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 41 724
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.
Topaz creative upscale
Create a creatively enhanced, resized image with Topaz Reimagine. Upload a source image and choose Scale factor. For a first run, use the default 4× scale, leave Prompt empty and keep Creativity at 2. A 4× scale requests four times the source width and height, approximately 16 times as many pixels; a scale of 1 requests the original dimensions. Add an optional prompt to guide the desired details or appearance. Creativity accepts values from 1 to 9. Preserve colors enables preservation of the original palette. Subject detection offers All, Foreground and Background modes. For portraits, enable Enhance faces to use Face creativity and Face sharpness, both ranging from 0 to 1. Face sharpness controls how sharp enhanced faces are relative to the background. Preserve facial identity is a separate option and defaults to off. Output dimensions follow the source aspect ratio, subject to pixel rounding; independent width and height choices are unavailable. The size calculation branch supplies dimensions, while the original image goes directly to Topaz. Crop to fill remains off because this workflow has no independent aspect-ratio choice. Uploaded transparency is not preserved: only the loader's image output is connected, without its alpha mask.
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.
FLUX.2 Klein single-image edit
Generate an edited image from one uploaded source image and written instructions with FLUX.2 Klein 9B Distilled. For a first run, upload your source image, then describe what to change and which details to retain. The supplied instruction replaces the background with a coastal cliff; replace it if that edit does not suit your image. Start with 1 megapixel, one image per run, 4 steps, guidance scale 1 and Euler sampling. Seed -1 chooses a new random seed each run; use a fixed seed when comparing instruction or control changes. Output size approximately follows the source image's aspect ratio at the chosen megapixel count. This setting resizes the reference and determines the generated canvas dimensions. Resize method controls interpolation of the uploaded reference before encoding; it is available alongside output size. Advanced controls expose image count, seed, steps, guidance scale and sampler. Larger sizes and batches require more memory. The uploaded image supplies reference conditioning. Generation starts from a fresh latent rather than directly denoising the upload, so exact preservation of identity, pose or unchanged regions is not guaranteed. There is no mask, edit-strength slider or separate negative prompt. Text conditioning for the negative branch is zeroed automatically, while the image reference is supplied to both conditioning branches. Uploaded transparency is not preserved because only the loader's RGB image output is connected. This tool accepts one source image. Combining a main image with a second visual reference belongs to the separate multi-reference edit tool.
AloeVera's SuperNegative embeddings
0.VERY IMPORTANT -> All the versions of the embeddings are available on the huggingface link. (Civitai has upload limitations). Also click on "Show more" down below for all the examples/comparisons + tips. ☺️
Multi-keyframe video
Create one silent video by generating five prompted transitions between six ordered keyframe images with Wan 2.2 and its paired four-step Lightx2v LoRAs. The generated frame batches are joined in sequence. For a first run, keep all six keyframes enabled and upload an image to each slot. Describe the subject, motion and camera action for each adjacent pair in its transition prompt. Replace transition 1's cat example and fill the other four prompts. Leave size, frame counts and output encoding at their defaults. The defaults generate five 25-frame segments at 720 × 720, joined into 125 frames played at 24 FPS: approximately 5.21 seconds. In advanced controls, each transition has its own frame count and dimensions. Use frame counts of 4n + 1, such as 25, 49 or 81. If changing size, set identical widths and identical heights across all five transitions, using multiples of 16; mismatched dimensions can prevent frame joining. Playback FPS changes how fast the existing frames play, without generating more frames. Duration is the sum of all five frame counts divided by FPS. To omit an endpoint image, disable its keyframe node. Every enabled keyframe needs an upload. Disabling an interior keyframe removes the preceding transition's end-image condition and the following transition's start-image condition. It does not remove either transition or shorten the sequence. A transition with both endpoints disabled still generates from its prompt. All five prompts remain independently editable in these modes. Each transition has an independent initial noise seed. Use -1 for a new random seed each run, or a fixed seed to reuse that transition's noise. Negative prompts are independently connected, but the packaged CFG value of 1 does not apply conventional negative-prompt guidance. The two sampling stages use a coordinated four-step schedule with a handoff after step two; retain the packaged preset for normal use. Video output offers automatic, MP4, MKV or WebM file selection and automatic, H.264 or AV1 encoding. Leave automatic selection and CRF -1 for the first run; these controls affect encoding rather than generated content. The graph joins full frame batches without trimming shared endpoints or blending seams. Repeated boundary frames or visible seams between independently generated transitions may occur. The result has no audio or transparency; uploaded alpha masks are not connected.
Runway image generation
Generate images with Runway from a text prompt and an optional reference image. For a first run, replace the example prompt with your desired subject, setting, composition, and visual style. Keep Output shape at 1024:1024 for a square image. Reference image is enabled initially: upload one image, or bypass that stage to generate from text alone. Run to preview the generated result in Sweet Tea. With a reference image enabled, describe the result you want that image to guide. Only one reference image is accepted, and no image transformation strength control is exposed. Other output shape values must be supported by the Runway node; the draft does not enumerate them. Running requires configured ComfyUI partner API access and sufficient account credits. Generation sends the prompt and any enabled reference image to Runway and uses a paid provider call. The output stage returns images for preview without permanently saving them through ComfyUI.
Causal Forcing image to video
Animate an uploaded starting image into one silent video with Causal Forcing Framewise. For a first run, upload an image and replace the example motion prompt with a description of your subject's movement and the desired camera behavior. Choose width and height in multiples of 16 with an aspect ratio similar to the image. Start with 832 × 480, duration 5, batch size 1 and playback at 16 FPS. The image is used as the starting-frame input; uploaded transparency is not preserved through the connected RGB image output. Duration is measured on a fixed 16 FPS generation basis. The graph calculates min(duration × 16 + 1, 81) and uses its integer output as the requested frame count. Use positive duration values up to 5 seconds; larger values do not add frames. At 16 FPS, 81 frames play for about 5.06 seconds. Playback FPS changes how quickly the generated frames play, independently of their count: higher FPS shortens playback and lower FPS lengthens it. Seed -1 requests fresh random variation each run. A fixed seed reuses the sampling noise. CFG defaults to 1, where the negative prompt has no effect. For experiments with CFG above 1, describe unwanted appearance or motion in the negative prompt. Changing guidance departs from the supplied checkpoint preset. Advanced sampling controls expose steps, noise schedule and denoise fraction. Begin with the source configuration: 4 steps, simple schedule and denoise 1. Denoise controls the sampling schedule rather than directly specifying how closely to preserve the uploaded image. The fixed model is causal_forcing-framewise.safetensors with the Wan VAE and text encoder; its autoregressive sampler is fixed to one frame per block, matching the Framewise mode. Keep batch size 1 for a single sequence. The graph has one video assembly path and does not return separate videos for batch members. File type and codec control output encoding and default to auto. No audio input is connected, so the result is silent.
CyberRealistic Negative - Pony v2.0
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
Expand an image with Flux.1
Generate new content beyond an uploaded image’s edges with Flux.1 and preview the expanded image. For a first run, upload an image, replace the expansion prompt with a description of the surrounding scene, and keep the default expansion of 184 pixels on each side. Run the Pipe to view the result. Each side accepts 0–2048 pixels; set a side to zero to leave it unexpanded. Left and right expansion add width, while top and bottom expansion add height. Guidance controls prompt influence, and steps controls the generation step count. Optional prompt enhancement automatically rewrites your prompt for more creative generation; when enabled, the same seed will not produce exactly the same result. Keep seed at -1 for a fresh random seed each run, or enter a fixed seed to reuse the noise choice. Generation sends the image and prompt to BFL and uses a paid provider call. This workflow offers edge expansion without mask-based editing controls. Uploaded transparency is not preserved through the connected image path.
Luma text to video
Generate one video from a scene description through Luma, with optional camera motion concepts. Enter a text prompt describing the subject, setting, action, lighting, and movement. This tool has no image input. Generation sends the request to Luma and requires API access and sufficient account credits. For a first run, replace the example prompt and keep Ray 2, 16:9, 720p, and 5s. Leave both camera stages bypassed and run the tool to receive the video. Enable Loop to request a looping clip. For camera concepts, enable Camera motion in the advanced controls. Its initial choices are zoom_in and orbit_left; change the four slots as needed, using None for unused slots. Enable Additional camera motion as well when you want to combine up to four more concepts with the primary stage. Its slots initially contain None. Bypassed stages do not add their own selected concepts. The model affects supported output settings: Ray 1.6 ignores duration and resolution. Re-run seed controls whether the API generation runs again, not reproducibility. Keep -1 to randomize each run; identical seeds do not reproduce the same video. Video output returns the generated clip through Sweet Tea. Keep File type and Codec at Auto for the first run, or use the advanced output controls to choose a container and codec. These settings affect output encoding, rather than the scene generated by Luma.
花想容/Chinese style/古风/中国風です Lora
推荐的质量词: masterpiece, best quality, score7, score8, highres, extremely detailed 8k, illustration, great quality, amazing quality, very aesthetic, absurdres, Chinese style,
