Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Use this workflow to edit generated images like Qwen-Image-Edit without additional models or LoRAs. Prompt one change at a time, or all at once. There is NO INPAINTING and NO MASKING - simply stack prompts until the...
Profil d'exécution
Description de la source
ZImage Turbo Edit:
Use this workflow to edit generated images like Qwen-Image-Edit without additional models or LoRAs. Prompt one change at a time, or all at once. There is NO INPAINTING and NO MASKING - simply stack prompts until the edit is complete.
ZImage Turbo Merge:
Generated images are created using seed-locked bifurcation + latent merge , implemented as latent interpolation inside a three-stage sampler handoff :
Seed-locked bifurcation : both branches are anchored to the same seed (samplers are driven by the same seed input links)
Three-stage sampling / prompt handoff : Stage #1 creates the foundational image. Stage #2 stops early ( end_at_step ) to create the additional image, Stage #3 resumes at start_at_step and runs to end_at_step = TOTAL to create the merged image.
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
ZIMAGE EDIT + UPSCALE + MERGE WORKFLOW — v2.0 is for editing generated images with prompts, optionally merging image branches, cleaning edited results, and optionally upscaling them; it takes generated images, prompts, shared seeds, and merge controls and can produce edited, mung
For prompt-based edits, enter one change at a time or stack multiple changes together; the workflow does not use inpainting, ControlNet, or masking.
For merges, both branches use the same seed, sampling moves through three stages, and LatentBlend with ModelSampling combines style and composition elements from both images.
After editing, the Renderer Pass can clean the image before it is sent to optional SeedVR2 Upscale.
For editing, provide a generated image and prompts; for merging, use shared seeds plus start_at_step, end_at_step, LatentBlend, and ModelSampling controls.
The workflow can produce an edited image, a merged composition, a cleaned render, and an optional upscale.
The listing identifies this as a workflow, version v2.0, based on ZImageTurbo.
The listed model files include ae.safetensors, ema_vae_fp16.safetensors, qwen_3_4b.safetensors, and seedvr2_ema_7b-Q4_K_M.gguf.
They also include UglyPeopleLora.safetensors, XUPLX_Medium.safetensors, XUPLX_UglyPeopleLoRA.safetensors, and z_image_turbo_bf16.safetensors.
The listed ComfyUI node packs are ComfyUI_Comfyroll_CustomNodes, comfyui_fizznodes, comfyui-easy-use, comfyui-mixlab-nodes, comfyui-rvtools_v2, pr-was-node-suite-comfyui-47064894, rgthree-comfy, and seedvr2_videoupscaler.
To shape a merge, tune LatentBlend and ModelSampling and set the stage handoff with start_at_step and end_at_step.
Suggestion · non vérifié
Because the workflow does not provide inpainting, ControlNet, or masking, verify that prompt-based editing fits your use case.
Suggestion · non vérifié
Verify exact filenames and installation sources before use because some listed files and node packs do not have a fully identified source.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 2275 downloads · Type Workflows · Base model ZImageTurbo
Latent merge : Using LatentBlend and ModelSampling, tune the merge to your taste to create an interesting composition that uses style and composition elements from both images.
ZImage Turbo Renerer:
Once the generated image has been edited, send the image through the Renderer Pass to clean the image before sendoff to SeedVR Upscale (Optional).
DON'T BUY ME A COFFEE!!!
Download ExportGPT - Media & Chat Export Toolkit from the Chrome Web Store, and use it to quickly export assets from ChatGPT and Sora. I update the extension regularly, it has FIVE STARS, and it's FREE FOREVER .
Estimation des besoins VRAM
Estimation indisponible
Les tailles des fichiers du modèle ne sont pas encore suffisamment complètes pour calculer cette exigence.
Exigences
Exigences 16ema_vae_fp16.safetensors
PossibleVAE · Unknown
seedvr2_ema_7b-Q4_K_M.gguf
Non résoluCheckpoint · Unknown
LoRA · Civitai · 2220894
Checkpoint · Hugging Face · danrhern/XUPLX
LoRA · Civitai · 2220894
Checkpoint · Civitai · 2168935
Sources possibles
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
comfyui-mixlab-nodes
PossiblePack de nœud · Registry
Pack de nœud · Registry
pr-was-node-suite-comfyui-47064894
Non résoluPack de nœud · Registry
Pack de nœud · Registry
seedvr2_videoupscaler
Non résoluPack de nœud · Registry
