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 42 663
Wan 2.2 controlled video · Four-step
Generate a silent video from a scene prompt and control footage using Wan 2.2 Fun Control with a four-step Lightx2v preset. For a first run, upload a control video and replace the example scene prompt. Leave Canny edge extraction disabled for already prepared control frames. For ordinary footage, enable Canny edge extraction; its normalized thresholds apply only when enabled, and the low threshold should stay below the high threshold. Reference-image conditioning is disabled initially. To use it, upload an image and enable Reference image. Leave it disabled when no image is supplied. The reference upload supplies RGB image conditioning; the loader's alpha mask is not connected. Start with 640 × 640 pixels, 81 frames and 16 playback FPS, producing approximately 5.1 seconds. Width and height use increments of 16 pixels; frame count follows 1 + 4n. Playback FPS is independent of source FPS. Source audio is not included, and there is no source-FPS resampling control. The result is newly generated footage guided by control frames. Leave batch size at 1 for a single clip; this Pipe exposes one video output rather than separate outputs for batch items. Both generation stages run for every result. Initial sampling uses the high-noise model for steps 0–2; refinement uses the low-noise model for steps 2–4 without adding fresh noise. Both use a four-step schedule, Euler sampling, the simple scheduler, CFG 1, sampling shift approximately 8 and their corresponding Lightx2v LoRA at strength 1. Refinement is part of generation rather than a standalone postprocessing mode. The standard sibling uses a twenty-step path without this LoRA pair. Use seed -1 for randomization or a fixed nonnegative seed to reuse initial noise with unchanged inputs and settings. Advanced controls expose independent guidance, samplers, schedulers, schedule boundaries, model shifts and LoRA strengths. Preserve the supplied preset initially. When changing schedules, keep both schedule lengths equal, coordinate schedulers, match Initial end step to Refinement start step within the schedule, and set Refinement end step to complete it. LoRA strength changes do not automatically change the schedule. Negative conditioning is available but may have no effect at CFG 1. Leave output container, codec and CRF on automatic selection initially. CRF -1 uses automatic selection; explicit values range from 0 to 63 and their effects depend on the codec. Explicit container and codec choices must be compatible. Video construction offers 8-bit and 10-bit representation; the source documents smoother gradients with 10-bit and possible player or downstream compatibility limitations.
Wan 2.5 text to image
Generate still images from English or Chinese prompts with the Wan 2.5 text-to-image preview API. The resulting image appears in the Pipe preview. For a first run, replace the example prompt with a description of your subject, composition, lighting, and style. Keep the default 1024 × 1024 dimensions and prompt enhancement enabled, then run the Pipe. No uploaded image is required. Optionally add a negative prompt describing elements or visual characteristics to avoid. Width and height are independently adjustable from 768 to 1440 pixels in increments of 32; together they determine the aspect ratio. Prompt enhancement allows the service to expand your description. Disable it to submit your wording without automatic expansion. Add watermark requests an AI-generated watermark on the result. Seed -1 randomizes each run; a nonnegative seed requests a particular randomization. The model is fixed to wan2.5-t2i-preview. This tool produces still images even when the example or your prompt describes camera movement. Generation sends your prompt to a remote partner API and requires configured ComfyUI API access, connectivity, and sufficient account credits.
FLUX.2 Klein two-image edit
Generate an edited image from a main image, a second visual reference and written instructions using FLUX.2 Klein 9B Distilled. Use the second image to supply an object, appearance or other visual information for the edit. For a first run, upload the main scene or character as Source image and the additional visual guidance as Reference image. Both uploads are required. Write Edit instructions explaining what to take from each image and how they should relate. The supplied example asks a character to hold a bag with both hands; replace it when your inputs call for another edit. Start with 1 megapixel for each image, one image per run, 4 steps, guidance scale 1 and Euler sampling. Output size resizes the source reference and sets the generated canvas dimensions, approximately retaining the source aspect ratio. Reference resolution independently resizes the second image for conditioning and does not set output dimensions. Each image has its own resize method controlling interpolation before encoding. Larger resolutions and batches require more memory. Advanced controls include second-reference resolution, seed, steps, guidance scale, sampler and images per run. Seed -1 selects fresh random noise each run; use a fixed seed to compare control or instruction changes with the same starting noise. Images per run generates a batch sharing the same instructions and references. Steps controls sampling iterations, sampler chooses the sampling method, and guidance scale changes guidance between instructed and zeroed-text conditioning. Both conditioning branches include both image references. Generation starts from a fresh latent rather than directly denoising the uploaded source. Exact preservation of identity, unchanged regions or object placement is not guaranteed. There is no mask, edit-strength control or separate negative prompt. Uploaded transparency is not preserved because only the loaders' image outputs are used. This tool always uses two image references; editing from one upload is served by the separate single-image edit tool.
Foundation text to image
Generate a batch of images from text, with adjustable dimensions and sampling settings and up to four optional LoRAs. For a first run, enter a positive prompt describing your subject, composition, lighting, and style. Optionally enter unwanted content in the negative prompt. Use the supplied DreamShaper checkpoint option under sd15, leave all LoRA stages disabled, and run with the defaults: four 512 × 512 images, 30 sampling steps, and prompt guidance (CFG) 6. The checkpoint supplies the image model, text encoder, and VAE decoder; the supplied option is not an SDXL checkpoint. Width and height are in pixels; use multiples of 8. Image count sets how many images are generated together with the same prompts and settings. Larger dimensions and batches require more memory and computation. In Sampling, seed -1 requests fresh randomness for each run. Use a fixed seed when comparing otherwise unchanged settings. Steps set the sampling iteration count, CFG controls prompt guidance, and sampler and scheduler select the sampling algorithm and noise schedule. Denoising amount defaults to 1 for full generation. Lower values change the noise-removal range, but cannot preserve a source image: this tool starts from an empty latent and has no image input. For optional LoRAs, select an available checkpoint-compatible LoRA before enabling its stage. Unused stages should remain bypassed. Enabled stages apply in order from LoRA 1 through LoRA 4. Each has independent model and text-encoder strengths; the latter affects both positive and negative prompt encoding. Zero removes that component's contribution, and the source also supports negative strengths. Disabling a stage skips both contributions.
Caption folder images with Florence 2
Generate caption text for an original image selected from a folder using Florence 2. This tool does not run diffusion upscaling. First run 1. Enter a Source folder accessible to the execution host. This is a server-side directory path, not a browser upload. 2. Keep Image selection at incremental_image and Task at more_detailed_caption. Leave Task text blank for ordinary captioning. 3. Review Caption cleanup: it replaces “The image shows” with “sharp photo of” by default. Edit the phrases for your material, or bypass cleanup to retain the original response. 4. Run and review the returned text. Image selection offers single_image, incremental_image and random modes; the graph has no explicit whole-folder loop. Single-image selection uses the zero-based Image index. File pattern filters candidate files. Selection seed controls random image selection independently of Caption seed; -1 randomizes each run. Other Florence tasks include OCR, document questions and region-related tasks. Supply Task text when the selected task needs a question or task-specific text. Only the text response is returned—not region images, masks or structured JSON. Bypass phrase replacement when you need the task's unmodified response. Sample text controls sampling during text generation. Maximum new tokens limits generated tokens, not words; Beams controls decoding beams. The model is fixed to microsoft/Florence-2-base. This tool returns text, not caption files or matched image/text training pairs. It captions the original selected image, not the upscaling sibling's result. The archived upload branch is inactive and is not an input-selection mode. Review generated descriptions for accuracy before using them as labels.
Edit video with Grok
Edit a short uploaded video with written instructions using Grok Imagine. For a first run, upload a clip no longer than 8.7 seconds and no larger than 50 MB. Replace the example motorcycle prompt with the changes you want for your clip, such as subjects, action or visual style. Leave Seed at -1, then run to receive one edited video in Sweet Tea. This workflow uses grok-imagine-video and requires a source video. The clip and prompt are sent to the Grok provider through a paid provider call. Changing Seed triggers a fresh provider run; reusing a fixed seed does not guarantee identical results. The edited video output defaults to automatic file type and codec selection. The output section also supports MP4, MKV or WebM file types and H.264 or AV1 codecs. These settings control output encoding, while the editing prompt controls the requested creative changes.
LTX 2.3 audio-driven lip-sync video
Generate an audio-driven speaking or singing video from a reference image and a selected segment of uploaded audio, with image-aware prompt expansion, 2× spatial upscaling and refinement. Output defaults to an H.264 MP4 containing the cropped uploaded recording. For a first run, upload an image with a clearly visible face and a speech or singing recording. Set Crop start and Crop end in minutes:seconds within the recording, with the end after the start. The defaults select 0:33–0:48; adjust both for your upload. Replace the performance description to match your subject, expression, movement and camera behavior, explicitly mentioning speaking or singing with the recording. The source description requests a woman smiling and singing toward a fixed camera. Review the negative prompt, whose unrelated scene details and exclusions of smiling and looking at the camera can conflict with your intent. Prompt expansion requires the configured Gemini provider and uses the original uploaded image and performance description to produce the positive video prompt. Camera directions such as static, dolly in/out, orbit and focus shift are interpreted through that prompt; they are not deterministic camera controls. The cropped recording conditions both video sampling passes and supplies the exported soundtrack, rather than generated audio. Start with a 1280-pixel longest edge, original proportions and 25 FPS. Output dimensions are calculated and rounded to a multiple of eight before initial generation at half dimensions, followed by 2× spatial upscale and refinement. Changing proportions affects the separate reference resize: Center crops to fit, while Disabled stretches. The sizing stage's letterbox image and background color are not used as the generation reference. Custom ratio components apply only in a custom-ratio mode supported by the installed sizing node; the supplied evidence does not establish its exact selector value. Conditioning image size separately sets the reference preprocessing longest edge, with a default of 1536 pixels, before compression. Use positive dimensions and positive integer FPS. FPS drives frame count, model conditioning and export playback together. Frame count is cropped duration converted to integer seconds, multiplied by FPS, plus one. Fractional durations can therefore cause timing differences; use whole-second crop boundaries for a first run and inspect synchronization. Exact lip alignment and subject fidelity are not guaranteed. Uploaded transparency is not preserved. Initial and refinement image guidance have independent strengths and disable switches. Disabling a pass's image conditioning leaves that sampling pass active; the image remains required for dimensions and Gemini context. Upscaling and refinement still run. The optional fixed style LoRA affects both passes and starts enabled: bypass Style LoRA or set its strength to zero to remove its influence. Its filename suggests a xianxia style, but the supplied evidence does not establish its appearance. The separate distillation adapter also affects both passes; begin with its source strength of 0.5 and four initial steps. Advanced controls include separate seeds, prompt guidance and samplers for each pass. Seed -1 randomizes each run. Fixing video seeds does not freeze the Gemini-expanded prompt, and a fixed prompt-expansion seed does not establish deterministic provider responses. Prompt variation controls provider temperature. Steps, Scheduler and Denoise affect initial generation only; refinement uses its explicit comma-separated noise levels ending at zero. Ordinary negative guidance has no effect at CFG 1. Keep MP4/H.264, CRF 19, yuv420p, 8-bit and sRGB for the source encoding preset. Alternative file types, codecs, pixel formats and bit depths require compatible output transport and encoder support. GIF cannot retain the soundtrack. HDR output settings alone do not establish HDR generation. Use the shared FPS control to change playback timing. The configured provider, source models and custom nodes are required. Active loaders request gemma_3_12B_it_fp8_e4m3fn.safetensors, ltx-2.3-22b-dev.safetensors, ltx-2.3-spatial-upscaler-x2-1.1.safetensors and the two fixed LoRAs. Dependency metadata contains differing filenames; use the active loader choices.
Aissist XL - Negative Embedding
AissistXL is a negative embedding fine-tuned to be working on Animagine XL v3 and its derivatives. It trained on the standard negative prompt for Animagine XL v3 plus some extra parameters to make sure you always...
Text to sound effects
Generate an MP3 sound effect from a text description using ElevenLabs eleven_sfx_v2. For a first run, replace the traffic example in Sound description with the effect you want, or keep it to try the supplied example. Keep the 5-second duration, looping disabled and prompt influence at 0.3, then run the tool. No uploaded audio is required. Duration accepts 0.5–30 seconds. Enable Seamless loop to request a smoothly looping effect. Prompt influence ranges from 0 to 1; higher values make generation follow your description more closely. Generation audio format selects the generator's MP3 or Opus response. The connected output stage saves either response as MP3, so this choice does not change the final file type. In the advanced MP3 output section, choose V0, 128k or 320k for the final encoding setting. The tool provides one connected MP3 output.
ACE-Step 1.5 music generator
Generate music with ACE-Step 1.5 XL from a musical description and lyrics, and export MP3. No media upload is required. For a first run, keep the supplied description, lyrics, and defaults, then generate: the example requests a two-minute ambient song with English vocals at 72 BPM in E minor. Musical instructions guide generation rather than guaranteeing exact performance. To create your own track, describe genre, instruments, mood, vocal delivery, production, and arrangement in Music description. Enter sung words and optional bracketed section cues in Lyrics, then select the matching vocal language. Keep tempo, key, and meter references consistent across the text and musical controls. The time-signature selector offers source values 2, 3, 4, and 6, with no separate denominator control. Output duration sets the audio length in seconds. Conditioning duration is independent: update both to the same value when changing length. Track count sets the batch size using the same musical conditioning. Seed is shared by audio-code generation and diffusion sampling; -1 randomizes it, while a fixed nonnegative integer lets you reuse a seed with the same settings. Generate audio codes enables the additional language-model stage. Its guidance, temperature, top-p, top-k, and min-p controls apply only when enabled. Disabling it leaves the text-conditioned diffusion path available. Advanced Audio sampling controls set diffusion steps, CFG, sampler, scheduler, and denoising strength. Sampling configuration exposes the source sampling shift, defaulting to 3. Full denoising defaults to 1 because generation starts from an empty audio latent. Negative conditioning is automatically zeroed; there is no editable negative prompt. MP3 quality selects V0 variable-bitrate encoding or fixed 128k or 320k encoding and affects export rather than music generation. The workflow uses the ACE-Step XL base diffusion model, its two Qwen text encoders, and the ACE 1.5 audio VAE. It has no uploaded audio reference, continuation, or audio-editing input.
Kling 3.0 first and last frame video
Generate one video between two reference images with Kling 3.0, with optional generated audio. Upload both a first frame and a last frame; both are required. Replace the example goldfish prompt with a description of the action, transition and camera movement connecting your images. For a first run, keep the five-second duration and 720p resolution, and leave output file type and codec set to auto. Duration supports 3–15 seconds. Update any timing written in the prompt when changing duration. Resolution offers 720p, 1080p and 4k. Generate audio is enabled by default: describe the desired ambience, music or dialogue in the prompt, or disable it when sound is unnecessary. Advanced Video output settings let you choose the file type and codec for the returned video. Generation sends the reference images and prompt to an authenticated partner API and incurs provider charges. Duration, resolution and audio settings affect the charge. The seed default of -1 requests fresh randomization each run. Seed changes control re-running, but a fixed seed does not guarantee identical results.
AUTO-SEND FILES PRIVATE/SECURE 🔐: ComfyUI Output Folder >> Encrypt >> Send to GoogleDrive / Dropbox 😎👍 — v1.0.0
Sick of manually downloading your ComfyUI output files from the cloud? Want them to just show up in your GoogleDrive automatically? (or DropBox - Link Below)
Grok image restyling
Upload one image and describe the appearance you want. For a first run, keep the pixel-art instruction, 1K resolution and one result. The prompt is fully editable: specify the desired style and which subjects or details should remain recognizable. Identity preservation is a request to the generative model, not a guarantee. The source contains equivalent style examples. This tool uses one editing branch with one editable prompt rather than running every example simultaneously. Copy any of these source starting instructions into the prompt: - Change the images style into pixel art, maintain identity - Change the images style into 3d animation, maintain identity - Change the images style into claymation, maintain identity - Change the images style into hyper realistic, maintain identity - Change the images style into cross stitch, maintain identity - Change the images style into oil painting with visible brushstrokes, maintain identity - Change the images style into detailed colored pencil, maintain identity - Change the images style into flat vector illustration, maintain identity - Change the images style into reflective metal sculpture, maintain identity - Change the images style into charcoal sketch, maintain identity - Change the images style into lineart, maintain identity - Change the images style into watercolor, maintain identity Choose 1K or 2K resolution and request 1–10 edited images. Model selection exposes the source-supported grok-imagine-image, grok-imagine-image-quality and grok-imagine-image-pro options. Aspect ratio remains automatic for this single-image input; the source permits explicit ratios only with multiple input images. Increasing result count does not create multiple input images. Seed controls whether the provider node re-runs; results remain nondeterministic even with a fixed seed. The default randomizes on each run. Outputs are generated raster still images: animation and sculpture instructions describe appearances, vector instructions do not produce vector files, and cross-stitch instructions do not produce stitch patterns. Pixel art is prompted without enforced grid or palette constraints. Uploaded transparency is not preserved by the selected image-only path.
Kling image generation
Generate images from text with Kling Image O1 or Kling 3.0 Omni and view the results in Sweet Tea. For a first run, keep Kling Image O1, 1K resolution, square aspect ratio, and image series disabled. Use the supplied fashion portrait prompt or replace it with your own subject, composition, lighting, and style. Describe unwanted elements in the same prompt when needed; there is no separate negative prompt. Choose the aspect ratio for image proportions and 1K, 2K, or 4K resolution for the requested output size. To request a series of 2–9 images, select Kling 3.0 Omni and then choose the image series count. Keep image series disabled with Kling Image O1, which does not support that mode. This Pipe accepts text only; no reference image input is connected. Leave seed at -1 to randomize the run seed. Seed controls whether generation re-runs, rather than reproducibility: results remain non-deterministic even with a fixed seed. Generation sends the prompt to the paid Kling provider. Results are delivered through Sweet Tea's image output; the workflow does not permanently save image files.
[LuisaP] Sci-fi/Hard surface
Needs the keyword " structure " ex: a cyberpunk structure , a building structure , a turret structure .
Hunyuan3D texture from images
Generate a texture image by reconstructing an object with Hunyuan3D through the provider API. For a first run, upload a front view of the object and leave Back view bypassed. Keep model 3.1, 500,000 faces and PBR enabled, then run the Pipe. To include a back view, enable Back view and upload a matching image of the same object. Model version offers Hunyuan3D 3.1 or 3.0. Face count requests between 3,000 and 1,500,000 mesh faces; it does not set texture pixel resolution. PBR requests physically based material generation, but this Pipe returns only the texture image. Seed -1 requests a fresh run. The provider produces non-deterministic results even when a seed is reused; the seed controls node re-running and caching. Generation is fixed to Normal for the texture output. Geometry mode does not supply this deliverable, and LowPoly requires a polygon-type control absent from this interface and is unavailable with model 3.1. This Pipe runs the underlying 3D generation on each requested generation run. It does not accept an existing mesh. It delivers no GLB or OBJ model, rendered model preview, or separate metallic, normal or roughness maps.
Wan 2.2 four-step frame-to-video
Generate a silent video from a scene and motion prompt, optionally guided by a start image, an end image, or both. For a first run, upload a start image and replace the sleeping-cat prompt with your subject, action, camera movement and style. Upload an end image if you want ending-frame guidance; otherwise disable the End image stage. Both image stages initially remain enabled, so upload an image for each enabled stage or disable it explicitly. Leave the default 640 × 640 dimensions, 81 frames, 16 FPS and sampling settings for the first run, then generate and view the returned video. The default playback lasts approximately 5.1 seconds. The image stages can be disabled independently: start only animates from an opening image, end only provides ending guidance, both guide a transition, and disabling both leaves prompt-driven generation. Images provide guidance rather than a guarantee of an exact transition. Only RGB image outputs are connected; uploaded alpha masks are unused. There is no audio input in this tool. Width and height are pixels in increments of 16. Frame count follows 1, 5, 9 and so on and changes how many frames are generated. Playback FPS changes duration without generating additional frames: duration is frame count divided by FPS. Keep batch size at 1 for a single video; this Pipe has one video output rather than separate outputs per batch item. Advanced settings preserve separate initial and finishing-stage controls. Seed -1 randomizes initial noise; a fixed nonnegative seed repeats the noise choice with the same other settings. The high-noise stage adds noise and runs steps 0–2, then the low-noise stage continues steps 2–4 without adding fresh noise. Both use a total schedule length of 4, CFG 1, Euler, simple scheduling and sampling shift 8. The fixed high/low-noise Lightx2v LoRAs each have model strength 1. If deliberately changing this recipe, coordinate both total step counts and the segment boundaries; changing one field alone can interrupt the handoff. LoRA strengths do not select the standard 20-step sibling recipe. The supplied negative prompt is a Chinese list of unwanted visual defects and content; retain it or edit it for your scene. Output container, codec, CRF and bit depth control video representation and encoding. Leave container and codec on auto and CRF at -1 for the first run. Ten-bit output may be unsupported by some players or downstream nodes.
Ideogram V4 image generator
Generate an image through the Ideogram V4 partner API using a written prompt. No source image is required. For a first run, keep the bundled surreal collage-poster prompt, Auto output size, and DEFAULT rendering speed, then run. The execution environment needs access to the partner API. Replace the prompt with plain natural language for a simple idea, or edit the bundled JSON to describe composition, colors, objects, and in-image wording. JSON remains one prompt field; this Pipe does not provide separate per-object editors or a negative prompt. Treat layout and lettering instructions as generation requests rather than guaranteed exact placement or transcription. Choose an explicit output size when you need a particular pixel size and aspect ratio, and keep composition instructions consistent with that shape. Rendering speed offers DEFAULT, TURBO, and QUALITY modes for the provider's speed-versus-quality trade-off. Seed defaults to a new random value each run. The source's Gemini helper is disabled and disconnected. Prompt building is manual in this Pipe; it does not automatically expand ideas into JSON.
Action figure image edit
Create an articulated toy or action-figure style image from an uploaded image. Describe the edit in the positive prompt using "action the [thing]", such as "action the scene"; optionally add exclusions in the negative prompt. Fast mode selects the Lightning LoRA branch with four sampling steps by default; disabling it selects standard sampling. Advanced controls adjust edit strength, LoRA strengths, seed, sampler, scheduler, and each mode's steps and guidance.
Product placement video
Create a product-placement video from three product photos and one composition reference. Nano Banana generates a new start frame from all four images; Gemini examines it and writes a motion prompt; Kling animates it. Every run includes composition generation. This tool does not accept an existing finished start frame or return the intermediate still as a separate output. For a first run, upload all four required images: products are images 1–3, and the composition reference is image 4. Edit Placement prompt to describe how the products should appear in that scene. Its default assumes products held in a hand in a fanned arrangement; revise it for other compositions. In Motion instructions, describe desired subject movement and camera motion. These instructions go to Gemini, whose response becomes Kling's actual prompt automatically. Keep the initial 1K start frame, 5-second duration, 1080p video, and automatic output encoding settings. Start frame aspect ratio determines the composition shape and the resulting video's framing. Auto follows an input image's aspect ratio, but the supplied source does not identify which of the four takes precedence. Choose an explicit ratio when framing matters. Kling's own aspect-ratio field is ignored with the generated start frame connected. Start frame resolution and Video resolution are independent. The three model selectors act independently. Image model offers Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana 2 Lite. Both retain all four image bindings and share aspect-ratio and thinking-level controls. For Start frame resolution, enter 1K, 2K, or 4K with the full model; set 1K before switching to Lite, which supports only 1K. Thinking level offers MINIMAL or HIGH. Image temperature controls randomness from 0 to 2, and Image nucleus sampling controls the sampling threshold from 0 to 1; lower values favor more focused choices. Keep their supplied defaults initially. Image generation instructions changes foundational behavior; use Placement prompt for ordinary scene changes and preserve image production. Motion writer model offers gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro-preview, gemini-3-1-pro, and gemini-3-1-flash-lite. Motion writer instructions optionally changes its foundational behavior. Leave that field empty initially; any resulting response is consumed directly as the video prompt. Video model offers kling-v3 and kling-3.0-turbo. kling-v3 supports 4k, 1080p, and 720p; Turbo supports 1080p and 720p, so switch away from 4k before selecting Turbo. Generate audio controls kling-v3. Turbo always generates native audio and ignores this toggle. The retained mode generates a single shot lasting 3–15 seconds; storyboard controls are not exposed. Negative prompt describes unwanted elements for video generation and does not affect the still composition. A seed of -1 randomizes each run. Fixed image and motion-writer seeds request best-effort repeatability without guaranteeing identical results. Kling's seed controls re-running rather than reproducible video generation. File type and Codec affect the returned video's encoding; keep auto initially. Inspect product identity, packaging, label text, pose, and motion before using the result: prompt requests are not guarantees of exact reproduction. The upload loaders' alpha-mask outputs are not connected, so uploaded transparency is not preserved through a separate mask path. Text and thinking-image outputs from image generation are not returned. For a still composition without motion writing or animation, use the separate Product placement photo tool.
