Encuentra lo que necesita tu flujo.

PixelDiT image generator

Generate one image from text using the fixed PixelDiT 1300M model, Gemma text encoder, and pixel-space decoding. No source image is required. For a first run, replace the positive prompt with your subject, setting, composition, lighting, and desired appearance. Keep or edit the prefilled negative prompt to describe features to discourage. Start with the square, 1-megapixel default and the supplied sampling settings: 30 steps, CFG 4, er_sde sampler, simple scheduler, and denoise 1. Run the Pipe to obtain the generated image. Aspect ratio sets the image shape; megapixels sets the approximate total pixel count in millions. Width and height are calculated together. A square image at 1 MP is approximately 1024 × 1024. Prompt text such as “8k” does not set actual output resolution. Larger images require more resources. Advanced sampling controls include seed, steps, CFG, sampler, scheduler, and denoise. Seed -1 requests fresh randomization on each run; a fixed nonnegative seed reuses the noise initialization. Steps set the sampling step count. CFG controls prompt guidance; excessive values can harm the result. Sampler selects the sampling algorithm, while scheduler sets the progression of noise levels. Changing these controls can change the generated appearance. Keep denoise at 1 for full generation from the empty latent. Lower values sample a shorter noise range. This is text-to-image generation: there is no uploaded image to edit or preserve. Image count is fixed at one, and model selection is fixed. The execution environment needs pixeldit_1300m_1024px_bf16.safetensors, gemma_2_2b_it_elm_bf16.safetensors, and the Sweet Tea output nodes.

Recraft Crisp Upscale

Upload a source image and run to receive the Recraft Crisp Upscale result. Prepare a file no larger than 5 MB, with width and height each no larger than 2048 pixels, as specified by the source template. This tool has one fixed upscaling mode and exposes no prompt, scale factor or enhancement settings. Uploaded transparency is not preserved because only the image loader's RGB output reaches the upscaler. The image is sent to Recraft for processing through a paid provider call.

Not Just Another Pretty Face

Any resemblance to actual persons, living or dead, is purely coincidental. This work is a product of fiction and any similarities to real individuals are entirely unintentional.

TextualInversionSD 1.5

WanMove motion-guided image to video

Create a motion-guided video from an uploaded image, a scene-and-action prompt, and editable motion paths. For a first run, upload an image and replace the skiing example prompt with a description of its scene and desired action. Set path 1's start and end positions to guide the intended movement. Review paths 2 and 3 in Advanced: both are enabled by default, and each can be bypassed independently if unnecessary. Keep the initial 832 × 480 size, 81 frames and 16 FPS for an approximately five-second clip, and leave Turbo off to use the standard settings. The image is resized with Lanczos and center-cropped by default. The resized image supplies the start image and optional visual-reference encoding; its dimensions determine the video size. Use positive multiples of 16 when changing width or height. Uploaded transparency is not used, and the selected output has no connected audio. Each path creates a bundle of tracks. X runs from left (0) to right (1), and Y from top (0) to bottom (1) on that path's canvas. Curved path enables a Bezier control point defined by Curve X and Curve Y; the control point shapes the curve rather than specifying a required waypoint. Motion timing controls progression along the path. Track count sets the number of tracks, and Track spread sets their normalized spacing perpendicular to movement. Motion strength controls track-conditioning influence; paths guide generation rather than guaranteeing exact object trajectories. Video frame count and each path's frame count are independent. When changing length, update every enabled path to match. Video lengths follow 1 plus a multiple of 4, while path generators support at most 1024 frames. Frame rate changes playback duration, not the number of generated frames. Track canvases retain the source's 720 × 480 defaults, which differ from the 832 × 480 output. Canvas dimensions are independent controls: keep enabled path canvases consistent, and do not assume that changing output size updates them. Turbo mode selects the fixed Lightx2v LoRA together with its separate sampling settings. Standard defaults are 20 steps and CFG 6; Turbo defaults are 6 steps and CFG 1. LoRA strength affects only Turbo generation. The negative prompt applies in both modes; its supplied Chinese text lists unwanted artifacts and traits. Seed -1 randomizes the seed; use a fixed nonnegative seed to reuse it with otherwise matching settings. Sampler, scheduler, denoise and sampling shift remain available in Advanced. Keep Generation batch size at 1 for a single clip: the selected output assembles decoded images into one video rather than delivering separate files. Visual reference can be bypassed without removing the start image. Its center/none crop setting affects visual encoding and is separate from resize crop. Video encoding offers container, codec and CRF controls; auto container/codec and CRF -1 retain transport defaults. Bit depth defaults to 8; 10-bit may lack player support. The selected output is the generated video, without the source's disabled track-visualization diagnostic. The workflow uses fixed WanMove diffusion, UMT5 text-encoder, Wan 2.1 VAE, CLIP vision and Lightx2v LoRA assets identified in the source metadata. Those assets must be available to the runtime; this review does not establish execution results or generation speed.

Wan 2.11024x10248GB VRAM

ACE-Step1024x10248GB VRAM

Gemini image refinement and generation

Refine or edit an uploaded image with Gemini, or generate an image from a prompt, at a target resolution of 1K, 2K or 4K. For a first refinement run, upload a Source image, leave that stage enabled, and use the default prompt and 4K resolution. The prompt requests detail refinement while preserving text and composition. Replace it with specific editing instructions and describe what should remain unchanged. For text-only generation, bypass Source image and replace the editing prompt with a description of the image you want. Auto aspect ratio follows the reference image when supplied; choose an explicit ratio to specify the proportions when generating without a reference. Resolution selects the target output size; the source describes 2K and 4K as using Gemini's native upscaler. Model selects Gemini 3 Pro Image or Nano Banana 2 (Gemini 3.1 Flash Image). Seed -1 randomizes each run; a fixed seed requests best-effort repeatability, without guaranteeing identical results. System instructions set foundational behavior and default to prioritizing image creation. Response format requests IMAGE or IMAGE+TEXT, but this Pipe exposes only the generated image. Refinement is generative: text, textures and composition can change despite preservation instructions. Uploaded transparency is not preserved by the connected RGB image path. The generated image is returned through Sweet Tea's preview transport rather than a permanent SaveImage stage. Prompts and any reference image are sent to Gemini through a paid provider call.

Replace video background

Replace a video's background with a supplied image using Bria and receive one processed video. For a first run, upload the foreground video under Source video and a replacement image under Background image. Keep Background image enabled and leave File type and Codec on Auto, then run the Pipe. Background image is optional and bypassable. Bypassing it omits the replacement image; the supplied provider definition does not specify the resulting appearance. This Pipe has no replacement background video input. Uploaded image transparency is not carried through the connected RGB image output. Under Background replacement, Seed defaults to -1 to randomize on each run. Seed controls provider re-execution; results remain non-deterministic even with a fixed seed. Under Video output, File type offers Auto, MP4, MKV and WebM; Codec offers Auto, H.264 and AV1. Keep Auto for a first run, or choose a compatible container and codec together. The preserved hidden CRF control lacks documented semantics in the supplied evidence.

Subject and product composition

Generate a scene featuring a subject and product from two reference images using Gemini. Upload a subject image and a product image. In the scene prompt, image 1 means the subject and image 2 means the product. For a first run, keep the supplied prompt to request the subject holding the product with its logo visible, leave the other defaults in place, and run the Pipe. Edit the prompt to describe the interaction, setting, lighting, style and details to retain. Choose the output aspect ratio and resolution. Auto follows the reference aspect ratio; the product reference is resized and padded to match the subject image dimensions before both images are sent to Gemini. The 2K and 4K settings use Gemini's native upscaler. In Product reference preparation, padding selects white or black borders around the resized product, and interpolation selects its pixel resampling method. These controls affect the reference image rather than the generated scene background or final image size. Model selects either the supplied Gemini Pro image model or Nano Banana 2 (Gemini 3.1 Flash Image). Keep the supplied Generation instructions initially; edit them to change the provider's general behavior alongside the scene prompt. Provider response offers IMAGE or IMAGE+TEXT, but this Pipe returns only generated images through its image preview output; accompanying provider text is not returned. Use seed -1 for a new random seed each run. A fixed seed requests best-effort repeatability but does not guarantee identical results. Subject identity, product details and logo fidelity are requests rather than guarantees. Uploaded alpha masks are not connected, so uploaded transparency is not preserved through the reference path. Both reference images and the generation instructions are sent to Gemini for a provider-priced generation request.

Image grid

Combine two to four uploaded images into one collage. With all four inputs enabled and the default directions, the first pair forms the top row and the second pair forms the bottom row. For a first run, upload all four images and keep the defaults for a 2048 × 2048 output without gaps. Top-left and bottom-left images are required. Top-right and bottom-right are independently optional: disable their input stages when omitting them. With default directions, disabling both right inputs produces two images stacked vertically; disabling only one produces rows with different image counts. Open the advanced layout stages to change each pair's direction and the direction used to join the completed pairs. Each direction places the second image or pair relative to the first: right, down, left or up. Input position labels describe the default grid; changing directions changes their final positions. Size matching is enabled independently for each pair and for the final assembly. Gap widths and colors are also independent at those three joins. Gap widths are measured in pixels before the final resize, so resizing changes their final displayed size. A pair's direction, size matching and gap controls have no effect when its optional second image is disabled. Set the final width and height in pixels. Center cropping preserves proportions but can cut off collage content when its aspect ratio differs from the requested dimensions. Select disabled cropping to stretch instead, or set one dimension to zero to calculate it from the other while preserving aspect ratio. Keep at least one dimension greater than zero. Resampling controls pixel interpolation during this final resize. The result is one image returned through the Pipe output. Uploaded alpha masks are not connected, so uploaded transparency is not preserved.

Seedream 4 reference image generation

Create or edit images with Seedream 4 from one reference image and a text prompt, with an optional related-image mode. For a first run, upload your reference image and replace the example prompt with the result or edits you want. Describe which reference details should remain. Keep Output size at 2048x2048 (1:1) and Related images disabled to request one square image, then run the Pipe. This workflow requires one upload and does not provide additional reference inputs. Uploaded transparency is not preserved as an alpha mask. Choose an output size preset, or select Custom to use Width and Height in pixels. Custom width accepts even values from 1024 to 6240; custom height accepts even values from 1024 to 4992. These fields affect generation only when Custom is selected. For related scenes or variations, describe them in the prompt, set Related images to auto, and increase Maximum images. The model decides how many images to generate; Maximum images is a ceiling rather than an exact count. Input and generated images together cannot exceed 15, so with this one reference image keep Maximum images at 14 or below. Seed -1 randomizes each run; a fixed seed controls generation randomization. Enable Watermark to add an “AI generated” mark. Fail on partial results is enabled by default and aborts when requested images are missing or return an error; disable it to accept available partial results. Generation sends your reference image and prompt to ByteDance and uses a paid provider call.

ACE-Step song generator

Generate an MP3 song from music style tags and lyrics. Style tags describe the genre, instruments, vocals, tempo, and mood. Lyrics provide the sung text, with lyric strength available for tuning their influence. Choose the duration and number of variations; the default duration is 120 seconds. Advanced controls expose sampling, latent guidance, and MP3 encoding quality. Negative conditioning is automatically zeroed. For multilingual lyrics, the source notes require manual romanization and language markers such as [zh], [ja], or [ko].

UpscalingWan 2.21024x10248GB VRAM

Edit a photo and animate it

Edit a reference photo with FLUX Kontext, then animate the edited image with Wan 2.2. Each run returns an animated video and an edited starting-image preview. For a first run, upload a photo with a clearly visible subject. Replace or adapt Image prompt to describe the appearance, setting and visual style you want: the saved example requests a navy business suit in a modern office. Keep Motion prompt at its saved small-movement request, or describe the subject movement and camera behavior you want. Then run the Pipe and review both outputs. Image prompt controls the Kontext edit; Motion prompt controls the subsequent animation. In the advanced section, Video negative prompt discourages unwanted video content and movement. Its saved text combines Chinese visual-quality exclusions with English exclusions for fast movement, mouth movement, talking, visible teeth and camera zooms. Remove conflicting exclusions when requesting those actions. The negative prompt does not affect the image edit. Every run performs the image edit before animation. This interface has no separate animation-only or image-only mode. Video dimensions and seed come from the image-generation pipeline. Size, seed, duration, frame rate, sampling, Lightning acceleration, LoRA and enhancement settings remain at their saved workflow configurations and cannot be adjusted here. The workflow uses ComfyUI-UmeAiRT-Toolkit with the FLUX/Kontext and WAN_2.2/I2V model bundles. The broader source README describes additional configurations and toggles; those are not selectable modes in this Pipe.

HunyuanVideo1024x10248GB VRAM

Capybara: Image to Video

Create one silent video from an uploaded image using the fixed Capybara v0.1 model. The image supplies both the resized start frame and a separate visual reference. For a first run, upload an image and replace the example positive prompt with scene details, subject motion and camera movement appropriate to your image. Keep 640 × 640 pixels, 81 frames and 24 FPS for approximately 3.4 seconds of playback. Use positive dimensions divisible by 16 and frame counts of 4n + 1, such as 49 or 81. Larger dimensions and more frames increase generation work. The start image is resized to fit the output dimensions and padded when its aspect ratio differs. Padding color selects white or black borders; resize interpolation controls resampling. Reference crop selects center or none for the separate visual-reference encoding and does not change start-frame padding. Only the uploaded RGB image is connected; uploaded transparency is not preserved. Advanced controls include the negative prompt, seed, CFG, sampling settings and image preparation. Seed -1 randomizes each run; a fixed nonnegative seed reuses the initial noise. CFG controls the contrast between positive and negative conditioning. Begin with the existing sampling defaults: 20 steps, simple scheduler, Euler sampler, denoise 1 and model shift 7. Denoise changes the sampling schedule rather than directly controlling source-image preservation. Model shift changes the sampling model's noise-time behavior. FPS changes playback duration without changing the generated frame count. Choose 8-bit video for compatibility or 10-bit for smoother gradients where encoding and playback support it. File type and codec control the returned video's container and encoding; begin with auto for both, and use compatible combinations when selecting them manually. One video is returned through Sweet Tea's preview output, without a server-side save stage. No audio is connected. Batch size remains one in the normal interface because decoded frames are assembled into a single video rather than exported as separate variation clips.

Create a miniature architectural scene

Create an image of a miniature architectural model in a setting you describe. Upload a building photo or rendering; this Pipe generates a conceptual blueprint, then supplies both that blueprint and the original building image to the scene generator. It returns only the final scene image. Use the separate architectural blueprint tool for a standalone sheet. For a first run, upload your building image, edit the scene prompt to match its appearance, and keep the default 16:9 framing and 1K resolution. The supplied scene prompt requests a purple house on an architect’s desk with a blueprint displayed behind it. Describe the model, materials, surroundings, lighting, and camera view you want. Mention the blueprint in the scene prompt if you want it depicted. Scene aspect ratio and resolution control the final image. Auto framing asks the provider to match an input reference. Under Blueprint reference, edit the drawing views, annotations, and sheet layout for the intermediate image. Blueprint framing and resolution are independent of the final scene settings, but changes to that reference can influence the final composition. Both generation stages run on every request. Each stage has an independent model selector offering gemini-3-pro-image-preview and Nano Banana 2 (Gemini 3.1 Flash Image). Optional generation instructions guide each generator’s foundational behavior separately from its visual prompt; retain their defaults for a first run. Resolution choices are 1K, 2K, and 4K, with the provider’s native upscaler used for 2K and 4K. Each seed defaults to -1, which randomizes that stage on every run. Fixed seeds request best-effort consistency rather than identical results. Fixing only the scene seed does not stabilize an independently randomized blueprint reference. The blueprint and miniature scene are generated concept imagery. Geometry, dimensions, structural details, and annotations may be invented; use them for presentation rather than measured construction documentation. Higher resolution does not establish architectural accuracy.

Detail Tweaker LoRA (细节调整LoRA)

This is a LoRA for enhancing/diminishing detail while keeping the overall style/character; it works well with all kinds of base models (incl anime & realistic models)/style LoRA/character LoRA, etc.

Animate an image with Vidu Q1

Turn a starting image and motion prompt into a five-second, 1080p video with Vidu Q1. For a first run, upload your starting image, replace the example leopard prompt with action and camera instructions suited to that image, and leave Motion amount on auto. Generation uses the Vidu partner API and requires configured API access and sufficient credits. Motion amount requests the amplitude of object movement: auto lets the service choose, while small, medium, and large express an explicit preference. Describe camera movement and atmosphere in the prompt. Duration is fixed at five seconds and resolution at 1080p in this workflow; frame-rate wording in the prompt does not configure actual FPS. Seed -1 randomizes each run. A positive integer supplies a fixed generation seed without guaranteeing identical results; the provider treats 0 as random as well. The Video output advanced section offers automatic or explicit container and codec selection, plus CRF encoding quality. Leave File type and Codec on auto and Quality (CRF) on -1 for automatic settings. These controls affect output encoding rather than the generated action. The result is returned as a video through Sweet Tea.

Vidu Q11024x10248GB VRAM

LTX-Video 2.31024x10248GB VRAM

Image to video with generated audio

Animate a starting image into a video with generated sound using prompted motion, a base pass, a fixed 2× latent upscale, and refinement. Upload a starting image and enter a prompt describing the scene, action, camera motion, and desired sounds or dialogue. The model, distilled LoRA, and upscaler are fixed. For a first run, retain the 720-pixel output long edge, 97 video frames, 97 audio frames, and 20 fps for conditioning, audio timing, and export. Keep MP4 file type and H.264 codec. The video plays for approximately 4.85 seconds. Output proportions follow the uploaded image; latent sizing can round dimensions. The long edge means the larger dimension, not a guaranteed height. Uploaded transparency is not retained through the RGB image path. When changing duration, set video and audio frame counts together. Video length uses an 8n+1 pattern, such as 97 or 121 frames. Keep conditioning, audio, and export frame rates equal, using a positive whole-number rate within all three fields' ranges. These independent controls do not update one another. Changing only export fps changes video playback duration without changing generated audio timing. Keep both batch sizes at 1 for the first run; if adjusting them, keep them equal. Advanced image guidance offers independent base and refinement strengths and switches to skip either image injection. A strength has no effect when that pass's injection is skipped. Skipping refinement image conditioning retains the upscaled base result and still runs refinement. With both injections skipped, generation is prompt-driven, but the upload remains required for aspect ratio and sizing. Reference resize and compression affect conditioning preparation rather than saved-video dimensions or encoding. Advanced sampling offers a shared seed and sampler, separate CFG values and noise schedules for each pass, and independent model and text-encoder strengths for the fixed LoRA. Retain source defaults initially. Seed -1 randomizes each run; a fixed nonnegative seed reuses noise initialization. The negative prompt feeds both passes, but standard CFG at the default value of 1 gives it no negative-guidance contribution. The base schedule contains eight intervals and the refinement schedule three; changing their comma-separated values changes sampling steps and noise levels. File type and codec are separate export controls. Select a compatible combination that supports audio to retain generated sound; GIF cannot carry sound. Export also exposes CRF, bitrate in Mbps, pixel format, bit depth, and color-space settings. Retain their defaults for the first run and keep codec, pixel format, and bit depth compatible when changing them. Selecting HDR does not establish HDR information in generated frames. Advanced decoding controls spatial tile size and overlap in pixels and temporal chunk size and overlap in frames; keep overlaps smaller than their corresponding sizes.

ModeloCivitai

Hades style textual inversion

Textual Inversion trained on art from the Hades game, tested on Anything V3 model. Put this TI in the embeddings folder, type "Hades-8500" in prompt to activate. Also I recommend to use words "realistic", "cartoon",...

TextualInversionSD 1.5