ComfyUI Node: Forbidden Vision 🎯 Fixer
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Forbidden Vision
Inputs
model MODEL
vae VAE
positive CONDITIONING
negative CONDITIONING
steps INT
cfg_scale FLOAT
sampler
- euler
- euler_cfg_pp
- euler_ancestral
- euler_ancestral_cfg_pp
- heun
- heunpp2
- exp_heun_2_x0
- exp_heun_2_x0_sde
- dpm_2
- dpm_2_ancestral
- lms
- dpm_fast
- dpm_adaptive
- dpmpp_2s_ancestral
- dpmpp_2s_ancestral_cfg_pp
- dpmpp_sde
- dpmpp_sde_gpu
- dpmpp_2m
- dpmpp_2m_cfg_pp
- dpmpp_2m_sde
- dpmpp_2m_sde_gpu
- dpmpp_2m_sde_heun
- dpmpp_2m_sde_heun_gpu
- dpmpp_3m_sde
- dpmpp_3m_sde_gpu
- ddpm
- lcm
- ipndm
- ipndm_v
- deis
- res_multistep
- res_multistep_cfg_pp
- res_multistep_ancestral
- res_multistep_ancestral_cfg_pp
- gradient_estimation
- gradient_estimation_cfg_pp
- er_sde
- seeds_2
- seeds_3
- sa_solver
- sa_solver_pece
- ddim
- uni_pc
- uni_pc_bh2
scheduler
- simple
- sgm_uniform
- karras
- exponential
- ddim_uniform
- beta
- normal
- linear_quadratic
- kl_optimal
denoise_strength FLOAT
seed INT
face_selection INT
detection_confidence FLOAT
manual_rotation
- None
- 90° CW
- 90° CCW
- 180°
processing_resolution INT
enable_pre_upscale BOOLEAN
upscaler_model
- Fast 4x (Bicubic AA)
- Fast 4x (Lanczos)
- Fast 2x (Bicubic AA)
- Fast 2x (Lanczos)
crop_padding FLOAT
face_positive_prompt STRING
replace_positive_prompt BOOLEAN
face_negative_prompt STRING
replace_negative_prompt BOOLEAN
exclusions STRING
blend_softness INT
mask_expansion INT
sampling_mask_blur_size INT
sampling_mask_blur_strength FLOAT
enable_color_correction BOOLEAN
enable_segmentation BOOLEAN
enable_differential_diffusion BOOLEAN
enable_lightness_rescue BOOLEAN
enable_final_refinement BOOLEAN
offload_models_to_cpu BOOLEAN
image IMAGE
latent LATENT
clip CLIP
Outputs
IMAGE
IMAGE
IMAGE
MASK
Extension: Forbidden Vision
Custom face detection and segmentation for ComfyUI with automatic face fixing, intelligent color grading, and iterative refinement. Custom-trained models optimized for realistic, anime, and NSFW content.
Authored by luxdelux7
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.