QWEN_EDIT_IMAGE_api_predict – 8 MCP servers offer this tool
What it usually takes
fix_hands– in 8 of 8guidance_scale– in 8 of 8identity_strength– in 8 of 8image– in 8 of 8image2– in 8 of 8lora_adapter– in 8 of 8output_size– in 8 of 8preserve_identity– in 8 of 8prompt– in 8 of 8randomize_seed– in 8 of 8seed– in 8 of 8steps– in 8 of 8
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.kulkas2pintu/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model; pose still uses 8. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD | fix_hands,guidance_scale,identity_strength,image,image2,lock_face_hair,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.foq/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.ilaykoslov/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.innominato/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.jwolf007/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.magicwing/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.wilmgard/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |
Qwen-Image-Edit-2511-LoRAs-Fast co.huggingface.zenx566/qwen_edit_image Edit an image from a text prompt (Qwen-Image-Edit-2511). Returns [result_image, seed_used]. image : the image to edit (the person/subject whose identity is kept). prompt : what to change, e.g. "change her outfit to a red dress; turn to look left". lora_adapter : optional style name from the adapter list ("" = no style LoRA / base edit). image2 : optional second reference image (e.g. a style or lighting reference). seed : int seed (ignored if randomize_seed=True). randomize_seed : pick a new random seed each call. guidance_scale : true-CFG. 1.0 = fastest; >1 (e.g. 2.5) activates the negative prompt that suppresses extra fingers / identity drift (slower). steps : denoise steps. 4 is native for this distilled model. preserve_identity : keep the person's face while allowing pose/head to change. identity_strength : 0-100, how forcefully identity is locked. output_size : long-side pixels 1024-2048. Higher = more HD detail, slower. fix | fix_hands,guidance_scale,identity_strength,image,image2,lora_adapter,output_size,preserve_identity,prompt,randomize_seed,seed,steps | Not stated |