CivArchive
    FLUX 3 Klein 4K Upscale and Restore — Single Image - v1.0
    NSFW
    Preview 147650681


    RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2112078299170500609?inviteCode=rh-v1111

    RunningHub China: https://www.runninghub.cn/post/2111806478330982402/?inviteCode=rh-v1111

    Bilibili tutorial video: https://www.bilibili.com/video/BV11xJo6nEFh/

    # FLUX 3 Klein — Single-Image Reconstruction with RH Captioning

    ## What this workflow does

    Inspect one image, its generated caption, and its reconstructed output before moving to batch processing.

    ## Who should use it

    ComfyUI users able to resolve compatible node versions, provide authorized images, and inspect actual outputs. This is one independent workflow, not a verified result package or a new model checkpoint.

    ## Requirements

    Common loader references: `flux3_image_klein_sd_int8_convrot.safetensors`, `qwen3vl_4b_int8_convrot.safetensors`, `flux2-vae.safetensors`, and `RealESRGAN_x4plus.pth`. Weights, example inputs, and a tested installation lockfile are not included.

    The service node stores google/gemini-3.1-flash-lite-preview, but that identifier does not establish an endpoint, credential type, price, or verified invocation. Requests to preserve identity and composition are not fidelity measurements.

    ## Configuration and steps

    LoadImage 13 feeds the upscaler, RHLLMChatNode 16, and original-image side of comparer 12. The LLM sees the source image, not the enlarged image. Its response connects to CLIPTextEncode 8; a stored blank text widget does not mean the effective prompt is empty.

    Resolve compatible assets and nodes, select an authorized source image, and confirm the RH service configuration and image-transfer permissions. Review the returned description, then inspect the actual decoded result and original-versus-result comparison. Save node 5 uses prefix AIKSK_FLUX3_KLEIN_FINAL_4K_SINGLE.

    The image path passes through model upscaling, ImageScaleToMaxDimension, ReferenceMultiLatent, sampling, and VAE decoding. The scaling node stores ["lanczos", 3840], and its title/note describe a long-edge target. ReferenceMultiLatent stores keep resolution. The sampler array is [9527, "fixed", 16, 1, "euler", "simple", 1]; the source titles/notes call it a 16-step/CFG1 preset, but the export lacks a complete named widget schema. Confirm the matching UI instead of inventing parameter mappings. No fixed 3840×2160 size, unchanged aspect ratio, improved quality, or successful output is verified.

    ## Files

    - [Workflow JSON]()

    - [Promotional cover]()

    ## Version note and limitations

    The JSON retains the supplied source bytes. This copy does not announce a new publication, model version, performance upgrade, or relationship to an existing remote project. Cover artwork is not a verified inference sample; supply a real reviewed sample separately if required.

    No new runtime, GPU, cost, quality, or batch-completion evidence is included. A requested caption, stored target, or progress value is not an output guarantee. Verify installation, image-transfer permissions, effective naming/type settings, and actual results before deployment.

    ## Credits, tutorial, and rights

    The workflow is supplied through AI-KSK with source notes retained. A matching international tutorial URL has not been confirmed from the supplied metadata; no replacement is guessed. Verify rights for workflows, node code, weights, cover artwork, and source images separately. Regeneration does not remove source-image obligations or create blanket redistribution permission.

    Description



    RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2112078299170500609?inviteCode=rh-v1111

    RunningHub China: https://www.runninghub.cn/post/2111806478330982402/?inviteCode=rh-v1111

    Bilibili tutorial video: https://www.bilibili.com/video/BV11xJo6nEFh/

    # FLUX 3 Klein — Single-Image Reconstruction with RH Captioning

    ## What this workflow does

    Inspect one image, its generated caption, and its reconstructed output before moving to batch processing.

    ## Who should use it

    ComfyUI users able to resolve compatible node versions, provide authorized images, and inspect actual outputs. This is one independent workflow, not a verified result package or a new model checkpoint.

    ## Requirements

    Common loader references: `flux3_image_klein_sd_int8_convrot.safetensors`, `qwen3vl_4b_int8_convrot.safetensors`, `flux2-vae.safetensors`, and `RealESRGAN_x4plus.pth`. Weights, example inputs, and a tested installation lockfile are not included.

    The service node stores google/gemini-3.1-flash-lite-preview, but that identifier does not establish an endpoint, credential type, price, or verified invocation. Requests to preserve identity and composition are not fidelity measurements.

    ## Configuration and steps

    LoadImage 13 feeds the upscaler, RHLLMChatNode 16, and original-image side of comparer 12. The LLM sees the source image, not the enlarged image. Its response connects to CLIPTextEncode 8; a stored blank text widget does not mean the effective prompt is empty.

    Resolve compatible assets and nodes, select an authorized source image, and confirm the RH service configuration and image-transfer permissions. Review the returned description, then inspect the actual decoded result and original-versus-result comparison. Save node 5 uses prefix AIKSK_FLUX3_KLEIN_FINAL_4K_SINGLE.

    The image path passes through model upscaling, ImageScaleToMaxDimension, ReferenceMultiLatent, sampling, and VAE decoding. The scaling node stores ["lanczos", 3840], and its title/note describe a long-edge target. ReferenceMultiLatent stores keep resolution. The sampler array is [9527, "fixed", 16, 1, "euler", "simple", 1]; the source titles/notes call it a 16-step/CFG1 preset, but the export lacks a complete named widget schema. Confirm the matching UI instead of inventing parameter mappings. No fixed 3840×2160 size, unchanged aspect ratio, improved quality, or successful output is verified.

    ## Files

    - [Workflow JSON]()

    - [Promotional cover]()

    ## Version note and limitations

    The JSON retains the supplied source bytes. This copy does not announce a new publication, model version, performance upgrade, or relationship to an existing remote project. Cover artwork is not a verified inference sample; supply a real reviewed sample separately if required.

    No new runtime, GPU, cost, quality, or batch-completion evidence is included. A requested caption, stored target, or progress value is not an output guarantee. Verify installation, image-transfer permissions, effective naming/type settings, and actual results before deployment.

    ## Credits, tutorial, and rights

    The workflow is supplied through AI-KSK with source notes retained. A matching international tutorial URL has not been confirmed from the supplied metadata; no replacement is guessed. Verify rights for workflows, node code, weights, cover artwork, and source images separately. Regeneration does not remove source-image obligations or create blanket redistribution permission.

    Workflows
    Flux.3 Klein

    Details

    Downloads
    42
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/2/2026
    Updated
    11/8/2026
    Deleted
    -

    Files

    01_FLUX3_Klein_4K____RH_LLM__________.json