RealVisXL v4.0 not generating images properly about fastsdcpu HOT 10 CLOSED

thanks a lot

from fastsdcpu.

well now it generates an image (after changing the interference steps to 25 or max value) but the images look extremely bad according to https://imgsys.org/ RealVisXL v4.0 is the best open source image model. here are the images that it generated
prompt = nature landscape, size = 1024 1024

prompt = nature landscape or fantasy landscape i dont remember, size = 256 256

from fastsdcpu.

prompt = the moon, size = 512 512

from fastsdcpu.

same prompt same size

from fastsdcpu.

@AlgorithmicKing Able to generate image without any issue.

Config

{
    "lcm_model_id": "stabilityai/sd-turbo",
    "openvino_lcm_model_id": "rupeshs/sd-turbo-openvino",
    "use_offline_model": false,
    "use_lcm_lora": true,
    "lcm_lora": {
        "base_model_id": "SG161222/RealVisXL_V4.0",
        "lcm_lora_id": "latent-consistency/lcm-lora-sdxl"
    },
    "use_tiny_auto_encoder": false,
    "use_openvino": false,
    "prompt": "the moon",
    "negative_prompt": "",
    "strength": 0.6,
    "image_height": 768,
    "image_width": 768,
    "inference_steps": 3,
    "guidance_scale": 1.0,
    "number_of_images": 1,
    "seed": -1,
    "use_seed": false,
    "use_safety_checker": false,
    "diffusion_task": "text_to_image",
    "lora": {
        "weight": 0.5,
        "fuse": true,
        "enabled": false
    },
    "controlnet": null,
    "rebuild_pipeline": false
}

from fastsdcpu.

@AlgorithmicKing Follow the config, image size 768 x 768, steps 3
Mode - LCM-LoRa select LCM-Lora model as latent-consistency/lcm-lora-sdxl

from fastsdcpu.

how do i set the lcm lora model to SG161222/RealVisXL_V4.0? i dont see the option

from fastsdcpu.

@AlgorithmicKing update stable-diffusion-models.txt
Also refer : https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#models

from fastsdcpu.

1. also how did you know to set those specific configuration where did you get where can i get it for other models?

from fastsdcpu.

@AlgorithmicKing please checkout readme it has lots of details for you.
https://github.com/rupeshs/fastsdcpu/blob/main/Readme.md

from fastsdcpu.