Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Confirmed working with ComfyUI 0.26.0
Profil d'exécution
Description de la source
"Combined Workflow" v8.3 (20260623)
This "Combined Workflow" (about 2MB and over 600 nodes) is a ComfyUI txt2img workflow that performs SDXL , Pony , Illustrious , Flux1D , Qwen , ZImageTurbo/Base, Anima , Flux2Klein and Krea2Turbo generations with an optional prompt extension using LLMs / Ollama and Wildcards processing.
Note: the workflow is not fast, on a 4090, a batch of two image can take 7 minutes.
It will generate an upscaled 16MP image as the final result while staying as close as possible to the original generation and produce CivitAI compatible metadata for each stage of the image generation.
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
Use Combined Workflow v8.3 in ComfyUI to turn a text prompt into images with SDXL, Pony, Illustrious, Flux1D, Qwen, ZImageTurbo/Base, Anima, Flux2Klein, or Krea2Turbo; optional LLMs/Ollama can extend the prompt and Wildcards can be processed, producing an upscaled 16MP image andC
Stage 1 generates a regular image with the Detail Daemon sampler and sends it to a selector that can be bypassed for batch generation.
Stage 2 upscales the image to 4MP. Stage 3 uses Ultimate SD Upscale with the original model and LoRA characteristics, plus optional Flux.1D resampling, Cleanup, and face, hand, and eye detailers.
Stage 4 sends the result to SeedVR2 or HighresFix for a final 16MP image and performs color matching against the initial upscaled image.
Input: a text-to-image prompt. Optional inputs include LLM/Ollama prompt extension and Wildcards processing.
The workflow produces a regular image, a 4MP intermediate upscale, and a final upscaled 16MP image with CivitAI-compatible metadata for each generation stage.
Read the included READ ME FIRST section for usage and setup instructions, including diffusion-model checkpoints and Ultralytics setup; the listing names ComfyUI 0.26.0 as the version confirmed working.
Suggestion · non vérifié
The workflow lists these custom nodes: cg-image-filter, comfy-core, comfy-image-saver, comfy-mtb, comfyliterals, comfyui_controlnet_aux, comfyui_essentials, comfyui_llm_party, comfyui_ultimatesdupscale, comfyui-crystools, comfyui-custom-scripts, comfyui-detail-daemon, and comfyui
It also lists comfyui-fbcnn, comfyui-image-saver, comfyui-impact-pack, comfyui-inspire-pack, comfyui-kjnodes, comfyui-lora-manager, comfyui-ollama, comfyui-qwenvl, comfyui-resolution-master, comfyui-rmbg, rgthree-comfy, and seedvr2_videoupscaler.
The listed model files are 4x-UltraMix_Restore.pth, clip_l.safetensors, diffusion_pytorch_model.safetensors, jibMixFlux_v12SRPO-nvfp4.safetensors, Krea2Turbo/Krea2_Turbo_fp8mixed.safetensors, OmniSR_X2_DIV2K.safetensors, qwen_3_4b.safetensors, Qwen/jibMixQwen_v60.safetensors, Q?
For batch generation, bypass the Stage 1 selector; Stage 3 offers optional Flux.1D resampling followed by Cleanup.
If Ollama is available, the description says setting keep alive to 0 unloads the model immediately after a request and that the conversion model should be instruction-tuned.
Suggestion · non vérifié
Treat the 7-minute figure as a planning reference only: the description reports that a batch of two images on a 4090 can take 7 minutes.
Suggestion · non vérifié
Before use, verify the exact filenames and intended roles for Qwen/jibMixQwen_v60.safetensors, jibMixFlux_v12SRPO-nvfp4.safetensors, qwen_3_4b.safetensors, OmniSR_X2_DIV2K.safetensors, 4x-UltraMix_Restore.pth, diffusion_pytorch_model.safetensors, Krea2Turbo/Krea2_Turbo_fp8mixed.s
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
3 extraitsSource context: 2172 downloads · Type Workflows · Base model Other
Stage 1: Generate the regular image using Detail Daemon sampler, pass it to a selector (can be bypassed for batch generation)
Stage 2: Upscale to 4MP using a model
Stage 3: Use "Ultimate SD Upscale" to redefine the components of the 4MP image using the original model and LoRAs' specific characteristics. An optional Flux.1D resampler is available followed by a Cleanup stage, then Faces, Hands and Eyes Detailer are then used on the resulting image.
Stage 4: That result is sent to SeedVR2 or HighresFix to generate the final 16MP image and a color matching step is performed to make it as close as possible as the initial upscaled image.
The workflow contains a READ ME FIRST section that details some information about how it came to be, what it does and how to use it . Please refer to it for more details.
FYSA: list (and count) of used custom nodes:
1 "cg-image-filter", 235 "comfy-core", 4 "comfy-image-saver", 2 "comfy-mtb", 18 "comfyliterals", 1 "comfyui_controlnet_aux", 12 "comfyui_essentials", 9 "comfyui_llm_party", 2 "comfyui_ultimatesdupscale", 12 "comfyui-crystools", 61 "comfyui-custom-scripts", 9 "comfyui-detail-daemon", 51 "comfyui-easy-use", 5 "comfyui-fbcnn", 73 "comfyui-image-saver", 41 "comfyui-impact-pack", 1 "comfyui-inspire-pack", 35 "comfyui-kjnodes", 7 "comfyui-lora-manager", 6 "comfyui-ollama", 4 "comfyui-qwenvl", 1 "comfyui-resolution-master", 13 "comfyui-rmbg", 76 "rgthree-comfy", 3 "seedvr2_videoupscaler",
Previous releases:
v8.2 (20260531): Added Flux2Klein + Confirmed working with ComfyUI 0.22.0
v8.1 (20260504): Updated to work with updated cg-image-filter .
v8 (20260308): Added QwenVL as a local LLM (01a, 01b, 01z) + Added QwenVL based "image to prompt" extraction (01c) + Added a new post-positive prompt generation optimization (01z) + Added Detail Deamon for all Samplers and a couple resampler + Added ZimageBase and Anima
v7 (20260216): Added external LLMs capability + Added an "Automatic" system prompt with model specific rules + Added an optional Flux1.D Resampler (S3, 05a03) + Added a HiresFix "Cleanup" node right after the Resampler steps (S3, 05b01) + Split S3 into its core components (the largest block on the workflow) with many ways to compare from step to step + Added many additional "notes" to explain how to make better use of the workflow
v6 (20260131): Improved Stage 3: Resampler (2-pass: Regeneration + Details enhancement) and Detailers to follow original conditioning + Continued improvement to "Ollama" logic
v5 (20260124): Added "Advanced" Ollama prompt + Added a new "LoRA randomizer" group + Implemented SEGS for Detaillers using "small" Face/Eyes/Hands selection logic
v4.1 (20260118): included setup requirements (diffusion models as checkpoints + Ultralytics required setup) in "READ ME FIRST" section + Changed to a common resolution selector
v4 (20260111): Addition of alternate samplers for Qwen and Z Image Turbo + removal of node failing to install on new Comfy installation + extended documentation: muted nodes-chain need to be manually selected
v3.1 (20251231): Hotfix for face/hand size
v3 (20251230): Additional detailers tweaks + alternative models for refiner/detailer steps
v2 (20251228): Trigger word selection + Detailers tweak + Usage clarifications
v1 (20251226): Initial release
Work-in-Progress release:
This workflow(Pony, SDXL, Illustrious only for now) is a Work-In-Progress combination, testing and tweaking of various elements from other workflows to generate an upscaled 16MP image as the final result while staying as close as possible to the original generation as generate CivitAI metadata for each stage of the image generation.
Stage 1: Generate the regular image, pass it to a selector (can be bypassed for batch generation)
Stage 2: Upscale to 4MP using HiResFix
Stage 3: Use Ultimate SD Upscaler (No Upscale) to redefine the components of 4MP image using the original model and loras' specific characteristics. Faces and Eyes Detailer are then used on the resulting image.
Stage 4: That result is sent to SeedVR2 to generate the final 16MP image.
There are many nodes involved in this workflow. Because of that I made use of multiple subgraphs to keep the workflow organized and easy to navigate.
Groups exists as organizational structure for the entire process and follow the Stage numbers.
It "works for me" but it might not be the best way to do it. Feedback is welcome.
PS: Despite my best effort, I still do not know how to have the "Nodes" used show on each image's page on CivitAI -- if someone knows how to please let me know.
Older releases:
The workflows I use with my Wildcards (see my account for those).
Within the zip is a README.md that explains the various use cases:
The SDXL, Illustrious and Pony compatible workflow is an extension of @DigitalPastel 's "Smooth Workflow" https://civitai.com/models/1598938/smooth-workflow-txt2img
The txt2img Flux and Qwen workflow is an extension of @AlexLai 's "Atomix Workflow" https://civitai.com/models/878828/atomix-flux-txt2img-workflow
The Z-Image Turbo workflow is an extension of @MrSmith2025 's "Z-Image Turbo - T2I Workflow + Detailer + SeedVR2 Upscaler + Color Grading" https://civitai.com/models/2174733/z-image-turbo-t2i-workflow-detailer-seedvr2-upscaler-color-grading
Each workflow can work with Ollama (if available) to create a multi-line narrative. They use Ollama as part of the workflow, which might be a VRAM resource constraint (setting "keep alive" to 0 will unload the model immediately after the request finishes). The conversion model should be instruction-tuned.
Estimation des besoins VRAM
Estimation indisponible
64,8 GB sur 7 de 13 fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 334x-UltraMix_Restore.pth
Non résoluUpscaler · Unknown
Text encoder · 235 MB · SAFETENSORS · Hugging Face · Comfy-Org/stable-diffusion-3.5-fp8
Upscaler · Registry · ComfyUI_UltimateSDUpscale
ControlNet · 9.61 GB · Hugging Face · Kwai-Kolors/Kolors
jibMixFlux_v12SRPO-nvfp4.safetensors
Non résoluCheckpoint · Unknown
Checkpoint · Hugging Face · Krea2Turbo/Krea2_Turbo_fp8mixed.safetensors
OmniSR_X2_DIV2K.safetensors
Non résoluCheckpoint · Unknown
Text encoder · 7.49 GB · Hugging Face · Comfy-Org/flux2-klein
Sources possibles
Checkpoint · 38.1 GB · Civitai · 1936965
VAE · 242 MB · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
Sources possibles
Upscaler · 17.1 MB · PT · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Hugging Face · xiaofennuonuo/comfyui
ZImageTurbo/ultrafluxVAEImproved_v10.safetensors
Fichier non vérifiéVAE · Hugging Face · XimiXimix/ultrafluxVAEImproved_v10
Pack de nœud · Registry
Pack de nœud · Registry
Source context: 2068 downloads · Type Workflows · Base model Other
Source context: 2066 downloads · Type Workflows · Base model Other
Pack de nœud · Registry
Pack de nœud · Registry
comfyui_controlnet_aux
PossiblePack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
comfyui-qwenvl
PossiblePack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
