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
19 shown of 41,762
Mage-Flow image edit
Create edited images from one uploaded reference and written instructions using the fixed Mage-Flow-Edit model. Upload your source image, then describe what to keep and what to change. An instruction such as “Keep the subject and pose; replace the background with a grassy prairie” is a starting point. Preservation requests guide generation but do not guarantee unchanged pixels. For a first run, leave Resize reference enabled at 1 megapixel, Match reference size enabled, Number of results at 1, and sampling at 30 steps with instruction guidance 5. Leave Negative prompt blank unless you want to describe unwanted content or visual traits. Run the Pipe to receive the edited image results. Reference resizing retains the reference aspect ratio and aligns dimensions to multiples of 16. When Match reference size is enabled, output dimensions follow this processed reference, so Reference megapixels also affects output size. Turning Resize reference off passes the original image dimensions through. Turning Match reference size off uses Width and Height instead; reference preprocessing remains independent. Use positive manual dimensions divisible by 16. With resizing off and size matching on, use a source image whose dimensions are divisible by 16. Advanced controls include reference pixel area and interpolation, seed, sampling steps, instruction guidance, sampler, scheduler, and denoising amount. Seed -1 selects fresh randomization for each run; a fixed seed helps compare settings using the same sampling seed. The source sampling defaults are Euler, Simple, and denoising amount 1. Denoising amount acts on the edit encoder's latent output and is not established as a source-image preservation strength. This Pipe accepts one reference image and returns the requested number of edited images. It has no mask-based edit boundary, and uploaded transparency is not preserved: only the loader's IMAGE output is connected.
Style Swirl Magic
This is my fifth Textual Inversion, called Style-SwirlMagic. This model was trained on a single image using DreamArtist. As the name suggests, it adds magical swirls to images, making it a great tool for creating RPG...
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.
Swap a product in a character photo
Create an edited photo that replaces the product a person or character is holding with a product from a second photo. Upload the subject photo as image 1 and a clear replacement product photo as image 2. The product reference is resized and padded to the subject photo’s dimensions, then both images are sent to Gemini in that order. This uses a paid Gemini provider call and sends both images and the instructions to that provider. The generated image is returned for preview; this output transport does not permanently save it. For a first run, keep the supplied swap instructions, automatic aspect ratio, 2K resolution and default Gemini model. Add instructions about the subject, pose, lighting, background or product details you want retained. Model selection offers gemini-3-pro-image-preview and Nano Banana 2 (Gemini 3.1 Flash Image). Automatic aspect ratio follows the subject image; an explicit ratio requests a different output shape. Resolution offers 1K, 2K and 4K; 2K and 4K use the provider’s native upscaler. Reference preparation provides advanced white or black padding and resampling controls for the product reference. System instructions control Gemini’s foundational behavior; keep the image-generation directive and put the specific edit in Swap instructions. Seed -1 randomizes each run. A fixed seed requests best-effort consistency and does not guarantee identical results. IMAGE requests image-only generation; IMAGE+TEXT also requests accompanying text, but only the image is returned by this Pipe. This is a generative edit rather than a masked paste. Inspect the result for changes to hands, packaging, lettering and surrounding details. Uploaded alpha transparency is not preserved through the connected RGB image paths.
MiniMax H3 reference images to video
Generate a video with generated audio from two reference images and a scene prompt. For a first run, upload both images, replace the example story, and keep the five-second duration and default sampling settings. Identify the uploads as <Picture 1> and <Picture 2> in the prompt and explain what each contributes. Describe the action, camera movement, dialogue, music, and sound effects you want. The images guide generation; they are not guaranteed first and last frames. No uploaded audio or video reference is connected, so do not use an <Audio 1> tag. Output dimensions are fixed by the source's 16:9, 0.4-megapixel size configuration, approximately 864 × 480. Playback is fixed at 24 FPS. Requested seconds are converted to frames and adjusted to supported counts spaced 17 frames apart, starting at five frames. A five-second request produces 124 frames, approximately 5.17 seconds. The result returns video frames and generated audio together as one video. Advanced controls include reference detail, seed, sampling steps, scheduler, sampler, and denoise. Reference detail match scales references to the output resolution; max retains more reference detail, up to a 2048-pixel short edge according to the source notes, with increased sampling cost. Seed -1 requests a new random variation; a fixed seed reuses the initial noise. Start with 20 steps, res_multistep sampling, simple scheduling, and denoise 1. The source notes suggest beta or normal scheduling for reference-heavy prompts. Longer duration and more steps increase processing work. For delivery, leave format and codec on auto initially. Explicit container choices are mp4, mkv, and webm; codec choices are h264 and av1. Choose compatible combinations for your intended player. The default 8-bit output offers broad compatibility; 10-bit can retain smoother gradients but requires compatible encoding and playback.
Illustrious text to image with optional finishing
Generate an image from text using the fixed waiNSFWIllustrious_v130.safetensors checkpoint, with three optional LoRAs, tiled enlargement and automatic subject detailing. No uploaded image is required; the selected result is the saved image after all enabled stages. For a first run, replace the positive prompt with your subject, composition, lighting and style, review the negative prompt, and keep the 1024 × 1024 base size and sampling defaults. The supplied prompt is an example, including score tags and BREAK; prompt conventions depend on the checkpoint. Seed -1 selects a new random seed each run. Use a fixed seed when comparing settings. Width and Height set the base dimensions before enlargement. The advanced sections contain optional capabilities and their tuning controls. All three LoRA slots start disabled. For each slot you want to use, choose a compatible installed LoRA, enable that slot and set its strength. Slots are independent and can be combined. Upscaling starts disabled. Enable it to enlarge the newly generated image before detailing. The default factor of 2 doubles both dimensions: 1024 × 1024 becomes 2048 × 2048. Upscale denoise controls how much the enlargement may reinterpret the image. Tile controls configure processing and blending; seam correction starts at None, and seam controls apply when a correction mode is selected. Tiled decode is also available. Separate upscale steps, guidance, sampler and scheduler controls retain their source defaults; the supplied evidence does not define override or sentinel behavior, including steps=0 and the Pipeline selections. Prompt cleanup is enabled, but the source does not specify which prompt elements it changes. Subject detailing starts enabled with subject=face and denoise=0.5. It runs after generation and any upscaling. Disable it to keep the image without this additional refinement. The source describes face or body detailing; supported subject names depend on the installed Toolkit. Detail denoise controls how much detected regions may change. Low-level detection, crop, mask and sizing controls remain available, but their exact units and semantics are not documented in the supplied evidence. Keep their source defaults for a first run, especially the unusual numeric noise_mask, boolean guide_size and bbox_threshold=1024 fields. Optional-stage controls matter only when their stage is enabled. The checkpoint and baked VAE are fixed; CLIP skip remains adjustable. This Pipe always generates an image upstream and does not accept an existing image for standalone upscaling or detailing. The runtime requires ComfyUI-UmeAiRT-Toolkit and waiNSFWIllustrious_v130.safetensors. The optional upscaler uses 4x_NMKD-Siax_200k.pth; optional LoRAs must also be installed. The source says subject detailing uses detector and segmentation resources downloaded automatically by the Toolkit. Resource inventory currently marks the Toolkit, checkpoint and upscaler unresolved, and the supplied evidence does not verify those automatic downloads.
CyberRealistic Negative - SD 1.5
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
Seedream 4.5 image edit and generation
Edit a reference image or generate images from text using Seedream 4.5. For a first run, upload one source image, keep the Source image stage enabled, and describe the changes you want and the features to retain. The supplied example requests anime styling while retaining identity. Keep the defaults: 2048 × 2048 pixels, Related image generation disabled, seed -1 for randomization, watermark off and Require all requested images enabled. The output returns generated images. For text-only generation, disable the Source image stage and replace the editing example with a complete scene description. An upload is required while that stage is enabled. This tool uses the fixed seedream-4-5-251128 model. Output size determines the requested dimensions. Set it to Custom to use Custom width and Custom height, measured in pixels. Width accepts 1024–6240 and height accepts 1024–4992, both in increments of 2. These fields have no effect with other size selections. Related image generation set to disabled generates one image. Auto lets the model decide whether to generate a related set, such as story scenes or character variations. Describe the intended set in the instruction and increase Maximum images above 1 to permit multiple results. Maximum images is an upper limit, not a guaranteed count. Input and generated images together cannot exceed 15, so request at most 14 generated images with the source enabled or 15 with it disabled. Seed -1 selects randomization; a nonnegative seed sets the generation seed without a guarantee of identical results. AI watermark adds an “AI generated” watermark. Require all requested images aborts execution if any requested images are missing or return an error; disable it to allow partial results. This tool connects one RGB reference image and provides no mask-based editing input, multi-reference batching stage or denoise-strength control. Uploaded alpha transparency is not preserved because the loader's separate alpha-mask output is not connected.
Reimagine an image with Grok and refinement
Generate an upscaled, refined reinterpretation of a reference image with Grok and Z-Image Turbo. Upload a reference image and set the style direction and detail instructions. QwenVL describes the reference; your style direction, that caption and your detail instructions form one positive prompt used by both generation and refinement. The uploaded image reaches Grok through its caption only, so identity, layout and details may change. For a first run, replace the fashion and mossy-rock prompt text with instructions for your subject. Keep one image, square aspect ratio, 1K generation resolution, 1 base megapixel, post-upscale scale 0.5 and refinement strength 0.4. The result is the refined image batch. Prompt phrases such as “8k resolution” do not set actual output dimensions. Choose the Grok generation model from the available image, quality and pro variants. Aspect ratio sets the generated composition's proportions, and image count selects 1–10 images that each continue through upscaling and refinement. Generation resolution selects 1K or 2K for the initial Grok image; the later sizing controls determine refinement dimensions. The local Z-Image Turbo refinement model and RealESRGAN 4× upscaler remain fixed. Sizing first fits each generated image to the base megapixel budget, applies the fixed 4× upscaler, then multiplies width and height by the post-upscale scale before refinement. At 1 base megapixel and scale 0.5, final area is approximately 4 megapixels, with twice the base image's width and height, subject to pixel rounding. This is not necessarily twice the upload or Grok output. Scale 1 retains the full 4× base dimensions. Increasing either sizing control increases refinement work. Base and final resize methods choose interpolation at their respective resizing stages. Lower refinement strength retains more of the generated image; higher values permit larger changes guided by the shared positive prompt. Refinement steps, CFG, sampler and scheduler adjust local sampling. The negative prompt applies only to refinement, and its influence depends on CFG; the supplied CFG default is 1. Advanced sampling shift changes the refinement noise schedule and defaults to 3. Generation and refinement always run; there is no standalone upscale or refinement mode. Uploaded transparency is not preserved. Grok requires access to its provider service and remains nondeterministic regardless of its re-run seed. Use -1 for a fresh random seed value each run. The separate refinement seed controls local sampling noise; fixing it does not make the upstream Grok image reproducible.
Hue and saturation
Create a color-adjusted or single-hue colorized image from an uploaded source image. For a first run, upload your image and run with the saved settings: Master, HSL, Hue 3.9, Saturation 0 and Lightness or brightness 0. This applies a small hue shift. For an unchanged starting preview, set Hue to 0 as well, then change a control and run again. Choose Master to adjust all colors, or Reds, Yellows, Greens, Cyans, Blues or Magentas to target an existing hue range. These ranges are based on pixel color, not objects or manually selected regions, and leave grayscale pixels unchanged. If a mode control appears as a text field, enter the exact choice name. Hue shifts colors by -180 to 180 degrees. Saturation uses a unitless -100 to 100 scale: negative values reduce saturation, positive values increase it, and 0 adds no adjustment. Lightness or brightness also uses -100 to 100: negative darkens, positive brightens, and 0 adds no adjustment. The three adjustments combine in one output. In advanced controls, HSL adjusts saturation and lightness; HSB/HSV adjusts saturation and brightness. Color range overlap feathers individual hue ranges into neighboring colors, with higher values extending the affected range. The saved overlap is 50. Use a value above 0 through 100: exactly 0 makes the shader's feather calculation undefined. Overlap is ignored in Master and Colorize. Choose Colorize for a single-hue treatment using source luminance as the starting lightness. Hue becomes the target hue: 0 is red, 60 yellow, 120 green, ±180 cyan, -120 blue and -60 magenta. Set Saturation above 0 through 100 to add color; 0 produces grayscale, and negative saturation values are clamped to 0. Lightness or brightness adjusts HSL lightness in this mode. Colorize always uses HSL and ignores both Color space and overlap. Strong saturation or tonal adjustments can flatten color or tonal detail. 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 hue, saturation and the associated tonal adjustment or Colorize treatment; the other effects in this family are separate tools.
Wan 2.1 trajectory-guided video
Produces a silent video from a starting image, a motion prompt and point trajectories using the fixed Wan 2.1 ATI model. For a first run, upload your starting image and write a positive prompt describing its subject, intended action and camera movement. Review the negative prompt, whose source default is a Chinese-language exclusion list. Annotate motion paths for that same image with the source-recommended Trajectory Annotation Tool at https://comfyui-wiki.github.io/Trajectory-Annotation-Tool/ and paste its exported JSON into Trajectory JSON. The prompt and trajectory fields start empty because the source examples describe a particular image. Both must be supplied for your composition. Trajectory JSON is an outer array of tracks, each containing an ordered sequence of objects with numeric x and y coordinates. Use the annotation tool's export; the supplied evidence does not establish how arbitrary track lengths are resampled. Check trajectory alignment whenever you change the image composition or output dimensions. Initially retain 720 × 480 pixels, 81 frames, 16 FPS, 20 steps and CFG 3, giving approximately 5.1 seconds of playback. Width and height use multiples of 16; frame counts follow 4n + 1. More frames change the generated sequence length. FPS changes playback timing without generating additional frames. Image guidance optionally adds visual conditioning from the same uploaded image. Disabling it leaves the required starting-image and trajectory conditioning in place. Guidance crop affects only this optional visual conditioning and has no effect when image guidance is disabled. Sampling controls include seed, steps, CFG, sampler, scheduler and denoise. Seed -1 requests fresh random noise; a fixed seed reuses sampling noise. Denoise is not a direct source-image preservation slider because the video latent comes from the conditioning stage. Start with the supplied sampling defaults, including denoise 1 and sampling shift near 8. Keep batch size 1 for the documented single-video use. Trajectory temperature and top-k remain available, but their detailed effects are not documented in the supplied source evidence; initially retain 220 and 10. Video playback controls set FPS and bit depth. Start with 8-bit; 10-bit requires compatible encoding and playback. Video encoding controls select the output container, codec and CRF quality setting; initially retain auto, auto and -1. These settings affect delivery rather than the generated motion. The model and supporting encoders are fixed, and this workflow has no audio input.
Anima depth-guided illustration
Upload a reference image with the spatial layout you want to guide, then describe the new scene and style in the positive prompt. The reference is resized, Depth Anything 3 estimates its depth, and Anima generates a fresh image using that depth as guidance. Outputs include the generated image batch and the grayscale depth preview. For a first run, keep Output size at 1 megapixel, Depth strength at 1, and Turbo mode off. Output dimensions are derived from the depth preview rather than independent width and height fields. The source image supplies spatial guidance, not an encoded starting image: this tool does not preserve its exact colors, texture, identity, or transparency. Turbo mode selects the fixed Anima Turbo LoRA and switches to its separate sampling settings: 8 steps and CFG 1 by default, versus 30 steps and CFG 4 in standard mode. Each mode's steps and CFG remain independently tunable. Turbo LoRA strength only matters when Turbo mode is enabled. Adjust Depth strength to change the influence of the reference layout. Depth guidance start and end specify fractions of the sampling process and should remain ordered from start to end. Depth normalization and sky clipping change the map used both for the preview and generation. Keep the renderer on grayscale depth and the estimator in mono mode for the fixed model and depth patch. Increasing depth-estimation resolution can recover finer structure at greater memory and processing cost; it does not independently enlarge the final image.
0001SoftRealistic Negative and Positive Embeddings
Negative embedding, which I created for myself - I was too lazy to manually write a negative prompt every time. Works very well with my model 0001SoftRealistic - v154xxx | Stable Diffusion Checkpoint | Civitai , but...
Async's Negative
This is Negative Embedding for SD1.5, Not for SDXL . The concept was to improve quality, such as EasyNegative and veryBadImageNegative .
Wan 2.1 edge-guided video
Generate a silent video guided by source-video edges, a start image, and a text prompt using Wan 2.1 Fun Control. For a first run, upload a source video and a start image, then replace the positive prompt example with your desired subject, action, and style. The source video supplies frame-by-frame Canny contours. The start image supplies both initial-frame and visual conditioning. The negative prompt lists unwanted appearance or motion; its packaged default is in Chinese. Keep 960 × 544 pixels, 77 frames, 16 FPS, batch size 1, full denoise, and the packaged sampling settings initially. This gives approximately 4.8 seconds of video. Dimensions use multiples of 16 and frame counts follow 1 + 4n. Choose a source clip with enough frames for the requested sequence. There are no source trimming or frame-rate conversion controls. Low and high edge thresholds determine which contours guide generation. Lower thresholds include weaker edges; higher thresholds favor stronger contours. Keep the low threshold below the high threshold. Reference crop changes framing for visual conditioning only, independently of the initial-frame input. Frames determines the generated sequence length. FPS determines playback speed and duration without generating additional frames. Source FPS and source audio are not connected to output playback. The only selected output is the generated video; no separate edge preview is returned. Leave file type and codec on auto for a first run. Manual choices must be compatible with each other and your playback software. The optional 10-bit setting also requires compatible encoding and playback. Advanced sampling controls include seed, steps, prompt guidance, sampler, scheduler, denoise, and schedule shift. Seed -1 requests fresh random noise; a fixed seed lets you compare settings with the same starting noise. Keep denoise 1 and batch size 1 for normal use; batch variants have no separate video output branches. Skip-layer guidance exposes independent double-block and single-block layer lists, strength, rescaling, and a sampling-progress interval expressed as fractions from 0 to 1. Keep its start below its end. Attention adjustments independently scale structural and temporal self-attention and cross-attention. Either adjustment stage can be bypassed while preserving the model path; its controls apply only while enabled. The model, text encoder, vision encoder, and VAE remain fixed to the packaged Wan 2.1 Fun Control setup.
Gemini two-image editing
Generate an edited image from a source scene, a second visual reference and written instructions using Gemini. Upload both required images: the scene to change as Source image and an object, accessory, clothing item or other visual guide as Reference image. The source image is sent first and the reference second, together to Gemini. Explain each image's role, what to change and what to preserve. For a first run, upload a scene containing a person and a separate accessory reference. Replace the example Edit instructions with a request such as: “Use the first image as the scene. Put the accessory from the second image on the person, keeping the surrounding scene unchanged.” Choose an aspect ratio and resolution, then run the Pipe. Aspect ratio controls output proportions; auto asks Gemini to follow the input image's aspect ratio. Resolution offers 1K, 2K and 4K targets; 2K and 4K use Gemini's native upscaler. Model offers Gemini 3 Pro Image Preview or Nano Banana 2 (Gemini 3.1 Flash Image). Seed -1 randomizes each run; a fixed seed requests best-effort repeatability without guaranteeing identical images. System instructions set foundational provider behavior alongside the edit prompt. The default emphasizes producing an image. Provider response defaults to IMAGE; IMAGE+TEXT additionally requests text, but only the generated image is returned by this Pipe. Preservation of faces, objects and unchanged regions is a prompt request, not a guarantee. Both loaders send their IMAGE outputs; uploaded alpha masks are not connected, so uploaded transparency is not preserved through this path.
Capybara video edit
Generate a prompt-directed video variation from an uploaded clip using Capybara. Selected source frames are resized and supplied to video conditioning and, by default, a visual encoder; the generated frames become the output video. For a first run, upload a video with at least 121 frames, replace the example edit instruction with the change you want, and keep 960 × 960 pixels, 121 output frames, 24 FPS and batch size 1. The resulting playback duration is approximately 5.04 seconds. Describe both the desired change and any subject or action you want retained. The advanced negative prompt lists unwanted visual features. Width and height control both generation and source-frame resizing. Use positive multiples of 16. Source crop defaults to center, which crops to the output aspect ratio while preserving proportions; disabled stretches the frames to fit. Source resampling selects the resizing interpolation. Source start frame is the zero-based beginning of the selected visual reference range. Source frame count and output frame count are independent; keep both at 121 initially and keep the selected range within the uploaded clip. Use output frame counts of 4n + 1, such as 81 or 121. Output FPS is set independently of the uploaded video's frame rate. Source audio is attached unchanged: selecting later frames or changing output duration can cause audio synchronization differences. Visual guidance is an optional stage. Its crop control affects visual encoding of the already resized frames. Bypass Visual guidance to omit that encoding while retaining the source-frame conditioning connection. Advanced generation controls include seed, prompt guidance strength, steps, sampler, scheduler, sampling shift and denoise. The defaults are randomized seed (-1), guidance strength 6, 20 steps, Euler, simple scheduler, shift 7 and denoise 1. A fixed nonnegative seed reuses the initial noise. Sampling shift changes model sampling rather than source timing; denoise controls the fraction of the noise schedule and is not a calibrated video-edit strength. Keep batch size 1 for one clip because every decoded frame feeds the same video assembly path, rather than separate video outputs. Playback settings include 8- or 10-bit assembly; some players may not support 10-bit video. Video output offers automatic or explicit file type, codec and CRF settings. Start with auto file type, auto codec and CRF -1; explicit container and codec choices must be compatible. This is generative editing. Exact source-frame correspondence, subject preservation and source-motion preservation are not guaranteed.
Wan 2.2 camera video — Standard
Generate a silent camera-conditioned video from a scene prompt and an optional starting image with Wan 2.2 14B Fun Camera. For a first run, upload a starting frame with Source image enabled, replace the rover example under Scene and action, and keep the 720 × 720 dimensions, 81 frames and 16 FPS. Choose Static or a pan, zoom or rotation under Camera movement. Leave output container and codec on auto. The default clip is about 5.1 seconds long. To generate from text without a starting image, explicitly bypass Source image; an empty upload alone is not the mode switch. Describe subject action in the prompt and choose camera motion separately. Camera speed applies to moving presets. Width and height are pixel dimensions in increments of 16; frame counts follow 1, 5, 9 and so on. Frame rate controls playback speed and duration, while frame count controls how many frames are generated. Advanced camera intrinsic parameters use the source's 0–1 scales, not millimeters. Advanced settings include unwanted-content text, seed and independent prompt guidance for initial generation and refinement. Seed -1 selects new random variation; use a fixed nonnegative seed when comparing settings. The supplied negative prompt is Chinese and excludes artifacts, poor anatomy, clutter and static imagery; adapt it to your scene. The standard profile uses a high-noise stage followed by low-noise refinement, without the sibling four-step profile's acceleration LoRAs. Both samplers use a total schedule of 20 steps: the initial stage stops at 10 and refinement starts at 10. These are independent controls, not automatically synchronized. When changing the schedule, keep both total-step settings matched, keep the handoff boundaries matched and within the total schedule, and coordinate the noise schedulers. Refinement continues the initial latent without adding new noise. Separate model sampling shifts are also available. Keep latent batch size at 1 for one clip; this graph has a single video assembly and output path and does not expose separate clip downloads for larger batches. Output settings control container, codec and encoding CRF; -1 leaves CRF automatic. Video assembly supports 8-bit and 10-bit, with possible player or encoder compatibility limits for 10-bit. No audio is connected. Uploaded transparency is not preserved through the starting-image path because only the loader's image output is used. Camera choices condition generated motion rather than guaranteeing exact physical camera tracking.
Vidu start and end frame video
Generate a five-second 1080p video connecting two uploaded images with prompted motion using Vidu Q1. Upload both a start frame and an end frame. Replace the example Motion prompt with the action, camera movement, and transition you want between those images. For a first run, leave Movement amplitude on auto and Seed at -1. Movement amplitude controls the amount of object movement in the frame, with auto, small, medium, and large choices. The images supply the visual endpoints; the prompt directs the transition. This configuration fixes the model to Vidu Q1, duration to five seconds, and resolution to 1080p. Seed -1 randomizes each run. A positive integer sets the generation seed; Vidu also treats 0 as random. The generated video is returned for preview with automatic file type and codec settings by default. Output controls offer auto, MP4, MKV, or WebM file types and auto, H.264, or AV1 codecs. Generation sends the endpoint images and prompt to the Vidu partner API and requires an authenticated account with sufficient credits.
