Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
11 shown of 34,873
Gender Slider
Don't let the Model or Lora push a gender on you. Male, female, and every point in between. You decide. This isn't to push any agenda, just giving you the tools to get the image you want, despite the biases that...
Bridal Style
This is a Style which brings out a beautiful bridal aesthetic. Simply call Style-Bridal in your prompt and your female characters will be ready for their wedding day!
HappyHorse video edit
Edit a source video with text instructions and a reference image using HappyHorse 1.0, and return one edited video. For a first run, upload a 3–15 second source clip and a reference image. Adapt the example instruction to identify the subject in your clip and explain how the reference should be used. The instructions also support appearance changes or style transfer. Both uploads are required in this Pipe. Choose 720P or 1080P and the desired aspect ratio. The provider describes output duration as 3–15 seconds, matching the input within that range; clips longer than 15 seconds are truncated. This Pipe has no duration or FPS control. Use seed -1 for a new random seed each run, or enter a fixed seed to control generation variation. Enable Watermark to request the provider's AI-generated mark. Under Video output, leave file type and codec on auto for a first run, or choose the available container and codec settings. These affect encoding of the returned video. Execution requires configured access to the HappyHorse partner API. The source video, reference image and editing instructions are sent to the provider, and generation uses a provider-priced API call.
Replace video background
Replace an uploaded video's background with a selected solid color using Bria, and return the processed video as a preview result. For a first run, upload your source video, leave Background color on Black, keep Seed at -1 and leave the advanced File type and Codec controls on auto. Run the Pipe to view the resulting video. Choose another background color to change the solid fill behind the foreground subject. Seed -1 requests a fresh re-run seed each run. A fixed seed does not make Bria's results reproducible: results remain non-deterministic regardless of seed. For explicit output encoding, enter auto, mp4, mkv or webm for File type, and auto, h264 or av1 for Codec. Explicit selections must be compatible with each other; keep both on auto unless you need a particular encoding. The Bria stage sends the uploaded video to an external provider and uses a paid provider operation. This Pipe offers solid backgrounds only, with no transparent-background mode. Audio preservation is not established by the supplied source evidence.
NegativeMutation
Original Hugging Face Repository Simply uploaded by me, all credit goes to . If you like this embedding, please consider taking the time to give the repository a like and browsing their other work on HuggingFace.
SD 3.5 Image Generator
Generate images from text prompts using Stable Diffusion 3.5. Describe your subject and scene in the positive prompt, and use the negative prompt for elements to exclude. Set the image width, height and batch size. Advanced sampling controls include seed, steps, guidance, sampler, scheduler and denoise strength. The model is fixed.
LTX-2.3 first and last frame video
Generate a video with audio between two endpoint images, guided by a motion and audio prompt, using the fixed LTX-2.3 distilled model. For a first run, upload both a first frame and a last frame. Replace the example prompt with the action and camera movement connecting your images, and include desired music, sound effects, or dialogue in the same prompt. Keep the defaults of 1280 × 720, approximately 5 seconds, 25 FPS, and endpoint strengths of 0.7. Run the tool and review the returned video with generated audio. Both images are required; there is no exposed silent-output mode or audio upload. Width and height resize both images, and the first resized image determines the video canvas. Use matching aspect ratios and compatible compositions to reduce unwanted cropping. Each image has independent advanced fitting and resampling settings: center fitting preserves aspect ratio by cropping, while disabled fitting stretches to the requested dimensions. Area resampling suits downscaling, lanczos suits upscaling, and nearest-exact suits hard pixel edges. Uploaded transparency is not retained because only the loaders' RGB image outputs are connected. Endpoint strengths independently control each image's conditioning influence. The first guide is fixed at the beginning and the last guide at the end; these guide positions are not exposed controls. Endpoint guidance does not guarantee exact copied frames. Advanced preprocessing controls apply compression independently to each resized image before conditioning; both default to 25 on a 0–100 scale. Use positive dimensions of at least 64 pixels. The downstream latent schema declares a sizing step of 32, although the retained source height is 720; exact spatial alignment behavior is not established by the supplied evidence. Duration is requested in positive whole seconds. FPS controls generation conditioning, audio timing, and playback; use 1–120. The graph requests duration × FPS + 1 frames for video and audio, and this count must stay at or below the audio latent limit of 1000. Temporal alignment can change the final duration. Larger canvases and longer clips require more memory and computation. Keep CFG at 1 for the first run. At this value, negative conditioning does not contribute through standard classifier-free guidance. When changing CFG, review the negative prompt's scene-specific exclusions and replace them to suit your images. Seed -1 randomizes each run; a fixed seed reuses the initial generation noise. Ancestral noise defaults to zero; its separate noise scale becomes relevant when ancestral noise is enabled. The advanced sampling schedule contains nine comma-separated noise levels defining eight intervals. Editing it changes the sampling trajectory and interval count; there is no independent steps control. Keep the supplied distilled-model schedule for a first run. Advanced output settings offer 8-bit or 10-bit video, container selection, and codec selection. Use 8-bit and automatic container and codec selection initially. The source notes that 10-bit can retain smoother gradients, but some players and downstream tools may not support it. Explicit container and codec choices must be compatible. Encoding choices do not disable generated audio.
Hunyuan Video 1.5 Image to Video
Animate an uploaded image into a silent video with Hunyuan Video 1.5. For a first run, upload a starting image and enter a motion prompt describing the subject's action, atmosphere and camera movement. Leave the negative prompt empty unless you want to discourage particular content or artifacts. Keep the initial settings of 1280 × 720, 121 frames, batch size 1 and 24 FPS to return a clip lasting about 5.04 seconds. The image feeds both starting-frame conditioning and a separate visual-reference encoder. Visual reference crop offers center or none and affects only that encoder; it does not set output dimensions. Uploaded alpha transparency is not preserved by this route. Width and height set generated dimensions in pixels. Frame count changes how many frames are generated; playback FPS changes their speed and duration without adding frames. Duration is frame count divided by FPS. The frame-count control advances in increments of four from one. Batch size controls latent initialization; the Pipe returns one video rather than separate clips for batch members. Advanced controls retain the source's sampling choices: 20 steps, simple scheduler, euler sampler, CFG 6, denoise 1 and sampling shift 7. Seed -1 selects fresh random noise; a fixed nonnegative seed reuses initial noise. Denoise changes the sampling schedule rather than directly specifying how much of the uploaded image to preserve. The optional sampling cache is bypassed by default and can be enabled with its saved reuse settings. Choose the returned video's container and codec in Video output. Encoding quality uses -1 for the transport default and affects compression rather than generation. Video bit depth defaults to 8; 10-bit may retain smoother gradients but has player and downstream compatibility limitations. This Pipe returns the base-video route. The source's disabled 1080p refinement branch is not included, and there is no audio input.
Seedream layer separation
Separate an uploaded image into requested visual layers with generated transparency. Upload a source image and describe which elements should belong together, such as a character, background, lettering, or decorative graphics. The connected image outputs are combined with their corresponding generated masks and returned as one image batch. For a first run, replace the example layer instruction with elements present in your image, keep output resolution at 1K, and leave Crop layers off. The instruction requests layer organization; it does not guarantee a fixed number of output images. Enable Crop layers to request cropped layers, or leave it off to request the uncropped layout for compositing. Output resolution offers auto, 1K, 1.5K, and 2K; independent width and height controls are unavailable. Prompt optimization offers the provider's standard and fast modes. Watermark enables the provider's watermark option. Seed -1 requests a fresh randomized seed on each run; a fixed seed is supplied to the provider without guaranteeing identical results. Transparency comes from the generated separation masks. The source image's alpha-mask output is not connected, so uploaded transparency is not preserved as an input mask. Results are returned through Sweet Tea's image output; this graph does not permanently save PNG files.
Grok image edit
Edit a source image with a written instruction using Grok. For a first run, upload one source image, describe the changes you want and the features to retain, and keep the supplied defaults: grok-imagine-image, 1K resolution, one result and request seed -1. The example instruction requests anime styling while retaining identity. The output returns the edited images. Model selects among grok-imagine-image, grok-imagine-image-quality and grok-imagine-image-pro. Resolution selects a 1K or 2K output request. Image count requests 1 to 10 edited results from the same reference and instruction. Request seed controls whether the editing request reruns. Keep -1 for randomization or change a nonnegative seed to trigger another request. Results remain nondeterministic even with a fixed seed. Aspect ratio remains automatic. The source allows manual aspect ratios only with multiple connected reference images, while this tool connects one. Increasing image count changes the number of results, not the number of references. A source image is required; this tool has no text-only mode, mask-based editing input or denoise-strength control. Uploaded alpha transparency is not preserved because only the loader's RGB image output is connected.
FLUX.2 dev image generation
Generate images from a text prompt using the fixed FLUX.2 dev model, with an optional Turbo LoRA mode. No source image is required, and there is no negative prompt input. For a first run, replace the example positive prompt with your subject, composition, lighting and style. Keep output and scheduler dimensions at 1024 × 1024, image count at 1, guidance at 4, sampler at Euler and Turbo mode disabled. Standard mode uses the separate Standard steps setting, initially 20. Run the Pipe to receive the generated image batch. Width and height set output dimensions in pixels and must be multiples of 16. Whenever you change them, set Scheduler width and Scheduler height to the same values: these independent fields control the noise schedule and are not synchronized automatically. Image count sets batch size; larger batches require more memory. Enable Turbo mode to select the fixed Turbo LoRA and Turbo steps together. Turbo steps defaults to 8. Each mode uses only its own step setting; enter an integer from 1 to 4096. Turbo strength affects only the Turbo model branch. Setting strength to 0 leaves Turbo steps selected; disable Turbo mode to return to Standard mode. Advanced controls include prompt guidance, seed, both step counts, Turbo strength and sampler. Seed -1 chooses fresh random noise each run; use a fixed seed when comparing settings. Sampler selection applies in both modes and can change the result at the same seed and step count. The fixed model stack uses flux2_dev_fp8mixed.safetensors in diffusion_models, mistral_3_small_flux2_bf16.safetensors in text_encoders, full_encoder_small_decoder.safetensors in vae, and Flux_2-Turbo-LoRA_comfyui.safetensors in loras. All four are marked MISSING_MODEL in the supplied dependency evidence; ensure they are available before running. Source-provided downloads are https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors, https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors, https://huggingface.co/black-forest-labs/FLUX.2-small-decoder/resolve/main/full_encoder_small_decoder.safetensors, and https://huggingface.co/ByteZSzn/Flux.2-Turbo-ComfyUI/resolve/main/Flux_2-Turbo-LoRA_comfyui.safetensors. Model files are fixed by this Pipe rather than selectable controls.
