ComfyUI Node: JLC CaptionForge Qwen Caption
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
Captioning/CaptionForge/Captioning Nodes
Inputs
model
- Qwen2.5-VL-3B-Instruct
- Qwen2.5-VL-7B-Instruct
- Qwen2.5-VL-3B-Instruct-Unredacted-MAX
- Qwen2.5-VL-7B-Captioner-Relaxed
- Qwen2.5-VL-7B-NSFW-Caption-V3-abliterated
qwen_quantization
- Default
- Balanced (8-bit)
keep_loaded BOOLEAN
caption_template_mode BOOLEAN
caption_type
- Descriptive
- Straightforward
- LoRA Literal
- Stable Diffusion Prompt
- Taggy
- Dataset Audit
- Style Focus
- SFW Character Caption
caption_length
- any
- very short
- short
- medium-length
- long
- very long
- 20
- 30
- 40
- 50
- 60
- 70
- 80
- 90
- 100
- 110
- 120
- 130
- 140
- 150
- 160
- 170
- 180
- 190
- 200
- 210
- 220
- 230
- 240
- 250
- 260
custom_prompt_mode BOOLEAN
prompt_preset
- default_literal
- dense_lora_literal
- concise_literal
system_prompt STRING
custom_prompt STRING
max_new_tokens INT
temperature FLOAT
top_p FLOAT
top_k INT
repetition_penalty FLOAT
max_size INT
forbidden_phrases STRING
replace_pairs STRING
download_probe_only BOOLEAN
image IMAGE
pipeline_plan CAPTIONFORGE_PIPELINE_PLAN
template_options CAPTIONFORGE_EXTRA_OPTIONS
seed INT
Outputs
IMAGE
CAPTIONFORGE_PIPELINE_PLAN
CAPTIONFORGE_EXTRA_OPTIONS
STRING
STRING
Extension: CaptionForge
A model-agnostic captioning framework for ComfyUI designed to generate cleaner, more consistent, auditable captions for LoRA dataset preparation through structured comparison, repeated observation, and consensus-based refinement.
Authored by Damkohler
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.