Répertoire des ressources
Trouvez ce dont vous avez besoin pour votre flux de travail.
Guides: techniques, setup, and troubleshootingRecherchez Sweet Tea, Pipes, des flux de travail externes, des modèles, des packs de nœuds et des guides dans un catalogue unique lié aux preuves.
Commencez plutôt avec un flux de travail ↗Résultats de la recherche
Toutes les ressources
20 affiché of 42 670
Create images from two references
Generate or edit an image with Gemini using two reference images and a written instruction. Upload both references, then explain which subjects, details or style to take from each. Both uploads are required and are sent together as context for one image request, rather than processed into separate outputs. For a first run, upload character and clothing references, describe how to combine them in a casual fashion pose, and keep the supplied 1:1 aspect ratio and 1K resolution. The references have no fixed character or clothing roles; you can request other compositions or edits. Choose an explicit aspect ratio for the output shape. Auto asks Gemini to match the input image proportions; an explicit ratio avoids ambiguity when the references differ. Resolution selects 1K, 2K or 4K; 2K and 4K use Gemini's native upscaler. The model selector offers Gemini 3 Pro Image Preview and Nano Banana 2 (Gemini 3.1 Flash Image). System instructions set foundational behavior; the supplied instructions prioritize interpreting the prompt visually and producing an image. Keep IMAGE for image-only responses, or select IMAGE+TEXT to request accompanying text from Gemini. This Pipe returns only generated images, so accompanying text is not delivered. Use seed -1 for a new random seed each run. Fixed seeds request best-effort consistency, not identical results. Reference details are interpreted by the model, so exact identity or garment reproduction is not guaranteed. Uploaded alpha masks are not connected, so reference transparency is not preserved. This workflow sends the prompt and reference images to Gemini through a paid provider request. Generated images are returned to Sweet Tea through an output transport that does not permanently save them through the workflow.
Wan 2.1 video outpainting
Expand an uploaded video's canvas with generated surroundings using Wan 2.1 VACE, and export an H.264 MP4 with source audio when available. For a first run, upload a continuous scene and enter an outpainting prompt describing both the existing scene and the surroundings to add. Keep both aspect-ratio controls on Horizontal and retain the other defaults. If you change the canvas shape, set Aspect ratio and Continuation aspect ratio to the same choice: their generated batches must have matching dimensions. Both stages use the fixed I2V720p/HQ resolution preset. The input is resampled to 24 frames per second. Initial source size and Continuation source size set the original content's size in megapixels before padding to the target canvas. Smaller source frames can leave more space for generated surroundings; use matching sizes across stages for consistent framing. Each stage has its own mask-feathering and VACE control-strength settings. Control strength adjusts guidance from the padded source frames and masks. The workflow generates an initial 81-frame batch followed by three fixed continuation iterations. Each continuation requests 81 generated frames, carries the previous generated batch's last frame as a reference, and advances the source slice by 81 frames. The continuation source slices request up to frame index 405, approximately 16.9 seconds at 24 FPS. Supply enough continuous footage to cover those requests. This tool does not adapt its iteration count to the uploaded clip's length. The source's value labeled Length in Seconds controls loop arithmetic rather than exact playback duration and is not an editable duration control. Continuation slices request more conditioning frames than each generated batch; the supplied evidence does not establish precisely how excess conditioning frames are handled. Both stages share the prompt, negative prompt, seed, and CausVid LoRA. Seed -1 randomizes each run; a fixed seed reuses the shared noise seed. Initial and continuation sampling controls are independent. The supplied recipe uses CausVid strength 1, three Euler steps, normal scheduling, CFG 1, and denoise 1 in both stages. Keep these defaults for the first run; changes to LoRA strength affect both stages. Compression controls H.264 CRF: lower values retain more detail and generally create larger files. Trim to audio is enabled by default and can shorten the encoded video to the source audio's length. Disable it to retain generated frames beyond shorter audio. Playback remains fixed at 24 FPS. Outpainting synthesizes content and can alter the original region or show transitions between batches. Scene cuts can conflict with the previous-frame continuation reference. That reference remains part of the workflow and has no supported disable switch.
Boogu 0.1 image edit · Int8
Create edited images from one uploaded reference and natural-language instructions using the fixed Boogu Image Edit convrot Int8 model. Describe both the changes you want and anything that should stay unchanged, such as the subject, clothing or layout. The results appear as an edited-image batch in Sweet Tea. For a first run, upload your source image, replace the example editing instruction, leave Negative prompt blank, and keep Output megapixels at 1, Variants at 1 and the default sampling settings. Negative prompt describes features to discourage. Output size measures a resized copy of the source to derive output dimensions at the requested megapixel count while retaining its aspect ratio. The original uploaded image remains the editing reference. Bypass Output size to derive dimensions directly from the uploaded image instead; Output megapixels then has no effect. Final dimensions may be rounded by latent sizing. Variants controls how many edited images are generated from the same reference and instruction. Larger resolutions and batches require more memory. Seed -1 randomizes each run; use a fixed seed to reuse the initial noise with otherwise unchanged settings. Advanced controls include CFG, steps, sampler and scheduler. Sampling schedule fraction uses only part of the noise schedule when below 1; it is not an image-preservation strength. Keep Add noise enabled and the schedule fraction at 1 for the intended operation. Schedule shift affects the scheduler's noise-level calculation, while the sampler receives the original loaded model. Keep the source defaults initially. This tool generates from an empty latent conditioned on the reference, rather than directly denoising the uploaded pixels. Exact identity and layout preservation are not guaranteed. Only the loader's image output is connected; the uploaded alpha mask is unused, so uploaded transparency is not preserved. The selected output uses Sweet Tea preview transport rather than the original file-saving stage; the original PNG export settings do not apply.
ACE-Step music remix
Remix an uploaded music track with ACE-Step using style tags and lyrics, then export the result as MP3. For a first run, upload the audio excerpt you want to remix, replace the example style tags and lyrics with your intended direction, and keep the sampling defaults, including remix strength 0.3. Describe genre, instruments, mood, tempo and vocal character with comma-separated tags. Enter intended sung words with section labels and line breaks. Lyrics and tags guide generation; they do not guarantee exact words or performance. Remix strength ranges from 0 to 1: lower values retain more source structure, while higher values permit larger changes. Lyrics strength adjusts lyric conditioning, and CFG controls overall text guidance. The uploaded audio supplies the starting latent and temporal extent. Prepare your excerpt before uploading: this tool has no trimming, independent duration control or separate text-to-music mode. Negative conditioning is zeroed internally, with no editable negative prompt. Use seed -1 for random variations or a fixed nonnegative seed to compare settings. Steps, sampler and scheduler control denoising. Advanced latent tonemap multiplier and sampling shift controls change internal guidance and model sampling; retain their source defaults of 1 and 5 for a first run. Sampling shift is not an audio timing offset. MP3 quality offers V0 variable bitrate, 128k and 320k. This controls file encoding rather than the generated composition. For multilingual lyrics, the supplied source guidance calls for manual romanization and language markers such as [zh], [ja] or [ko]; automatic transliteration is absent. The workflow requires ace_step_v1_3.5b.safetensors in the ComfyUI checkpoints model directory. The supplied model source is https://huggingface.co/Comfy-Org/ACE-Step_ComfyUI_repackaged/resolve/main/all_in_one/ace_step_v1_3.5b.safetensors?download=true. The supplied dependency catalog has not resolved this checkpoint.
Anima masked image generation
Generate images from a prompt using Anima's LLLite image-and-mask guidance. Each run returns the generated image batch and a preview of the guidance mask. Before your first run, prepare a Painter PNG asset reference accessible to the execution runtime. Painted mask is a required text reference, not a PNG upload or an interactive painting editor. This Pipe does not create that asset for you. Enter the reference, upload a source image, replace the example prompt with your desired result, and start with the 1024 × 1024 output, one variant and Turbo enabled. Inspect the returned mask preview alongside the generated images. To work without a source image, disable the Source image stage. Painter then uses its blank-canvas width, height and background color; the Painter asset reference is still required. Leaving the upload empty while the stage remains enabled does not select blank-canvas mode. Canvas dimensions and generated output dimensions are independent controls. Prepare compatible image, mask and output sizes before running; the disconnected source resize node does not resize uploads. Turbo mode selects the Turbo LoRA and its own steps and CFG controls, initially 8 steps and CFG 1. Disabling Turbo selects the model without that LoRA and the standard controls, initially 30 steps and CFG 4. Both modes retain image-and-mask guidance. Turbo LoRA strength affects the Turbo branch only. Control strength scales the inpainting patch's influence, while Guidance start and Guidance end specify fractions of sampling from 0 to 1; keep start at or below end. Advanced controls include the negative prompt, separate steps and CFG for each mode, Turbo LoRA strength, sampler, scheduler and denoise. Seed -1 requests fresh random noise; a fixed seed reuses the initial noise. Width and height specify generated pixels in multiples of 8, and Variants sets the image count. Generation starts from an empty latent rather than an encoded source image. There is no final compositing stage to restore pixels outside the mask, so exact preservation of unedited regions and uploaded transparency is unsupported. Lowering denoise does not provide source-image preservation. The runtime needs anima-base-v1.0.safetensors in diffusion_models, anima-lllite-inpainting-v2.safetensors in model_patches, qwen_3_06b_base.safetensors in text_encoders, and qwen_image_vae.safetensors in vae. Turbo mode additionally selects anima-turbo-lora-v0.2.safetensors in loras. Source installation references are the circlestone-labs/Anima, Comfy-Org/Anima-LLLite and circlestone-labs/Anima-Official-LoRAs repositories on Hugging Face. The runtime must also provide the workflow's node implementations and Sweet Tea image output transport.
Kandinsky 5 Lite text to image
Generate an image or image batch from text with the fixed Kandinsky 5 Lite model. Describe the subject, composition, lighting, colors, and style in Positive prompt. Negative prompt can describe unwanted elements or remain blank. No uploaded image is required or supported. For a first run, use the supplied hiker prompt or replace it, keep Width and Height at 1024 pixels and Image count at 1, and leave the advanced settings at 50 steps, prompt guidance 3.5, Euler sampler, Simple scheduler, Schedule shift 3, and Denoise strength 1. Run the tool to receive the generated image batch. The output transport replaces ComfyUI SaveImage and does not permanently save images through that node. Width and Height use increments of 8; adjust them together to set the aspect ratio. Image count controls how many images are generated together. Larger dimensions and batches increase resource use. Advanced Sampling controls change randomness, sampling effort, prompt guidance, and the algorithm and noise schedule used to generate images. Seed -1 selects fresh randomness on each run; use a fixed seed when comparing settings. Schedule shift changes the model's timestep distribution. Denoise strength remains at 1 for the supplied setup because sampling starts from an empty latent. Reducing it does not provide image preservation or an image-to-image mode. The setup uses kandinsky5lite_t2i.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, clip_l.safetensors, and ae.safetensors, plus the Sweet Tea output node pack. These assets must be available in the execution environment. Model and encoder choices are fixed in this tool.
Hoshimachi Suisei 星街すいせい / Hololive
sui1, 1girl, solo, side ponytail, hoshimachi suisei, fingerless gloves, single thighhigh, jewelry, thigh strap, bracelet, buttons, plaid dress, blue choker, blue belt, plaid skirt, mini crown, grey skirt, blue ascot,...
Edit video with Runway Aleph 2
Edit existing footage with a text description using Runway Aleph 2. For a first run, upload a source video lasting 2–30 seconds at 30 fps or lower. Replace the example surfing prompt with an English description of what should appear in the result, using 1–1000 characters. Describe the desired changes to subjects, objects, surroundings, lighting, or visual style, then run the tool and inspect the returned video. Leave Seed at -1 to randomize each run, or enter a fixed seed to reuse the generation seed. Public figure moderation offers auto and low settings for recognizable public figures; the template defaults to low. Advanced Video output controls select the output container, codec, and encoding quality. Leave their defaults for a first run. These controls change output encoding, not the requested scene edit. This tool supports text guidance only; the source template's image-guidance and keyframe branches are disconnected from generation. There are no separate output-size, duration, or frame-rate controls. Inspect the result for unintended changes, since the graph does not enforce preservation of untouched details. The source template specifies a logged-in ComfyUI comfy.org API account for the Runway partner node.
TemporalDiff Motion Module
This model was created by CiaraRowles , posted to Civitai.com with permission. Basic Getting Started Tutorial available at the Civitai Education Hub !
Atomix Wan I2V Workflow — Wan 2.2
A Simple Wan I2V workflow
LTX 2.3 video with generated audio
Generate a video with audio from a text description using LTX 2.3. No image, video, or audio upload is required. For a first run, replace the example scene and sound prompt with your subject, setting, action, camera movement, dialogue, and sounds. Review the negative prompt, choose the requested width and height in pixels, and enter a positive duration in whole seconds. Keep the advanced sampling and encoding defaults for the first run. The source defaults request a 900 × 1600 portrait video lasting approximately 20 seconds at 24 FPS. Initial sampling jointly generates video and audio at half the requested spatial size. A fixed 2× latent upscaler feeds a second sampling stage, whose video is decoded for the final result. The returned soundtrack is decoded from the first stage; refinement settings do not replace it. Actual dimensions and duration can differ from the request because of latent spatial and frame-count constraints. Playback FPS controls playback, audio timing, and duration-to-frame conversion. Conditioning FPS is a separate control used by both sampling stages: change both fields together and keep them equal. Use playback FPS within the downstream video's supported 1–120 range. Each sampling stage has its own seed, CFG, sampler, and editable manual noise schedule in advanced settings. Seed -1 randomizes that stage; a fixed nonnegative seed reuses its noise. To reuse both stages' noise, set both seeds. The schedules define sampling intervals directly, so there is no separate steps control. Negative conditioning is connected to both stages, and its effect depends on their CFG settings. The optional fixed distillation LoRA starts disabled, matching the source. Enable its stage to make the LoRA strength operative. The base quantized model, text encoders, VAEs, 2× upscaler, and memory patches are fixed implementation choices. Output settings select the container, codec, bit depth, and compression quality. Start with MP4, automatic codec, 8-bit precision, and automatic CRF (-1). Container and codec must be compatible; 10-bit output also requires compatible encoding and playback. The source's 8 GB hardware claim is not a verified runtime guarantee. Dependency evidence is incomplete: the inventory lists an older upscaler than node 23 selects, and node 26's first text encoder filename has a doubled .safetensors suffix. The graph preserves those source model selections.
Portrait relighting
Generate a relit portrait from a reference image and written lighting directions. For a first run, upload a portrait, keep the default dual rim prompt, leave aspect ratio on auto and resolution at 1K, then run. The prompt requests identity preservation, but this is generative editing: likeness, details and composition can change. Use one editable prompt to explore the five lighting recipes in the source workflow. With a reference, begin with “Maintain the identity of input image 1, modify the scene lighting and shadows to match the following lighting style:” and append one of these recipes: - Dual rim: no front key, twin hard lights from behind left and right, subject silhouetted at center, glowing edge separation on both sides, dramatic dark fill. - Overhead: hard top-down overhead key, harsh light directly above, deep under-eye and jaw shadows, pronounced brow ridge highlight, strong nose shadow pointing straight down, theatrical and sculpted. - Split: hard side key at 90 degrees, one half of the face fully lit, the other half near-black, sharp nose shadow line, minimal fill. - Rembrandt: side key slightly above, deep falloff, subtle rim separation. - Motivated practical: off-axis kicker mimicking an environmental source, strong directional spill, naturalistic shadow logic, atmospheric fill. These are editable prompt recipes within one tool, rather than separate operations or simultaneous outputs. Change the directions freely to request another lighting arrangement. Bypass Source image to generate a new portrait without a reference. In that mode, replace the identity-preservation wording with a description of the subject and desired scene, and choose an explicit aspect ratio. Auto matches the reference aspect ratio when an image is supplied. Resolution offers 1K, 2K and 4K; the node uses Gemini's native upscaler for 2K and 4K. Model selects between the two source-supported Gemini image models. Seed defaults to a fresh random value per run; a fixed value requests best-effort consistency, not deterministic reproduction. Response mode controls whether the provider also generates text, but this Pipe delivers the image only because the source text output is unconnected. Generation instructions provide advanced behavioral guidance; retain instructions to produce an image when editing them.
Wan 2.1 video inpainting
Generate an edited video segment with SAM3 object selection and Wan 2.1 VACE masked video conditioning. For a first run, upload a source video, replace Object to edit with a description of existing content in that clip, and replace Edit prompt with the desired replacement, scene and motion. Leave Reference image disabled for text-only editing. To add appearance guidance, enable that stage and upload an image. Start frame is a zero-based source-frame index. Frame count requests the segment to edit, and the actual selected frame batch determines generation length. Begin with Start frame 0 and the default 81 frames when the clip has enough frames. Approximate segment duration is frame count divided by the source frame rate. This tool outputs the generated segment, without reinserting it into the full source video. Output width and height are in pixels and are rounded down to multiples of 16. Use positive dimensions of at least 16. Center framing crops while preserving proportions; Disabled stretches to fit. SAM3 selects content after resizing. Mask margin expands that selection in resized-frame pixels; negative margins shrink it. Detection threshold and refinement passes adjust selection. Combined masks are the normal video setting; separate object masks have no dedicated alignment stage here. Fast sampling selects the fixed CausVid LoRA and the Fast steps and Fast CFG controls. Turning it off selects the base model and Standard steps and Standard CFG. CausVid LoRA strength affects only fast mode. Both modes share the seed, sampler, scheduler, denoise strength and sampling shift. Use seed -1 for randomization. VACE control strength is separate from prompt guidance. Keep batch size 1 for the normal single-sequence output; larger batches are not split into separate video outputs. The output uses the source video's frame rate and passes through its audio. Audio is not explicitly trimmed or offset to match Start frame and Frame count, so synchronization and duration may differ for a selected segment. Generated frames are decoded directly, without a final composite that guarantees unchanged pixels outside the mask. Video encoding controls select the output container, codec and compression setting. The workflow uses fixed SAM3, Wan VACE, text-encoder and VAE models; fast mode additionally uses the fixed CausVid LoRA. These model assets must be available to the execution environment. The supplied dependency evidence marks them missing; this review establishes the connected tool and its guidance, not a completed runtime test.
Wan 2.2 text to video
Generate one silent video from a text description with Wan 2.2. No uploaded image or video is required. For a first run, edit the positive prompt to describe your subject, movement, camera, lighting and setting, then keep the 640 × 640 size, 5-second duration and 16 FPS defaults. The negative prompt independently discourages unwanted content and visual traits; its supplied Chinese text includes artifacts, static frames and clutter. Standard mode uses 20 total steps, CFG 3.5 and a handoff at step 10. Enable Lightning mode to select both Lightx2v LoRAs together with the separate Lightning settings: 4 total steps, CFG 1 and a handoff at step 2. Only the selected mode's steps, CFG and handoff settings apply. LoRA strength controls apply only in Lightning mode. Each handoff must remain strictly between zero and its mode's total step count. The downstream samplers accept 1–10000 total steps and CFG values from 0–100. Width and height are pixels in multiples of 16. Use a positive duration and a frame rate from 1–120 FPS. Requested frame count is floor(duration × FPS) + 1; choose a combination whose floored product is a multiple of 4 for the expected 4n + 1 frame layout. FPS also sets playback speed. The defaults request 81 frames, giving approximately 5.06 seconds of encoded playback. Larger dimensions, longer duration and higher FPS increase generation work and memory use. Seed -1 randomizes each run; use a fixed seed to compare settings. Advanced initial and finishing sampler, scheduler and schedule-shift controls apply in both modes. The initial stage adds noise and runs the high-noise model; the finishing stage continues the same latent without adding new noise. Both stages use the selected total step count, with the handoff dividing their work. The supplied sampler, scheduler and shift values match across stages. Keep file type, codec and encoding quality on automatic selection for a first run. Explicit container and codec choices require compatible encoding and playback support. Video assembly defaults to 8-bit; optional 10-bit assembly can retain smoother gradients but requires downstream support. CRF controls encoding quality separately from generation. Latent batch size remains one; this tool returns one video and does not offer separate batch files. Audio is not generated.
Psycho Style
This is a DreamArtist Textual Inversion Style Embedding trained on an image of a colorful cyberpunk-style skeleton (wearing headphones). You can expect to get some super weird colors, and intricate robotic cyberpunk...
CyberRealistic Negative - Pony v1.0
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
Bernini-R image editing
Edit an uploaded image with text instructions using Bernini-R. Upload a source image, describe the changes in English and state what should remain unchanged. For a first run, use “make it night,” a 1280-pixel long edge, Turbo enabled, batch size 1 and frame count 1. Run the Pipe to receive an edited image. The resized source supplies the output dimensions and retains the source aspect ratio. Turbo selects the LightX2V LoRAs and defaults to 6 total steps, a 3-step high-noise stage and CFG 1. Turning it off uses the same Bernini model pair without those LoRAs and defaults to 40 total steps, a 20-step high-noise stage and CFG 5. Each mode has separate advanced step, split and guidance controls; changing controls for the inactive mode does not affect the current run. LoRA strengths apply only with Turbo enabled. Use total steps from 1 to 10000, a positive split strictly below the corresponding total, and CFG from 0 to 100. The negative prompt describes unwanted characteristics. The supplied Chinese text includes artifacts, malformed anatomy and motion-related exclusions; revise it for your intended result. The sampler and noise schedule are shared by both stages. Denoise changes the schedule range rather than directly blending the source and output. Initial-stage noise is enabled by default; its seed uses -1 for a new random seed each run. Set a fixed seed to compare settings. Finishing-stage noise is disabled by default so the second stage continues the existing latent; enabling it makes the separate finishing seed active. Batch size requests multiple results. Frame count 1 produces still images; 5, 9 and subsequent increments of 4 request sequences conditioned on the uploaded still. Results are returned as individual images through the preview output, without video encoding or a playback rate. Prompt prefix offers Default, Text to Image, Text to Video, Image Editing and Subject to Image. These choices only select system prompt wording. The uploaded image remains connected in every selection; reference-image composition and text-only generation are not supported by this selector. The graph uses rendering without a separate prompt planner. Uploaded transparency is not preserved because only the loader’s RGB IMAGE output is connected.
LTX 2.3 first-to-last frame transition
Generate a video transition guided by two uploaded images, with jointly generated audio. Upload both a start image and an end image, then replace the example prompt with your subject, scene, movement, camera motion and transformation. Describe desired sounds or dialogue in the same prompt. The result is one video containing generated audio; there is no audio upload input. Endpoint images guide generation rather than guaranteeing exact copies, and exact dialogue or synchronization is not guaranteed. For a first run, use images with similar framing and keep 720 × 1280 pixels, a requested duration of 6 whole seconds, 25 FPS, both image strengths at 0.7, transition LoRA strength at 1 and CFG at 1. The example prompt describes photography changing into watercolor and includes zhuanchang, the token suggested by the source notes for the transition LoRA. Replace its scene description to match your images. Width and height feed both image resizers; the resized start image establishes the video dimensions. Use explicit positive integer dimensions of at least 64 pixels. Avoid 0: it calculates aspect ratio independently for each image and can produce incompatible guide sizes. Both images are center-cropped by default. Advanced framing controls independently choose center cropping or stretching and interpolation for each image. Area interpolation suits downscaling, lanczos suits upscaling and nearest-exact suits pixel art. Uploaded transparency is not preserved because only the loaders' RGB image outputs are connected. Advanced preprocessing controls independently set compression for each resized image on a 0–100 scale; both default to 25. Duration is requested in positive whole seconds. The graph requests Duration × FPS + 1 frames and shares FPS across audio timing, video conditioning and playback. Use FPS from 1 to 120 and keep Duration × FPS + 1 at or below 1000, the supplied audio latent limit. The extra frame and model frame handling mean requested duration is not an exact final running time. Start and end guide indices default to 0 and -1. Keep these for endpoint guidance, or change them to move the guides within the clip. Negative indices count backward from the end; choose positions within the generated clip. Their strengths independently control image influence. The transition LoRA can be bypassed or set to strength 0 while retaining both image guides. Seed -1 requests a fresh random seed each run; use a fixed nonnegative seed when comparing settings. CFG defaults to 1, where conventional negative-prompt guidance has no effect. If you raise CFG, review the negative prompt first: its supplied exclusions include scene-specific details and restrictions that may conflict with stylized imagery or your intended audio. Advanced sampling controls expose ancestral noise and its noise scale. Ancestral noise defaults to off at 0; noise scale becomes relevant when ancestral noise is nonzero. The manual sigma schedule contains nine values defining eight sampling intervals, with no separate Steps control. Keep the supplied schedule for a first run. Video bit depth defaults to 8-bit. The supported 10-bit option can retain smoother gradients, but some players or downstream tools may not support it. Advanced video file controls offer automatic or explicit container and codec choices. Keep both on auto for a first run; explicit choices must be compatible.
PA7_Portrait_Tools
Portrait promptography is an art form that goes beyond simply capturing someone's physical appearance. It delves deep into the core of their being, aiming to encapsulate their essence, personality, and emotions in a...
LTX-2.3 Audio-Conditioned Video
Create one audio-conditioned video with LTX-2.3. Upload a reference image and audio track, then replace the cactus example prompt with your subject, action, setting and camera movement. For a first run, keep 1280 × 720, 24 FPS, 9 seconds and the supplied sampling settings. Supply enough audio after Audio start to cover Duration. Audio start is measured in seconds; negative values count from the end of the track. Duration controls both audio trimming and video frame calculation: integer(Duration × FPS + 1). The extra frame can make video playback slightly longer than the audio excerpt. Use positive dimensions, duration and frame rate. The source latent layout declares spatial steps of 32 pixels at the initial half resolution and a temporal step of 8 frames; use compatible settings when changing output shape or timing. The workflow generates at half the requested dimensions, upscales the video latent by 2× and runs a refinement pass. Width and height also set reference framing: center crops to the requested aspect ratio, while disabled stretches the image. Reference longer edge independently resizes the prepared image before compression and both image-conditioning passes; its default is 1536 pixels. Uploaded transparency is not used as an alpha mask: only the image loader's RGB image output is connected. Image strength controls reference influence in initial generation; Refinement image strength independently controls its reapplication after upscaling. Text-to-video mode disables image conditioning in both passes while retaining audio conditioning. A valid reference image remains required because its loader and preparation stages stay connected. Enhance prompt is enabled by default and rewrites your scene prompt using text only. Describe relevant image and audio context yourself. Disable it to use your original prompt directly. Advanced prompt settings include text sampling, its independent seed and temperature, token-selection controls, the generation limit, template and optional model-supported thinking mode. The fixed Gemma LoRA strength applies to prompt enhancement separately from the video distillation strength. Initial generation and refinement have independent seeds, CFG, samplers and manual noise schedules. Schedule entries determine sampling intervals; there is no separate Steps control. Keep the supplied schedules and distillation strength for a first run. Seed -1 randomizes each run; fix both video seeds and the sampled enhancement seed, or disable enhancement, when controlling those sources of variation. At CFG 1, the negative prompt has no classifier-free guidance effect in that pass. The delivered video includes audio decoded from the audio latent after both passes, rather than a direct copy of the uploaded file. Exact waveform preservation and precise lip synchronization are not guaranteed. Advanced output settings select container, codec, encoding quality and bit depth; keep their defaults for a first run. Ten-bit video requires compatible encoding and playback.
