ComfyUI Node
Draw Things Sampler
A ComfyUI node in DrawThings with 63 inputs and 1 output.
Draw Things Sampler
- model
- image
- mask
- lora
- control_net
- upscaler
- refiner
- hints
- IMAGE
◄settingsBasic►
◄serverlocalhost►
◄port7859►
◄use_tlstrue►
◄strength1.00►
◄seed0►
◄seed_modeScaleAlike►
◄width512►
◄height512►
◄steps20►
◄num_frames14►
◄cfg4.5►
◄cfg_zero_starfalse►
◄cfg_zero_star_init_steps0►
◄speed_uptrue►
◄guidance_embed4.5►
◄sampler_nameDPM++ 2M AYS►
◄stochastic_sampling_gamma0.30►
◄res_dpt_shifttrue►
◄shift1.00►
◄batch_size1►
◄fps5►
◄motion_scale127►
◄guiding_frame_noise0.02►
◄start_frame_guidance1.0►
◄causal_inference0►
◄causal_inference_pad0►
◄clip_skip1►
◄sharpness0.6►
◄mask_blur1.5►
◄mask_blur_outset0►
◄preserve_originaltrue►
◄high_res_fixfalse►
◄high_res_fix_start_width448►
◄high_res_fix_start_height448►
◄high_res_fix_strength0.70►
◄tiled_decodingfalse►
◄decoding_tile_width640►
◄decoding_tile_height640►
◄decoding_tile_overlap128►
◄tiled_diffusionfalse►
◄diffusion_tile_width512►
◄diffusion_tile_height512►
◄diffusion_tile_overlap64►
◄tea_cachefalse►
◄tea_cache_start5►
◄tea_cache_end2►
◄tea_cache_threshold0.20►
◄tea_cache_max_skip_steps3►
◄separate_clip_lfalse►
◄clip_l_text—►
◄separate_open_clip_gfalse►
◄open_clip_g_text—►
◄positive—►
◄negative—►
CategoryDrawThings
Inputs (63)
| Name | Type | Default | Description |
|---|---|---|---|
| settings | COMBO | Basic | 3 options: Basic, Advanced, All |
| server | STRING | localhost | The IP address of the Draw Things gRPC Server. |
| port | STRING | 7859 | The port that the Draw Things gRPC Server is listening on. |
| use_tls | BOOLEAN | true | — |
| model | DT_MODEL | The model used for denoising the input latent. | |
| strength | FLOAT | 1.000–1 | When generating from an image, a high value allows more artistic freedom from the original. 1.0 means no influence from the existing image (a.k.a. text to image). |
| seed | INT | 0-1–4294967295 | The random seed used for creating the noise. |
| seed_mode | COMBO | ScaleAlike | 4 options: Legacy, TorchCpuCompatible, ScaleAlike, NvidiaGpuCompatible |
| width | INT | 512128–8192 | — |
| height | INT | 512128–8192 | — |
| steps | INT | 201–150 | The number of steps used in the denoising process. |
| num_frames | INT | 141–201 | — |
| cfg | FLOAT | 4.50–50 | The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality. |
| cfg_zero_star | BOOLEAN | false | — |
| cfg_zero_star_init_steps | INT | 00–50 | — |
| speed_up | BOOLEAN | true | — |
| guidance_embed | FLOAT | 4.50–50 | — |
| sampler_name | COMBO | DPM++ 2M AYS | The algorithm used when sampling, this can affect the quality, speed, and style of the generated output. |
| stochastic_sampling_gamma | FLOAT | 0.300–1 | — |
| res_dpt_shift | BOOLEAN | true | — |
| shift | FLOAT | 1.000.1–16 | — |
| batch_size | INT | 11–4 | — |
| fps | INT | 51–30 | — |
| motion_scale | INT | 1270–255 | — |
| guiding_frame_noise | FLOAT | 0.020–1 | — |
| start_frame_guidance | FLOAT | 1.00–25 | — |
| causal_inference | INT | 00–129 | Set to 0 to disable causal inference |
| causal_inference_pad | INT | 00–129 | — |
| clip_skip | INT | 11–23 | — |
| sharpness | FLOAT | 0.60–30 | — |
| mask_blur | FLOAT | 1.50–50 | — |
| mask_blur_outset | INT | 0-100–1000 | — |
| preserve_original | BOOLEAN | true | — |
| high_res_fix | BOOLEAN | false | — |
| high_res_fix_start_width | INT | 448128–2048 | — |
| high_res_fix_start_height | INT | 448128–2048 | — |
| high_res_fix_strength | FLOAT | 0.700–1 | — |
| tiled_decoding | BOOLEAN | false | — |
| decoding_tile_width | INT | 640128–2048 | — |
| decoding_tile_height | INT | 640128–2048 | — |
| decoding_tile_overlap | INT | 12864–1024 | — |
| tiled_diffusion | BOOLEAN | false | — |
| diffusion_tile_width | INT | 512128–2048 | — |
| diffusion_tile_height | INT | 512128–2048 | — |
| diffusion_tile_overlap | INT | 6464–1024 | — |
| tea_cache | BOOLEAN | false | — |
| tea_cache_start | INT | 50–1000 | — |
| tea_cache_end | INT | 2-151–150 | A positive value corresponds to last step tea_cache should be appplied. Use a negative value to specify steps from the end+1. IE: -1 is the last step, -2 is the second to last step, and so on. |
| tea_cache_threshold | FLOAT | 0.200–1 | — |
| tea_cache_max_skip_steps | INT | 31–50 | — |
| separate_clip_l | BOOLEAN | false | — |
| clip_l_text | STRING | — | |
| separate_open_clip_g | BOOLEAN | false | — |
| open_clip_g_text | STRING | — | |
| imageopt | IMAGE | — | |
| maskopt | MASK | A black/white image where black areas will be kept and the rest will be regenerated according to your strength setting. | |
| positiveopt | STRING | The conditioning describing the attributes you want to include in the image. | |
| negativeopt | STRING | The conditioning describing the attributes you want to exclude from the image. | |
| loraopt | DT_LORA | — | |
| control_netopt | DT_CNET | — | |
| upscaleropt | DT_UPSCALER | — | |
| refineropt | DT_REFINER | — | |
| hintsopt | DT_HINTS | Hint images, or control inputs, are used with ControlNets and certain other models, like Kontext, to help guide the generation. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |