Issue with Enhancement Not Working When Using Image Prompt

[deadpipe]

Hello,

I have a question—apologies if this is obvious. I'm trying to provide an input image along with a text prompt while having enhancement enabled ("After First Enhancement" option enabled).

I tested both /v2/generation/text-to-image-with-ip and /v2/generation/image-prompt. While they generate images, the server logs show:

[Enhance] Skipping, preconditions aren't met

Additionally, when I post the same parameters to /v2/generation/image-enhance, the server returns a 500 Internal Server Error with this traceback:

UnboundLocalError: local variable 'input_image_bytes' referenced before assignment

Below are my parameters and code:

import requests
import json
import base64
import io

host = "http://127.0.0.1:1111"

source = open("C:\\Users\\Deadpipe\\Downloads\\test.png", "rb").read()
image = base64.b64encode(source).decode('utf-8')

def image_prompt(params: dict) -> dict:
    response = requests.post(
        url=f"{host}/v2/generation/text-to-image-with-ip",
        data=json.dumps(params),
        headers={"Content-Type": "application/json"}
    )
    return response.json()

params = {
  "prompt": "Elegant and modern living room",
  "negative_prompt": "low light, night light, dim light",
  "style_selections": [
    "Fooocus Photograph"
  ],
  "performance_selection": "Quality",
  "aspect_ratios_selection": "1024*1024",
  "image_number": 1,
  "image_seed": -1,
  "sharpness": 2,
  "guidance_scale": 4,
  "base_model_name": "juggernautXL_v8Rundiffusion.safetensors",
  "refiner_model_name": "None",
  "refiner_switch": 0.5,
  "loras": [
    {
      "enabled": True,
      "model_name": "sd_xl_offset_example-lora_1.0.safetensors",
      "weight": 0.1
    },
    {
      "enabled": False,
      "model_name": "None",
      "weight": 1
    },
    {
      "enabled": False,
      "model_name": "None",
      "weight": 1
    },
    {
      "enabled": False,
      "model_name": "None",
      "weight": 1
    },
    {
      "enabled": False,
      "model_name": "None",
      "weight": 1
    }
  ],
  "advanced_params": {
    "adaptive_cfg": 7,
    "adm_scaler_end": 0.3,
    "adm_scaler_negative": 0.8,
    "adm_scaler_positive": 1.5,
    "black_out_nsfw": False,
    "canny_high_threshold": 128,
    "canny_low_threshold": 64,
    "clip_skip": 2,
    "controlnet_softness": 0.25,
    "debugging_cn_preprocessor": False,
    "debugging_dino": False,
    "debugging_enhance_masks_checkbox": False,
    "debugging_inpaint_preprocessor": False,
    "dino_erode_or_dilate": 0,
    "disable_intermediate_results": False,
    "disable_preview": True,
    "disable_seed_increment": False,
    "freeu_b1": 1.01,
    "freeu_b2": 1.02,
    "freeu_enabled": False,
    "freeu_s1": 0.99,
    "freeu_s2": 0.95,
    "inpaint_advanced_masking_checkbox": True,
    "inpaint_disable_initial_latent": False,
    "inpaint_engine": "v2.6",
    "inpaint_erode_or_dilate": 0,
    "inpaint_respective_field": 1,
    "inpaint_strength": 1,
    "invert_mask_checkbox": False,
    "mixing_image_prompt_and_inpaint": False,
    "mixing_image_prompt_and_vary_upscale": False,
    "overwrite_height": -1,
    "overwrite_step": -1,
    "overwrite_switch": -1,
    "overwrite_upscale_strength": -1,
    "overwrite_vary_strength": -1,
    "overwrite_width": -1,
    "refiner_swap_method": "joint",
    "sampler_name": "dpmpp_2m_sde_gpu",
    "scheduler_name": "karras",
    "skipping_cn_preprocessor": False,
    "vae_name": "Default (model)"
  },
  "save_meta": True,
  "meta_scheme": "fooocus",
  "save_extension": "png",
  "save_name": "test",
  "read_wildcards_in_order": False,
  "require_base64": False,
  "async_process": False,
  "webhook_url": "",
  "image_prompts": [
  {
    "cn_img": image,
    "cn_stop": 0.6,
    "cn_weight": 1.6,
    "cn_type": "PyraCanny"
  }
  ],
  "enhance_input_image": "",
  "enhance_checkbox": True,
  "enhance_uov_method": "Upscale (2x)",
  "enhance_uov_processing_order": "After First Enhancement",
  "enhance_uov_prompt_type": "Original Prompts",
  "save_final_enhanced_image_only": True,
  "enhance_ctrlnets": [
    {
      "enhance_enabled": False,
      "enhance_mask_dino_prompt": "face",
      "enhance_prompt": "",
      "enhance_negative_prompt": "",
      "enhance_mask_model": "sam",
      "enhance_mask_cloth_category": "full",
      "enhance_mask_sam_model": "vit_b",
      "enhance_mask_text_threshold": 0.25,
      "enhance_mask_box_threshold": 0.3,
      "enhance_mask_sam_max_detections": 0,
      "enhance_inpaint_disable_initial_latent": False,
      "enhance_inpaint_engine": "v2.6",
      "enhance_inpaint_strength": 1,
      "enhance_inpaint_respective_field": 0.618,
      "enhance_inpaint_erode_or_dilate": 0,
      "enhance_mask_invert": False
    }
  ],
}

result = image_prompt(params)
print(json.dumps(result, indent=4, ensure_ascii=False))

Could you please let me know if I am missing something? Thank you for your time!

[mrhan1993]

The problem is that the current code doesn't support this, so you can try to separate them. I will fix this problem when I have time.

[deadpipe]

Sure @mrhan1993 . I'll look forward to it