Image editingTool
Fisher Pose: Pose and Camera Editor for Qwen-Image 2.1Fisher Pose is a ComfyUI node that redraws a character in a new pose or camera angle for Qwen-Image 2.1, using a 3D mannequin, 209 OpenPose skeletons and a matching LoRA.
ComfyUI News & Open-Source AI Releases
ComfyUI ecosystem updates — open-source model releases, custom nodes, workflows, and tools for image, video, and audio generation.
Image editing
Text to imageTool
Texture-Fix-VAE: A Cleaner VAE Decoder for Qwen-Image 2.1madebyollin's Texture-Fix-VAE retrains the Qwen-Image 2.1 VAE decoder to remove checkerboard texture artifacts. Drop the file into ComfyUI/models/vae and load it as usual.
qwen-research
Text to imageLoRA
Qwen-Image 2.1 Fun Acc LoRA: Official 4-Step DistillationAlibaba PAI distills Qwen-Image 2.1 to 4 steps with a 346 MB PDD LoRA that covers text-to-image and instruction editing, with its own sigma schedule.
qwen-research
Text to imageBase model
Seedream 5.0 Flash Lands in ComfyUI Partner NodesByteDance's Seedream 5.0 Flash adds a speed-focused tier to ComfyUI's ByteDance image nodes, with text-to-image and image edit templates at up to 2K.
API-Only
Text to imageControlNet
Qwen-Image 2.1 Fun ControlNet Union: 8 Controls in One FileAlibaba PAI's ControlNet Union for Qwen-Image 2.1 packs eight structural controls and inpainting into one 7.5 GB branch, now with merged ComfyUI support.
qwen-research
Text to imageTurbo
Pruna 5-Step and 8-Step Qwen-Image 2.1 LoRAs in ComfyUIPrunaAI's Pruna-Qwen-Image-2.1 LoRAs cut Qwen-Image 2.1 generation and editing to 5 or 8 steps with no CFG, with community ComfyUI conversions and per-step sigma schedules.
Qwen Research License
Text to imageTurbo
Viggle Turbo v0.2: 5-Step Qwen-Image 2.1 Distill in ComfyUIViggle's v0.2 DMD distillation of Qwen-Image 2.1 cuts generation to 5 steps with no CFG, shipping as a rank-256 LoRA with community ComfyUI conversions.
Qwen Research License
Text to imageFine-tune
Zen Image Edit: Qwen-Image 2.1 on a 0.8B Encoder in ComfyUIZen Image Edit runs Qwen-Image 2.1 on a Qwen3.5-0.8B text encoder plus a 158M fusion adapter, cutting the encoder from 17.5 GB to 1.7 GB, with two ComfyUI routes.
Image to imageLoRA
Krea 2 Anygles: Camera Viewpoint Control LoRA for ComfyUIKrea 2 Anygles turns one photo of a person into a new camera view with a 3D human normal LoRA, plus ComfyUI nodes and a workflow for orbit, elevation and distance.
Text to imageLoRA
Qwen-Image 2.1 Fix LoRA: Corrected Settings for ComfyUIQwen-Image 2.1 Fix is a community LoRA with a companion 20-step ComfyUI workflow, aimed at the model's washed-out colors and broken fine texture.
Qwen Research License
Text to imageBase model
Tencent HY Image 3.5 Preview Arrives in ComfyUI Partner NodesTencent's HY Image 3.5 Preview adds text-to-image, reference-image and multi-turn editing to the Hunyuan image API, with new ComfyUI text-to-image and edit nodes.
API-Only
Video editingLoRA
MiniMax H3 VFX Edit LoRA Brings Prompt-Directed Video EditingAlissonerdx's MiniMax H3 LoRA pack adds prompt-directed VFX Edit plus documented Style Transfer and Head Swap adapters, with ComfyUI workflows and example clips.
Apache-2.0
InpaintingControlNet
MiniMax H3 Fun ControlNet Union 2.0 in ComfyUI: Eight Control TypesAlibaba PAI's ControlNet Union 2.0 for MiniMax H3 adds Scribble, Layout and Gray control and doubles the injection blocks, with same-day ComfyUI support.
minimax-h3-community-license-agreement
Video editingTool
obvpm Timeline: MiniMax H3 Clip Editing Nodes for ComfyUIcomfyui-obvpm-timeline adds a mini video editor to ComfyUI for MiniMax H3: extend, prepend, bridge and loop clips with latent-grade joins and a one-pass upscale.
GPL-3.0
Text to imageBase model
Supra2-IMG: A 100M Text-to-Image Model Trained in 10 HoursSupraLabs releases Supra2-IMG, a 105M-parameter DiT text-to-image model trained from scratch in 10 hours on one H100, with samples at 256x256.
Apache-2.0
Text to imageTool
Qwen-Image 2.1 Prompt Enhancer Models Run in ComfyUIQwen's PE-T2I and PE-I2I prompt rewriting models expand short requests and edit instructions, and a community node pack runs both in ComfyUI through Load CLIP.
EcosystemLoRA
CrossView-Warp LoRA: New Camera Angles for MiniMax H3 VideoCseti ports CrossView-Warp to MiniMax H3: a Ref2VA LoRA plus a ComfyUI node that re-renders existing footage from a new camera angle using a MoGe depth warp.
MiniMax-H3-Community
EcosystemTool
ComfyUI v0.37.0: Qwen-Image 2.1 and MoGe 3 SupportComfyUI v0.37.0 adds native Qwen-Image 2.1 support with three official templates, MoGe 3 geometry estimation, faster Qwen3.8 text encoders and automatic fast disk loading.
Text to videoTool
ComfyUI MiniMax H3 SPEED V2: Multi-Sampler Progressive ResolutionComfyUI-MiniMax-H3-SPEED V2 supports Euler, Heun, DPM2 and RES Multistep, adds a sampler-aware Sigma Harvest, and fixes I2V keyframe resizing.
Text to imageBase model
Qwen-Image 2.1: 7B T2I and Editing Model in ComfyUIDownload Qwen-Image 2.1 for ComfyUI: qwen_image_2.1_bf16 and int8_convrot safetensors, qwen3vl_8b encoder and official 2K text-to-image, edit and background removal workflows.
Qwen Research License