**Creator**: [ChillDesire](https://civitai.com/user/ChillDesire)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-04
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2192228
+**Civitai Version ID**: 2468386
+**Stats (at time of fetch for this version)**:
+*   Downloads: 153
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+Z-Image workflow with Ultimate SD Upscale and FaceDetailer.
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2192228?modelVersionId=2468386)**
+*   [View Full Model Page →](https://civitai.com/models/2192228)
+*   [View Creator Profile →](https://civitai.com/user/ChillDesire)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTurboUltimateSD_v10.zip`
+*   **Size**: 0.01 MB
+*   **Hash (AutoV2)**: `E3E59B7A1C`
+*   **Hash (SHA256)**: `E3E59B7A1CF2B4BEEC8768C78B0F487F87AC59702C7DCF571C8E439222448123`
+---
+
+---
+# Z-Image Turbo - T2I Workflow + Detailer + Upscaler + Color Grading (Version: v3.0)
+**Creator**: [MrSmith2025](https://civitai.com/user/MrSmith2025)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-12-04
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2174733
+**Civitai Version ID**: 2468562
+**Stats (at time of fetch for this version)**:
+*   Downloads: 332
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+⚡
+Z-Image Turbo Workflow
+⚡
+Compact TXT-2-IMG WF + Detailer + Upscaler + Lora Loader & Color Grading
+Z-Image Turbo is a fast, distilled, powerful and highly efficient image generation model with
+6B
+parameters. The strength of this model lies in its ability to generate photorealistic images. But even though the model follows prompts very well, the output still isn’t premium in terms of quality. We still need an upscaling process here to make the images presentable. This is where this workflow comes in, including the ADetailer and Ultimate SD Upscaler.
+🚀
+What do you need to get started right away?
+This Workflow - just
+download
+it, unzip the file and load the *.json into ComfyUI
+Z-Image Model:
+z_image_turbo_bf16.safetensors
+(place in
+\models\diffusion_models\
+)
+Text encoder file:
+qwen_3_4b.safetensors
+(place in
+\models\text_encoders\
+)
+The VAE file:
+ae.safetensors
+(place in
+\models\vae\
+)
+Face Detector:
+face_yolov8m.pt
+(place in
+\models\ultralytics\bbox\
+)
+Eyes Detector:
+Eyeful_v2-Paired.pt
+(place in
+\models\ultralytics\bbox\
+)
+Various
+upscale models
+of your choice (place in
+\models\upscale_models\
+)
+Regarding the upscale model I recommend
+4x_NMKD-Siax_200k.pth
+or
+4x_UltraSharp.pth
+. These deliver the best results. But feel free to try out different upscale models. You can find a good selection
+here
+.
+If you used FLUX before then you already have the ae.safetensors file and dont need to download it again.
+You can also use the
+fp8 checkpoint
+if you run a gpu with 8gb of vram. I see no reason to use GGUF models here as the BF16 and FP8 models are already small enough for every kind of GPU.
+🚨
+Make sure that you use the latest stable ComfyUI Core version. Also don't forget to update the ComfyUI Frontend package and your Custom Nodes. Otherwise compatibility problems may occur and the workflow is not working properly.
+The v3 version was made with the following versions:
+ComfyUI Core v0.3.75
+ComfyUI Frontend v1.34.2
+ComfyUI Manager v3.37.2
+Python Version 3.12.10
+PyTorch Version 2.8.0+cu128
+All latest versions of the custom nodes listed below
+Please ensure that you are also using at least these versions. Otherwise, I cannot provide support if something is not working for you.
+❓
+Do I need some special nodes to run this workflow?
+The nodes inside the workflow are common nodes that should or could be already installed on your ComfyUI. If ComfyUI still indicates a missing node just install it via ComfyUI Manager and restart briefly.
+Custom nodes used in this workflow:
+rgthree-comfy
+ComfyUI-Impact-Pack
+ComfyUI-Easy-Use
+ComfyUI_UltimateSDUpscale
+ComfyUI-Art-Venture
+ComfyUI-Impact-Subpack
+ControlAltAI_Nodes
+Save Image with Generation Metadata
+VRGameDevGirl Video Enhancement Nodes
+🛠️
+Why the Text Encoder (Positive Prompt) is connected to negative and positive on the KSampler Node?
+If the CFG value is set to 1.0 the negative prompt is ignored. This is one of the reasons why the model is so fast. This is intentional and not a mistake. Other workflows are ignoring this fact and offer a negative input node. But you dont need a negative prompt here. Simply enter your positive prompt and you're good to go!
+💡
+Usage Tips:
+Simply set the desired resolution on the left, select your preferred upscaler on the far right, put in your prompt and start generating.
+For prompting, it's recommended to use natural language in complete sentences. Describe the person or people, the setting, the camera angle, and the lighting. The more detailed you are, the more accurate the result. 100-300 words works best.
+If you only want to generate raw images for testing purposes, simply toggle off the upscaling and detailer groups using the first node on the top-left. This is also recommended for color grading. Don't forget to fix the seed for that.
+Feel free to experiment with the denoise values ​​in the detailer und upscale nodes to get the perfect result. Also try out different upscale models.
+You don't need to go higher than 9 steps with this model. It is a 8 Steps Model. It will not generate better images if you go higher. Just leave it on 8 or max 9 steps.
+I like to have the option to directly select the aspect ratio (e.g. 5:7 or 9:16) in the node. If you prefer to enter the resolution manually simply disconnect or delete the "Base Resolution Node". Afterwards you can enter your desired resolution in the "latent image" node.
+✅
+v2 Changelog:
+In comparison to my other results with SDXL I wasn't entirely satisfied. Therefore, I revised and optimized the v1 workflow. I have made the following changes to v2:
+✨
+Added Toggle On/Off Node for Upscaling Group
+Toggling the entire upscaler group just to generate RAW images was cumbersome. Now, a single on/off switch at the start lets you enable or disable the upscaler with just one click – quick and easy.
+✨
+Added Lora Loader Node
+With more Lora's being released for Z-Image Turbo these days, this node lets you load and configure multiple Loras at once. Making experimentation faster and easier.
+✨
+Added Clear VRAM and Clear Cache Node
+Placed between the Base Image Generation and Upscaler sections, these nodes improve memory management. Especially on GPUs with limited VRAM and slightly speed up the workflow.
+✨
+Added Seed Generator Node
+The new Seed Generator node is connected to the KSampler and also to the Upscaler node. This means that the Upscaler receives the same seed. I feel this leads to better results.
+✨
+Added fast sharpen / unsharpen node
+This node allows you to adjust the sharpness slightly after upscaling. Feel free to experiment with the
+strength
+value. However, I suggest leaving it at 0.50.
+✨
+Added fast film grain node
+This node adds film grain after upscaling. This provides a professional finish and a cinematic look. The
+grain_intensity
+value can be increased up to 0.050. I find less is more here and therefore have it set to 0.010.
+✨
+Adjusted some parameters for better performance
+I adjusted some parameters, mainly affecting the Image Upscale node. I found that 20 steps unnecessarily slowed down the upscaling process and resulted in a poorer outcome, especially regarding skin texture. Eight steps proved to be the perfect value. This reduced the overall workflow time to 30% while simultaneously improving the quality.
+🛠️
+All the changes combined now result in a much faster workflow and very decent images compared to v1.
+🆕
+v3 Changelog:
+The results with version 2 of the workflow are already quite good. But there's always room for improvement. So I've made some further adjustments that will help you get better images. What's changed?
+✨
+Added Color Grading Node
+Since the release of the Z-Image model, generating thousands of images showed that it struggles with following light and color grading prompts. Images often look overbrighten and like they were taken with a high-end smartphone, making it hard to achieve a cinematic look. To fix this, a color grading node has been added to the first block (next to the LoRa loader). Here, you can adjust temperature, brightness, contrast, saturation, and gamma to get truly impressive results. For best results, set the seed in the "Seed Generator" node to "fixed," disable the detailer and upscaler, and experiment a bit. This lets you achieve a cinematic look immediately - no LoRa needed.
+✨
+Added Adetailer Group for Image Improvement
+To complement the upscaling process, a dedicated face and eye detailer section has been added. Bare feet and hands already render well in 99% of cases with Z-Image, so no detailer is needed for them. Adding one would only slow down the workflow unnecessarily. To keep the overall workflow compact despite the new nodes, the relevant parts have been moved into subgraphs. You still have full control over key parameters such as steps, CFG, and denoise for both detailers. Too small changes indicate a denoise value that’s too low, while issues with eyes or other image artifacts mean the denoise value is too high. Feel free to experiment with the denoise to get the best results.
+Make sure that you have downloaded the 2 needed files for the detailer:
+Face Detector:
+face_yolov8m.pt
+(place in \models\ultralytics\bbox)
+Eyes Detector:
+Eyeful_v2-Paired.pt
+(place in \models\ultralytics\bbox)
+Without these files the workflow will just stop at the detailer group!
+✨
+Added Adetailer Group to the Toggle On / Off Node
+The new detailer section has been integrated into the Toggle On/Off node at the start of the workflow. This allows you to enable or disable it with a single click. It’s especially useful when generating RAW images, testing color grading, or looking for a good seed without applying additional detail enhancements.
+✨
+Added Calculated Resolution Node
+To make it easy to see which base resolution is being used, I've added a node that displays this information. It's the result of the selected resolution in megapixels and the aspect ratio. You can see this "Calculated Resolution" node between the "Base Resolution" and "Latent Image" nodes on the left.
+✨
+Added Model Sampling Aura Flow Node
+In other Z-Image workflows, you'll see the "Model Sampling Aura Flow" node, but it is usually muted. Since I didn’t find it useful for generating more variations from the same prompt, I removed it in versions 1 and 2 of the workflow. I’ve now added it back so you can test it yourself. This doesn’t affect runtime, and of course, the node can still be muted if desired.
+✨
+Adjusted some parameters
+I’ve tweaked a few settings again to achieve the best possible results. First, I increased the base resolution from 1.2MP to 2.0MP. This alone slightly improves image quality, as there are more pixels in the RAW image. If you have a powerful GPU, you can raise this value to 2.2MP or even 2.5MP. Additionally, I increased the sharpen strength from 0.50 to 0.55 and adjusted the film grain intensity from 0.010 to 0.015, which seems to be the sweet spot. Of course, feel free to experiment yourself.
+🛠️
+The download includes two versions: a full version with all updates, including the Detailer section, and a Lite version without the Detailer Group but with all other changes and color grading. Enjoy!
+If you have a question or comment about the workflow feel free to leave a post in the comment section. If something isn't working, please specify exactly what isn't working. Please also include the message displayed in the terminal window.
+Have fun and feel free to post your generated images in the gallery below! I would like to see what you do with this workflow!
+👍
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2174733?modelVersionId=2468562)**
+*   [View Full Model Page →](https://civitai.com/models/2174733)
+*   [View Creator Profile →](https://civitai.com/user/MrSmith2025)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTurboT2IWorkflow_v30.zip`
+*   **Size**: 4.09 MB
+*   **Hash (AutoV2)**: `A454088D35`
+*   **Hash (SHA256)**: `A454088D35B7F96D99D28CBF31FB47D51C0740CC96FCD51A1673D1FBD2F3BBEC`
+---
+
+---
+# Z-Image Turbo - T2I Workflow + Detailer + Upscaler + Color Grading (Version: v1.0)
+**Creator**: [MrSmith2025](https://civitai.com/user/MrSmith2025)
+**Type**: Workflows
+**Base Model**: ZImageTurbo
+**Version Uploaded**: 2025-11-29
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 2174733
+**Civitai Version ID**: 2449002
+**Stats (at time of fetch for this version)**:
+*   Downloads: 139
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## Description (Parent Model)
+⚡
+Z-Image Turbo Workflow
+⚡
+Compact TXT-2-IMG WF + Detailer + Upscaler + Lora Loader & Color Grading
+Z-Image Turbo is a fast, distilled, powerful and highly efficient image generation model with
+6B
+parameters. The strength of this model lies in its ability to generate photorealistic images. But even though the model follows prompts very well, the output still isn’t premium in terms of quality. We still need an upscaling process here to make the images presentable. This is where this workflow comes in, including the ADetailer and Ultimate SD Upscaler.
+🚀
+What do you need to get started right away?
+This Workflow - just
+download
+it, unzip the file and load the *.json into ComfyUI
+Z-Image Model:
+z_image_turbo_bf16.safetensors
+(place in
+\models\diffusion_models\
+)
+Text encoder file:
+qwen_3_4b.safetensors
+(place in
+\models\text_encoders\
+)
+The VAE file:
+ae.safetensors
+(place in
+\models\vae\
+)
+Face Detector:
+face_yolov8m.pt
+(place in
+\models\ultralytics\bbox\
+)
+Eyes Detector:
+Eyeful_v2-Paired.pt
+(place in
+\models\ultralytics\bbox\
+)
+Various
+upscale models
+of your choice (place in
+\models\upscale_models\
+)
+Regarding the upscale model I recommend
+4x_NMKD-Siax_200k.pth
+or
+4x_UltraSharp.pth
+. These deliver the best results. But feel free to try out different upscale models. You can find a good selection
+here
+.
+If you used FLUX before then you already have the ae.safetensors file and dont need to download it again.
+You can also use the
+fp8 checkpoint
+if you run a gpu with 8gb of vram. I see no reason to use GGUF models here as the BF16 and FP8 models are already small enough for every kind of GPU.
+🚨
+Make sure that you use the latest stable ComfyUI Core version. Also don't forget to update the ComfyUI Frontend package and your Custom Nodes. Otherwise compatibility problems may occur and the workflow is not working properly.
+The v3 version was made with the following versions:
+ComfyUI Core v0.3.75
+ComfyUI Frontend v1.34.2
+ComfyUI Manager v3.37.2
+Python Version 3.12.10
+PyTorch Version 2.8.0+cu128
+All latest versions of the custom nodes listed below
+Please ensure that you are also using at least these versions. Otherwise, I cannot provide support if something is not working for you.
+❓
+Do I need some special nodes to run this workflow?
+The nodes inside the workflow are common nodes that should or could be already installed on your ComfyUI. If ComfyUI still indicates a missing node just install it via ComfyUI Manager and restart briefly.
+Custom nodes used in this workflow:
+rgthree-comfy
+ComfyUI-Impact-Pack
+ComfyUI-Easy-Use
+ComfyUI_UltimateSDUpscale
+ComfyUI-Art-Venture
+ComfyUI-Impact-Subpack
+ControlAltAI_Nodes
+Save Image with Generation Metadata
+VRGameDevGirl Video Enhancement Nodes
+🛠️
+Why the Text Encoder (Positive Prompt) is connected to negative and positive on the KSampler Node?
+If the CFG value is set to 1.0 the negative prompt is ignored. This is one of the reasons why the model is so fast. This is intentional and not a mistake. Other workflows are ignoring this fact and offer a negative input node. But you dont need a negative prompt here. Simply enter your positive prompt and you're good to go!
+💡
+Usage Tips:
+Simply set the desired resolution on the left, select your preferred upscaler on the far right, put in your prompt and start generating.
+For prompting, it's recommended to use natural language in complete sentences. Describe the person or people, the setting, the camera angle, and the lighting. The more detailed you are, the more accurate the result. 100-300 words works best.
+If you only want to generate raw images for testing purposes, simply toggle off the upscaling and detailer groups using the first node on the top-left. This is also recommended for color grading. Don't forget to fix the seed for that.
+Feel free to experiment with the denoise values ​​in the detailer und upscale nodes to get the perfect result. Also try out different upscale models.
+You don't need to go higher than 9 steps with this model. It is a 8 Steps Model. It will not generate better images if you go higher. Just leave it on 8 or max 9 steps.
+I like to have the option to directly select the aspect ratio (e.g. 5:7 or 9:16) in the node. If you prefer to enter the resolution manually simply disconnect or delete the "Base Resolution Node". Afterwards you can enter your desired resolution in the "latent image" node.
+✅
+v2 Changelog:
+In comparison to my other results with SDXL I wasn't entirely satisfied. Therefore, I revised and optimized the v1 workflow. I have made the following changes to v2:
+✨
+Added Toggle On/Off Node for Upscaling Group
+Toggling the entire upscaler group just to generate RAW images was cumbersome. Now, a single on/off switch at the start lets you enable or disable the upscaler with just one click – quick and easy.
+✨
+Added Lora Loader Node
+With more Lora's being released for Z-Image Turbo these days, this node lets you load and configure multiple Loras at once. Making experimentation faster and easier.
+✨
+Added Clear VRAM and Clear Cache Node
+Placed between the Base Image Generation and Upscaler sections, these nodes improve memory management. Especially on GPUs with limited VRAM and slightly speed up the workflow.
+✨
+Added Seed Generator Node
+The new Seed Generator node is connected to the KSampler and also to the Upscaler node. This means that the Upscaler receives the same seed. I feel this leads to better results.
+✨
+Added fast sharpen / unsharpen node
+This node allows you to adjust the sharpness slightly after upscaling. Feel free to experiment with the
+strength
+value. However, I suggest leaving it at 0.50.
+✨
+Added fast film grain node
+This node adds film grain after upscaling. This provides a professional finish and a cinematic look. The
+grain_intensity
+value can be increased up to 0.050. I find less is more here and therefore have it set to 0.010.
+✨
+Adjusted some parameters for better performance
+I adjusted some parameters, mainly affecting the Image Upscale node. I found that 20 steps unnecessarily slowed down the upscaling process and resulted in a poorer outcome, especially regarding skin texture. Eight steps proved to be the perfect value. This reduced the overall workflow time to 30% while simultaneously improving the quality.
+🛠️
+All the changes combined now result in a much faster workflow and very decent images compared to v1.
+🆕
+v3 Changelog:
+The results with version 2 of the workflow are already quite good. But there's always room for improvement. So I've made some further adjustments that will help you get better images. What's changed?
+✨
+Added Color Grading Node
+Since the release of the Z-Image model, generating thousands of images showed that it struggles with following light and color grading prompts. Images often look overbrighten and like they were taken with a high-end smartphone, making it hard to achieve a cinematic look. To fix this, a color grading node has been added to the first block (next to the LoRa loader). Here, you can adjust temperature, brightness, contrast, saturation, and gamma to get truly impressive results. For best results, set the seed in the "Seed Generator" node to "fixed," disable the detailer and upscaler, and experiment a bit. This lets you achieve a cinematic look immediately - no LoRa needed.
+✨
+Added Adetailer Group for Image Improvement
+To complement the upscaling process, a dedicated face and eye detailer section has been added. Bare feet and hands already render well in 99% of cases with Z-Image, so no detailer is needed for them. Adding one would only slow down the workflow unnecessarily. To keep the overall workflow compact despite the new nodes, the relevant parts have been moved into subgraphs. You still have full control over key parameters such as steps, CFG, and denoise for both detailers. Too small changes indicate a denoise value that’s too low, while issues with eyes or other image artifacts mean the denoise value is too high. Feel free to experiment with the denoise to get the best results.
+Make sure that you have downloaded the 2 needed files for the detailer:
+Face Detector:
+face_yolov8m.pt
+(place in \models\ultralytics\bbox)
+Eyes Detector:
+Eyeful_v2-Paired.pt
+(place in \models\ultralytics\bbox)
+Without these files the workflow will just stop at the detailer group!
+✨
+Added Adetailer Group to the Toggle On / Off Node
+The new detailer section has been integrated into the Toggle On/Off node at the start of the workflow. This allows you to enable or disable it with a single click. It’s especially useful when generating RAW images, testing color grading, or looking for a good seed without applying additional detail enhancements.
+✨
+Added Calculated Resolution Node
+To make it easy to see which base resolution is being used, I've added a node that displays this information. It's the result of the selected resolution in megapixels and the aspect ratio. You can see this "Calculated Resolution" node between the "Base Resolution" and "Latent Image" nodes on the left.
+✨
+Added Model Sampling Aura Flow Node
+In other Z-Image workflows, you'll see the "Model Sampling Aura Flow" node, but it is usually muted. Since I didn’t find it useful for generating more variations from the same prompt, I removed it in versions 1 and 2 of the workflow. I’ve now added it back so you can test it yourself. This doesn’t affect runtime, and of course, the node can still be muted if desired.
+✨
+Adjusted some parameters
+I’ve tweaked a few settings again to achieve the best possible results. First, I increased the base resolution from 1.2MP to 2.0MP. This alone slightly improves image quality, as there are more pixels in the RAW image. If you have a powerful GPU, you can raise this value to 2.2MP or even 2.5MP. Additionally, I increased the sharpen strength from 0.50 to 0.55 and adjusted the film grain intensity from 0.010 to 0.015, which seems to be the sweet spot. Of course, feel free to experiment yourself.
+🛠️
+The download includes two versions: a full version with all updates, including the Detailer section, and a Lite version without the Detailer Group but with all other changes and color grading. Enjoy!
+If you have a question or comment about the workflow feel free to leave a post in the comment section. If something isn't working, please specify exactly what isn't working. Please also include the message displayed in the terminal window.
+Have fun and feel free to post your generated images in the gallery below! I would like to see what you do with this workflow!
+👍
+## Civitai Links
+*   **[View This Version on Civitai →](https://civitai.com/models/2174733?modelVersionId=2449002)**
+*   [View Full Model Page →](https://civitai.com/models/2174733)
+*   [View Creator Profile →](https://civitai.com/user/MrSmith2025)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `zImageTurboT2IWorkflow_v10.zip`
+*   **Size**: 3.00 MB
+*   **Hash (AutoV2)**: `E265083616`
+*   **Hash (SHA256)**: `E265083616CB17413E515886CE0EAC4BDC259C51236F9D865E55EFE7238BE004`
 ---

civitai_tracker.json

@@ -294,6 +294,31 @@
       "versions": [
         "2474075"
       ]
+    },
+    "2181602": {
+      "name": "Z-Image T2I Compact",
+      "versions": [
+        "2456549"
+      ]
+    },
+    "2197289": {
+      "name": "Z-Image Text-to-Image High-Definition Workflow (No Magnification)",
+      "versions": [
+        "2474056"
+      ]
+    },
+    "2192228": {
+      "name": "Z-Image Turbo + Ultimate SD Upscale + Face Detailer Workflow",
+      "versions": [
+        "2468386"
+      ]
+    },
+    "2174733": {
+      "name": "Z-Image Turbo - T2I Workflow + Detailer + Upscaler + Color Grading",
+      "versions": [
+        "2468562",
+        "2449002"
+      ]
     }
   },
   "versions": [
@@ -356,6 +381,11 @@
     "2463494",
     "2467420",
     "2473381",
-    "2474075"
+    "2474075",
+    "2456549",
+    "2474056",
+    "2468386",
+    "2468562",
+    "2449002"
   ]
 }