Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

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

Open
rodneyviana opened this issue Nov 10, 2023 · 2 comments

Comments

@rodneyviana
Copy link

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.

@pydn
Copy link
Owner

pydn commented Nov 28, 2023

Thank you! Do you have a link to the custom node repo? And the version you are using to create the workflow_api.json file?

@rodneyviana
Copy link
Author

rodneyviana commented Nov 28, 2023 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants