WorkflowListedExternal

Fast Chroma w/ Upscaler, Refiner and Face detailer [Low VRAM] — v1.4

Sourcecivitai.com/models/1907566

TaskMultiCapabilitiesImage edit · Image to image · Text to image · UpscalingFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Sep 13, 2026

Source description

So, here’s how I roll: this workflow generates a little Chroma image with txt2img, upscales and refines it for some extra polish with FluxRefinerV1.1 with img2img , and gives faces a nice touch-up ( Face Detailer ). On my trusty laptop (rockin’ an RTX 3070 with 8GB VRAM and 40GB RAM), it makes a 1120 x 1120 pic in about 180 to 280 seconds —depending on the prompt, as I said in my previous workflow, I’m new to ComfyUI, so if you’ve got any tips or tricks, I’m all ears! On the bright side, at least I didn’t make a huge Spaghetti Monster this time!

Models:

chroma-unlocked-v48-detail-calibrated-Q4_0.gguf

fluxRefiner_v11.safetensors

CLIPs:

flan_t5_xxl_TE-only_FP8.safetensors

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

This workflow turns text prompts into Chroma images, then upscales and refines them with FluxRefinerV1.1 through img2img and touches up faces with Face Detailer; the description specifies a 1120 × 1120 output.

Inputs and outputs

Input: a text prompt. Output: a Chroma image described as 1120 × 1120.

Setup

The listing names Flux.1 D as the base model and labels the workflow “[Low VRAM].”

Dependencies

Files named for this workflow include chroma-unlocked-v48-detail-calibrated-Q4_0.gguf, flux1-dev-fp8.safetensors, fluxRefiner_v11.safetensors, flan_t5_xxl_TE-only_FP8.safetensors, and ae.safetensors.
Other named files include 4x_NMKD-Siax_200k.pth, 4x-UltraSharp.pth, bbox/Eyeful_v2-Paired.pt, bbox/face_yolov8m.pt, and sam_vit_b_01ec64.pth.
Named ComfyUI add-ons include comfy-image-saver, comfyui_essentials_mb, comfyui_memory_cleanup, comfyui-impact-pack, comfyui-impact-subpack, comfyui-kjnodes, comfyui-unload-model, and comfyui-upscale-by-model; the description also names comfyui-uscape-by-model and comfyui-vrgamde

Configuration

No LoRA is listed.
The listing does not specify a model use license.

Cautions

Before setup, confirm the exact files intended for chroma-unlocked-v48-detail-calibrated-Q4_0.gguf, flan_t5_xxl_TE-only_FP8.safetensors, ae.safetensors, and bbox/face_yolov8m.pt.
Suggestion · not verified
Confirm which ComfyUI add-on is intended by comfyui-gguf before installing it.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1907566

Verified Jul 19

Source excerpts

1 excerpt

NoteJul 19civitai.com/models/1907566

Source context: 1342 downloads · Type Workflows · Base model Flux.1 D