Encontre o que você precisa para seu fluxo de trabalho.

ComfyUI CivitAI + Hugging Face Downloader

ComfyUI-BroadcastResolutions

A drop-in custom ComfyUI node suite built for video editors, motion designers, and creators to force AI-generated video onto real broadcast and social delivery standards without manual dimension math or messy canvas...

Vidu Q1 text to video: mechanisms and practical controls

Request one five-second 1080p video from text, choose framing and object movement, and handle the retained seed-default conflict safely.

Image levels

Create an image with adjusted black and white points and midtones from an uploaded source image. For a first run, upload your image and run with the saved settings: RGB, Input black 85, Input white 255, Gamma 4.33, Output black 36 and Output white 201. These settings apply a stylized adjustment rather than a neutral preview. For no levels adjustment, use input endpoints 0 and 255, Gamma 1, and output endpoints 0 and 255, then change a control and run again. Choose RGB to apply the same settings to all three channels, or R, G or B to adjust only that channel while leaving the other two unchanged. If Channel appears as a text field, enter these exact names. All black and white points use a 0 to 255 scale. Input black and Input white define the range that is normalized before gamma adjustment; values outside that range are clipped to its endpoints. Keep Input white greater than Input black. Clipping cannot recover detail outside the selected range. Gamma is unitless and must be positive; do not use 0 because the shader divides by it. The source describes 0.01 to 9.99 as its intended range. Gamma 1 adds no midtone adjustment. When Output white is above Output black, gamma above 1 brightens midtones and gamma below 1 darkens them. Advanced controls set the output endpoints after gamma adjustment. Raising Output black lifts the dark endpoint; lowering Output white dims the bright endpoint. Reversing these endpoints reverses the tonal mapping, while equal endpoints produce a constant value in the selected channels. Output dimensions follow the source image. Uploaded transparency is not preserved because the image loader's separate alpha mask is unused. This output applies only levels; the other image adjustments in this family are separate tools.

ZI Roxanne McKee (vrtlRoxanneMcKee).safetensors

Character Change (♀) - BansheeCh - Cursed to haunt the night

At the lost of someone important, your waifu now screams with grief...

ZI Sophie Turner (vrtlSophieTurner).safetensors

ZI Ella Purnell (vrtlEllaPurnell).safetensors

ZI Rihanna (vrtlRihanna).safetensors

【FLUX】INPAINT — v5.0b

New simple version, civitai metadata not include.

S0123

sai-nc-community

Bianca Brunette

This LoRA does not depict a real person; it is a fictional creation.

App Icon designer

→ Get it now for much cheaper prices, skip the wait:

McLaren Senna

Weight 1 is good, if you want you can go lower weighting no problem

Timesformer Base Finetuned K400 Finetuned Snapdata Short Classification Sample Rate32

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.9266 Accuracy: 0.6862 0 Precision: 0.6305 0...

Izumi Shimomura - Ajin - COMMISSION

izumi shimomura, short hair, black hair, (black eyes:1.5),

WaveSpeed image upscale

Upscale an uploaded image to a 2K, 4K, or 8K provider preset with SeedVR2 or Ultimate through WaveSpeed. For a first run, upload your source image, leave the model at SeedVR2 and target resolution at 4K, then run to view the returned upscaled image. The source image is required; no bundled example image is needed. Choose SeedVR2 or Ultimate to change the upscaling model. Both use the same target-resolution control. To compare their results, run each model with the same source image and resolution preset. The resolution choices are provider presets rather than explicit pixel width and height settings. This operation sends your image to WaveSpeed and uses a paid provider call. The workflow uses only the loaded RGB image; uploaded alpha transparency is not preserved.

ZI Genevieve Hannelius (vrtlGenevieveHannelius).safetensors

Reduce memory at the tiled VAE decode stage

For an out-of-memory failure at VAEDecodeTiled node 109 in the selected LTX-2 recipe, try the published smaller_decode_tiles adaptation and inspect the resulting video for seams. This changes spatial VAE decoding only; no measured memory reduction or whole-machine fit is established.

DALL·E 2 image generation: mechanisms and practical controls

Make a square-image preview batch from one prompt, configure the real size and count inputs, and understand what this exact recipe does not provide.