Realism......
I design the most professional workflows out there. I have better options, better samplers, better detailers, better prompt assist, better controlnet, and basiclly better everything, and I give them away for free. I'm not going to charge you $30 for a crappy workflow with a renamed Clownshark sampler, a horribly vibecoded detailer, and a bad Lut. I give you an almost infintite amount of adjustments and leave you notes on how to do it.
If here is a feature you want, I'll add it. If you have questions, I answer them. I also have several other realism workflows. Just don't waste your money.
All of the images I posted to V7 were zero LoRAs and basic settings. You can make any adjustment you want. I give you the tools to do it.
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules.
⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directions
也有中文说明
This is an advanced workflow. I encourage you to take the time to learn it. If you feel overwhelmed, you can start here:
https://civarchive.com/models/2348914/zimage-base-and-turbo-essentials-workflow
A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown
All in 1 workflow:
Controlnet
Checkpoint option for merged models
I2I
Prompt generation
Prompt enhancement
Lora Loader
Flowmatch Sampler (Rez4Lyf)
Draft mode for making corrections without having to rerun the workflow.
Seed variance enhancer
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, eyes, and expressions
NSFW detailers
Seed VR2 Upscaler to get 4k on low VRAM
Massive Post Production Suite
Smart Noise scrubber
Full tutorial available.
也有中文说明
Check out my other models:
My NSFW version with Anantomy Correctors:https://civarchive.com/models/2270894/zit-nsfw-anatomy-corrector
For ultimate Anime detail and control: https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations
For Realism and variety over the base model: https://civarchive.com/models/2231181/z-image-ultra-real-workflow
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉
Description
Updated Main brains 🧠 to Clownshark Samplers
Improved Sampler Options
One of the main advantages to using Clownshark Samplers is their fully_imlicit, diag_implicit, and multiple other sampler options. However, their names and schedules are not compatible with anything other than Clownshark Samplers, and only a fraction of regular names work with them, so I have dealt with this in two ways:
Regex replace: I have taken the base names and concerted them into Clownshark sampler names (the long list of string replaces on teh far left of this section)
ClownSampler Selector: You can manually select any one of the Clown Samplers to use. Note: all other parts of the workflow will be based on your choice in the ⚙️ User Settings area.
Added word ✂️nodes in Florence to get rid of any trace of logos or watermarks
Updated Qwen VL prompt enhance to abliterated GGUF capable one
added 3 choices of LLM instructions for better options creating realistic images
Added Sam3 detailers to bring it inline wth my other workflows
Improved notes
Improved CivitAI 🚩 words remover
Made tweaks
FAQ
Comments (15)
Hi! I’m using the new V8.0 workflow. I downloaded the required model Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf and placed it in:
/ComfyUI/models/LLM/GGUF/
The file is present and has fully downloaded (15.26 GiB), but I cannot select it in the QwenVL Prompt Enhancer (GGUF) node. The model dropdown only shows the default Qwen3-4B models, and the required Qwen3-VL-8B model does not appear.
I also refreshed the browser, recreated the node, and added the model to gguf_models.json, but it still does not appear in the dropdown.
Could you please tell me how to make the V8.0 Qwen node recognize this model, or confirm the correct model folder/path?
Okay, this is pretty common.,, It is NOT an issue with the software of teh file. What is happening is that I use a regular Load Clip for the regular model, and a Load Clip (GGUF) for the GGUIF model.
Try switching it to GGUF and see if it loads in that clip loader
The GGUF version does not work in the regular clip loader. I have tried numerous times to get teh regular model to play nice with it, but to no avail. If you want to use the abliterated text encoder, you need to use a GGUF model.
@lonecatone23 Thanks, but I’m not referring to the regular CLIP Loader or Load CLIP (GGUF).
I mean the separate QwenVL Prompt Enhancer (GGUF) node named “Qwen 📝🪄” in the V8.0 workflow. The workflow JSON itself has this exact model selected:
Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf
The file is already located in:
/ComfyUI/models/LLM/GGUF/
However, this exact model does not appear in the model_name dropdown of the QwenVL Prompt Enhancer node. Could you confirm how this specific node discovers local models, and whether the model requires another folder or a specific version of ComfyUI-QwenVL-Mod?
@fedechkoyursi114 That should automatically download the files it needs. They are built in. It does not need to hav eteh model loaded for it and will typiclaly crash when you do.
Remove the file from the folder and try a diffeent version.
@lonecatone23 Thanks. Just to clarify: when you say “remove the file and try a different version,” do you mean a different version of the QwenVL custom node, a different Qwen model, or a different workflow version?
The V8.0 workflow appears to reference Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf, so I want to make sure I understand correctly before deleting the 15.26 GiB file.
@fedechkoyursi114 No. Remove your abliterated file and stor it somewhere else. The custom node installs it for you.
If that does not work, then feed yout log to an LLM. There are sometimes conflicts due to updates
@lonecatone23 Hi, I followed your instructions and removed the manually downloaded abliterated GGUF file. I then removed and re-imported the V8.0 workflow and restarted ComfyUI completely.
However, the issue still occurs when I run the workflow.
The QwenVL Prompt Enhancer (GGUF) node shows:
Value not in list:
model_name: 'Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf' not in (list of length 31)
The execution log also reports:
FileNotFoundError: [QwenVL] GGUF missing and no repo_id/filename to download:
/workspace/runpod-slim/ComfyUI/models/llm/GGUF/Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf
I also noticed that there are two differently capitalized model paths:
/workspace/runpod-slim/ComfyUI/models/LLM/GGUF/
/workspace/runpod-slim/ComfyUI/models/llm/GGUF/
Since Linux paths are case-sensitive, these are two separate directories.
Previously, the manually downloaded 15.26 GiB GGUF file was located in:
/workspace/runpod-slim/ComfyUI/models/LLM/GGUF/
but the error shows that the node is searching in:
/workspace/runpod-slim/ComfyUI/models/llm/GGUF/
Could this LLM/llm path difference be causing the problem?
Also, both of these custom-node packages are currently installed:
ComfyUI-QwenVL
ComfyUI-QwenVL-Mod
The workflow appears to reference ComfyUI-QwenVL-Mod, but the traceback points to:
/workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL/AILab_QwenVL_GGUF_PromptEnhancer.py
Could these two packages be registering the same node and conflicting with each other?
I will paste the complete startup and execution logs below.
[INFO] [Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[INFO] [Impact Pack] Wildcards loading done.
[INFO] ComfyUI-GGUF: Allowing full torch compile
[/workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ckpts path: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_controlnet_aux/ckpts
[/workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using symlinks: False
[/workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[INFO] [RunpodDirect] Cgroup RAM patch enabled: host=503.42 GiB, limit=57.74 GiB, available=55.66 GiB
[INFO] ### Loading: ComfyUI-Manager (V3.41)
[INFO] [ComfyUI-Manager] network_mode: public
[INFO] [ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
[INFO] ### ComfyUI Version: v0.26.2 | Released on '2026-06-29'
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
------------------------------
[Civicomfy Config Initialized]
- Plugin Root: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy
- Web Directory: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/web
- ComfyUI Base Path: /workspace/runpod-slim/ComfyUI
------------------------------
[Civicomfy Manager] Warning: ComfyUI folder_paths not available. Path validation/opening might be limited.
[Manager] Successfully loaded 4 items from /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/download_history.json.
Civitai Download Manager starting (Max Concurrent: 3).
[Manager] Process queue thread started.
[Civicomfy] All server route modules loaded.
[Civicomfy] Core modules imported successfully.
------------------------------
--- Civicomfy Custom Extension Loaded ---
- Serving frontend files from: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/web (Relative: ./web)
- Download Manager Initialized: Yes
- API Endpoints Registered: Yes
- Frontend files found.
- Look for 'Civicomfy' button in the ComfyUI menu.
------------------------------
[Civicomfy] Verified model type directories:
- checkpoint: /workspace/runpod-slim/ComfyUI/models/checkpoints
- diffusionmodels: /workspace/runpod-slim/ComfyUI/models/unet
- unet: /workspace/runpod-slim/ComfyUI/models/unet
- lora: /workspace/runpod-slim/ComfyUI/models/loras
- locon: /workspace/runpod-slim/ComfyUI/models/loras
- lycoris: /workspace/runpod-slim/ComfyUI/models/loras
- vae: /workspace/runpod-slim/ComfyUI/models/vae
- embedding: /workspace/runpod-slim/ComfyUI/models/embeddings
- hypernetwork: /workspace/runpod-slim/ComfyUI/models/hypernetworks
- controlnet: /workspace/runpod-slim/ComfyUI/models/controlnet
- upscaler: /workspace/runpod-slim/ComfyUI/models/upscale_models
- motionmodule: /workspace/runpod-slim/ComfyUI/models/motion_models
- poses: /workspace/runpod-slim/ComfyUI/models/poses
- wildcards: /workspace/runpod-slim/ComfyUI/models/wildcards
- other: /workspace/runpod-slim/ComfyUI/models/other
[INFO]
Import times for custom nodes:
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfy-image-saver
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/Anomalous_Model_Browser
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-florence2
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/websocket_image_save.py
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI_JPS-Nodes
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-RunpodDirect
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/seedvarianceenhancer
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/cg-use-everywhere
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-mxtoolkit
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-workflow-encrypt
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Workflow-Encrypt
[INFO] 0.1 seconds (IMPORT FAILED): /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-GGUF-FantasyTalking
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-GGUF
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/erosdiffusion-eulerflowmatchingdiscretescheduler
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-post-processing-nodes
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-impact-subpack
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_essentials
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL
[INFO] 0.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-image-saver
[INFO] 0.3 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-various
[INFO] 0.3 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/gguf
[INFO] 0.4 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_ultimatesdupscale
[INFO] 0.4 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/demonalone-nodes-comfyui
[INFO] 0.4 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-custom-scripts
[INFO] 0.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-advancedliveportrait
[INFO] 0.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Zlycoris
[INFO] 0.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-ThinkingLLM
[INFO] 0.7 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy
[INFO] 0.7 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-vslinx-nodes
[INFO] 0.8 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/derfuu_comfyui_moddednodes
[INFO] 0.9 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-KJNodes
[INFO] 1.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL-Mod
[INFO] 1.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-impact-pack
[INFO] 1.2 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/rgthree-comfy
[INFO] 1.3 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
[INFO] 1.4 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_controlnet_aux
[INFO] 1.7 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-levelpixel
[INFO] 2.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-easy-use
[INFO] 3.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/seedvr2_videoupscaler
[INFO] 3.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfy-mtb
[INFO] 3.5 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Manager
[INFO] 3.8 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-logicutils
[INFO] 5.5 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_layerstyle
[INFO] 5.7 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/RES4LYF
[INFO] 6.8 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Crystools
[INFO] 7.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-ReActor
[INFO] 9.6 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-propost
[INFO] 10.3 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui-rmbg
[INFO] 79.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/comfyui_fill-nodes
[INFO] 79.3 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/was-ns
[INFO] 138.8 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/crt-nodes
[INFO]
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
FETCH ComfyRegistry Data: 5/161
[INFO] Using RAM pressure cache.
[INFO] Starting server
[INFO] To see the GUI go to: http://0.0.0.0:8188
FETCH ComfyRegistry Data: 10/161
FETCH ComfyRegistry Data: 15/161
FETCH ComfyRegistry Data: 20/161
FETCH ComfyRegistry Data: 25/161
FETCH ComfyRegistry Data: 30/161
FETCH ComfyRegistry Data: 35/161
FETCH ComfyRegistry Data: 40/161
FETCH ComfyRegistry Data: 45/161
FETCH ComfyRegistry Data: 50/161
FETCH ComfyRegistry Data: 55/161
FETCH ComfyRegistry Data: 60/161
FETCH ComfyRegistry Data: 65/161
FETCH ComfyRegistry Data: 70/161
FETCH ComfyRegistry Data: 75/161
FETCH ComfyRegistry Data: 80/161
FETCH ComfyRegistry Data: 85/161
FETCH ComfyRegistry Data: 90/161
FETCH ComfyRegistry Data: 95/161
FETCH ComfyRegistry Data: 100/161
FETCH ComfyRegistry Data: 105/161
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[INFO] [vsLinx] Combo type fix enabled via settings.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 110/161
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 115/161
FETCH ComfyRegistry Data: 120/161
FETCH ComfyRegistry Data: 125/161
FETCH ComfyRegistry Data: 130/161
FETCH ComfyRegistry Data: 135/161
FETCH ComfyRegistry Data: 140/161
[INFO] [vsLinx] Combo type fix enabled via settings.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 145/161
FETCH ComfyRegistry Data: 150/161
FETCH ComfyRegistry Data: 155/161
FETCH ComfyRegistry Data: 160/161
FETCH ComfyRegistry Data [DONE]
[INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[INFO] [ComfyUI-Manager] All startup tasks have been completed.
[ComfyUI-Manager] The ComfyRegistry cache update is still in progress, so an outdated cache is being used.
FETCH DATA from: /workspace/runpod-slim/ComfyUI/user/__manager/cache/1514988643_custom-node-list.json [DONE]
FETCH DATA from: /workspace/runpod-slim/ComfyUI/user/__manager/cache/746607195_github-stats.json [DONE]
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extras.json [DONE]
FETCH DATA from: /workspace/runpod-slim/ComfyUI/user/__manager/cache/1742899825_extension-node-map.json [DONE]
[INFO] got prompt
[ERROR] Failed to validate prompt for output 2229:
[ERROR] * AILab_QwenVL_GGUF_PromptEnhancer 2293:
[ERROR] - Value not in list: model_name: 'Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf' not in (list of length 31)
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 2083:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 1574:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 1302:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 2080:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 1281:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 1704:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 1286:
[ERROR] Output will be ignored
[ERROR] Failed to validate prompt for output 2082:
[ERROR] Output will be ignored
[WARNING] WARNING: .ISCHANGED() got an unexpected keyword argument 'format'
[WARNING] WARNING: PlaySound.IS_CHANGED() missing 1 required positional argument: 'self'
Florence2 missing keys: ['language_model.model.encoder.embed_tokens.weight', 'language_model.model.decoder.embed_tokens.weight']
[INFO] Requested to load Florence2
[INFO] loaded completely; 21103.80 MB usable, 665.28 MB loaded, full load: True
Florence2 beam: 100%|██████████| 1024/1024 [00:04<00:00, 255.30tok/s]
</s><s>A photorealistic portrait shoot from a portrait angle about a young woman with long brown hair wearing a white t-shirt. the image also shows soft lighting and a blurred background. in the middle of the image, a 20-year-old woman appears to be in her late teens or early twenties, with a neutral expression and a slight smile. she is wearing a simple white t-shirt that is short-sleeved and has a simple design. her brown hair falls down her back, and her blue eyes are looking directly at the viewer. her body is slim and her face is contorted in a neutral expression. she is wearing minimal makeup, but her lips are slightly parted. the background is blurred, with a clear blue sky and greenery in the distance. the overall mood of the image is peaceful and serene.
1girl, solo, long hair, looking at viewer, smile, blue eyes, shirt, brown hair, collarbone, white shirt, short sleeves, outdoors, sky, short-sleeved, lips, t-shirt, simple background, plain white shirt, realistic, white t-shirt</s>
[INFO] Using pytorch attention in VAE
[INFO] Using pytorch attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
[INFO] model_type FLOW
[WARNING] unet unexpected: ['model_sampling.sigmas']
[INFO] Requested to load ZImageTEModel_
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 7671MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[ERROR] !!! Exception during processing !!! [QwenVL] GGUF missing and no repo_id/filename to download: /workspace/runpod-slim/ComfyUI/models/llm/GGUF/Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf
[ERROR] Traceback (most recent call last):
File "/workspace/runpod-slim/ComfyUI/execution.py", line 542, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/runpod-slim/ComfyUI/execution.py", line 341, in get_output_data
return_values = await asyncmap_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/runpod-slim/ComfyUI/execution.py", line 315, in asyncmap_node_over_list
await process_inputs(input_dict, i)
File "/workspace/runpod-slim/ComfyUI/execution.py", line 303, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL/AILab_QwenVL_GGUF_PromptEnhancer.py", line 383, in process
self._load_model(model_name, device)
File "/workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL/AILab_QwenVL_GGUF_PromptEnhancer.py", line 267, in loadmodel
self._maybe_download_model(model_name, resolved)
File "/workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-QwenVL/AILab_QwenVL_GGUF_PromptEnhancer.py", line 222, in maybedownload_model
raise FileNotFoundError(f"[QwenVL] GGUF missing and no repo_id/filename to download: {resolved}")
FileNotFoundError: [QwenVL] GGUF missing and no repo_id/filename to download: /workspace/runpod-slim/ComfyUI/models/llm/GGUF/Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf
[INFO] Prompt executed in 38.68 seconds
@fedechkoyursi114 You're on Linux AND runpod?
yOu can just yank that node out. Its just to improve prompts. The workflow should self heal.
hi, the workflow seems really good. But i have a little problem, first the node huchukato/ComfyUI-QwenVL-Mod (1) ist recognized on ComfyUI, even though i downloaded it on this github repo https://github.com/huchukato/ComfyUI-QwenVL-Mod but it keep saying that the node pack is missing, i putted in custom nodes, and there is a requirement.txt file inside. And the other problem I have is this : Node 'Qwen 📝🪄' has no class_type. The workflow may be corrupted or a custom node is missing.
I have no clue what can be the error here, i have the lastest version of the workflow and comfyUI, i am on mac too. Do you have any solutions to my problems ?
its for this workflow : Z-Image Base & Turbo Pro Grade Realism Workflow (Low or High VRAM)
@yodabn67528 This is a common error. If you go to thebottom of that Repo, you will see a troubleshooting guide on how to fix it. I also have a link in my Tutorial article
@lonecatone23 i did, i downloaded python3 -m pip install -r requirements.txt --break-system-packages on the file but i still have the same error. Is this the solution? I downloaded llama cpp too. Are we using flash attention2 in this workflow? Should I do the "Flash Attention 2 not working?" troubleshoot?
@yodabn67528 Try feeding your log into an LLM. I purposely swapped the old one out for this version.
you can always delete it
@lonecatone23 thanks, it worked for me. the new bug i have is this : TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.
(File ".../custom_nodes/RES4LYF/beta/samplers.py", line 1248, in outer_sample: sigmas = sigmas.to(device))
how can i change the system to float32? LLM told me that i cant on mcbook but i would like your opinion first
@yodabn67528 oof...macbook. I have no idea. Bypass the sigma selector and see if you still error out.