Skip to content

Problem with Efficient Loader because there are too many properties(?) #26

@rodneyviana

Description

@rodneyviana

First of all, congratulations for this amazing software. I was able to make most of it work, but there is a problem with a particular custom node. So this is the portion I believe is failing, I am attaching the workflow to this post) and the code generated,

... removed for brevity ...
    "class_type": "Eff. Loader SDXL"
  },
  "2": {
    "inputs": {
      "input_mode": "simple",
      "lora_count": 2,
      "lora_name_1": "add-detail-xl.safetensors",
      "lora_wt_1": 0.7000000000000001,
      "model_str_1": 1,
      "clip_str_1": 1,
      "lora_name_2": "xl_more_art-full_v1.safetensors",
      "lora_wt_2": 0.7000000000000001,
      "model_str_2": 1,
      "clip_str_2": 1,
      "lora_name_3": "None",
      "lora_wt_3": 1,
      "model_str_3": 1,
      "clip_str_3": 1,
      "lora_name_4": "None",
      "lora_wt_4": 1,
      "model_str_4": 1,
      "clip_str_4": 1,
      "lora_name_5": "None",
      "lora_wt_5": 1,
      "model_str_5": 1,
... removed for brevity ...

Generates:
        lora_stacker = NODE_CLASS_MAPPINGS["LoRA Stacker"]()
        lora_stacker_2 = lora_stacker.lora_stacker(input_mode="simple", lora_count=2)

        eff_loader_sdxl = NODE_CLASS_MAPPINGS["Eff. Loader SDXL"]()
        ksampler_sdxl_eff = NODE_CLASS_MAPPINGS["KSampler SDXL (Eff.)"]()
        saveimage = SaveImage()

        for q in range(10):
            eff_loader_sdxl_1 = eff_loader_sdxl.efficientloaderSDXL(
                base_ckpt_name="copaxTimelessxlSDXL1_v5.safetensors",
                base_clip_skip=-1,
                refiner_ckpt_name="sdXL_v10RefinerVAEFix.safetensors",
                refiner_clip_skip=-1,
                positive_ascore=6,
                negative_ascore=2,
                vae_name="Baked VAE",
                positive="photorealistic scene of (..removed for brevity..) freckles, realistic, wide angle,  wide shot, 4k, film grain, depth, masterpiece",
                negative="embedding:negativeXL (worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist, asian, long hands, helmet:1.5, cgi, 3d, illustration, blue skin, unnatural skin, close up shot, out of frame ",
                empty_latent_width=1024,
                empty_latent_height=1024,
                batch_size=1,
                lora_stack=get_value_at_index(lora_stacker_2, 0),
            )

workflow_api.json.txt
workflow_api.py.txt

Notice that the number of properties on the lora is huge and only the first 2 properties are added.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions