CivArchive
    Amazing Flux_SD3.5_8Mega_Pixel_image_upscale_process - v1.0
    NSFW
    Preview 25444764
    Preview 25445329
    Preview 25444080
    Preview 25444092

    Remember to read the instruction!

    Please use Pixel version, if you don't have good understanding on Latent version.

    This will provide you

    Crazzzzzzzzzzzzzzzzzzzzzzzzzzzzzy

    Amazzzzzzzzzzzzzzzzzzzzzzzzzzing

    Higggggggggggggggggggggggh

    Quaaaaaaaaaaaaaaaaaaaaaaaality

    Images!!!!

    just try it!

    remember use my custom node and modify the parameter carefully!

    adding jc2 version. Remember to download my nodes

    https://github.com/TTPlanetPig/Comfyui_TTP_Toolset

    https://github.com/TTPlanetPig/Comfyui_JC2

    check your Max VRAM before you run it :)

    at least 10GB for nf4 and 20GB for BF16

    Following is for Pixel version instruction:

    Just enjoy, and try not to touch my setting if you are not sure what you are doing.

    if you can run flux official properly, you can run this one

    Following is for Latent Version instruction:

    This is a workflow for my simple logic amazing upscale node for DIT model. it can be common use for Flux,Hunyuan,SD3 It can simple tile the initial image into pieces and then use image-interrogator to get each tile prompts for more accurate upscale process. The condition will be properly handled and the hallucination will be significantly eliminated.

    you can download my newly build node here:

    https://github.com/TTPlanetPig/Comfyui_TTP_Toolset  ,please update to latest version

    A updated version for Flux Hi-res fix!!!

    adjust the denoise to control the difference and possible latent block issue.

    You will be shocked by the detailed high-resolution photos!!!

    Key parameter to adjust:

    1. tile block numbers: recommended 2*3 or 3*2 or 3*3

    2. overlap rate: recommended 0.15-0.2! Please update my node to latest version for this function.

    I also used the node:

    https://github.com/yolain/ComfyUI-Easy-Use

    and

    https://github.com/kijai/ComfyUI-Florence2

    Description

    FAQ

    Comments (7)

    NoobFromEgyptAug 21, 2024
    CivitAI

    How to fix this problem

    Error occurred when executing DownloadAndLoadFlorence2Model:

    FlashAttention2 has been toggled on, but it cannot be used due to the following error: the package flash_attn seems to be not installed. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2.

    ttplanet
    Author
    Aug 21, 2024· 1 reaction

    please you can try replace it with other nodes for llm?

    NoobFromEgyptAug 21, 2024

    @ttplanet okay thanks

    raidmachine132017712Aug 22, 2024· 1 reaction

    can't we remove the LLM thing? we just give empty prompt, or any other way. low vram suffers with adding extra LLMs

    sh1201Aug 23, 2024

    @raidmachine132017712 area prompts lead to better result when upscaling, you may try tagging each tile yourself to save vram, simple descriptions are also working great

    ttplanet
    Author
    Aug 23, 2024

    @raidmachine132017712 I will release a non LLM version soon

    RLKAug 21, 2024
    CivitAI

    This is so much better than Ultimate SD Upscale, good job.

    Workflows
    Flux.1 D

    Details

    Downloads
    274
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/21/2024
    Updated
    8/5/2026
    Deleted
    -

    Files

    amazingFluxSD358mega_v10.zip

    Mirrors

    CivitAI (1 mirrors)