philz1337x / multidiffusion-upscaler

High resolution image Upscaler and Enhancer. Twitter/X: @philz1337x

  • Public
  • 19.3K runs
  • L40S
  • Paper
Iterate in playground
  • Prediction

    philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7
    ID
    owj767tblz32gyosrwrsnxc74y
    Status
    Succeeded
    Source
    Web
    Hardware
    A40
    Total duration
    Created

    Input

    seed
    1337
    image
    image
    width
    512
    height
    512
    prompt
    masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>
    sd_vae
    vae-ft-mse-840000-ema-pruned.safetensors
    cn_model
    control_v11f1e_sd15_tile
    sd_model
    juggernaut_reborn.safetensors [338b85bc4f]
    cn_module
    tile_resample
    cn_weight
    0.6
    scheduler
    DPM++ 3M SDE Karras
    td_method
    MultiDiffusion
    cn_lowvram
    td_overlap
    4
    num_outputs
    1
    cn_downsample
    1
    td_tile_width
    112
    cn_resize_mode
    1
    cn_threshold_a
    1
    cn_threshold_b
    1
    guidance_scale
    6
    td_image_width
    1
    td_tile_height
    144
    cn_control_mode
    1
    cn_guidance_end
    1
    negative_prompt
    (worst quality, low quality, normal quality:2) JuggernautNegative-neg
    td_image_height
    1
    td_scale_factor
    2
    tv_fast_decoder
    tv_fast_encoder
    cn_pixel_perfect
    enable_tiled_vae
    td_noise_inverse
    td_upscaler_name
    4x-UltraSharp
    cn_guidance_start
    0
    enable_controlnet
    td_overwrite_size
    denoising_strength
    0.35
    td_keep_input_size
    td_tile_batch_size
    8
    tv_move_vae_to_gpu
    cn_preprocessor_res
    512
    num_inference_steps
    18
    tv_decoder_tile_size
    192
    tv_encoder_tile_size
    3072
    enable_tiled_diffusion
    td_noise_inverse_steps
    0
    clip_stop_at_last_layers
    1
    tv_fast_encoder_color_fix
    td_noise_inverse_renoise_kernel
    3
    td_noise_inverse_renoise_strength
    0

    Output

    output
    Generated in

Want to make some of these yourself?

Run this model