NOT WORKING!
the Load Clip node return the following errors :
CLIPLoader
Error(s) in loading state_dict for Llama2:
size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([151936, 1024]) from checkpoint, the shape in current model is torch.Size([128256, 4096]).
size mismatch for model.layers.0.self_attn.q_proj.weight: copying a param with shape torch.Size([2048, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 4096]).
size mismatch for model.layers.0.self_attn.k_proj.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1024, 4096]).
size mismatch for model.layers.0.self_attn.v_proj.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1024, 4096]).
size mismatch for model.layers.0.self_attn.o_proj.weight: copying a param with shape torch.Size([1024, 2048]) from checkpoint, the shape in current model is torch.Size([4096, 4096]).
size mismatch for model.layers.0.mlp.gate_proj.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([14336, 4096]).
size mismatch for model.layers.0.mlp.up_proj.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([14336, 4096]).
size mismatch for model.layers.0.mlp.down_proj.weight: copying a param with shape torch.Size([1024, 3072]) from checkpoint, the shape in current model is torch.Size([4096, 14336]).
update comfy
update comfy
obviously I already did it, but nothing changed :(
Are you using the Comfyui Portable version or the Comfyui desktop version? Desktop version is updated weeks later than the portable version, I had to change to portable version to use Flux Klein Edit 4b some time ago
It's possible that you might be using the wrong text encoder or clip node setup, so please check that. If that still doesn't work then try installing comfyui again in another folder just to test if it works on a clean install.
Try this workflow. Just delete the qwenVL prompt node and the upload image node and this workflow works good for me. Save as a .json file and drag and drop into comfy.
{
"last_link_id":193,
"nodes":[
{
"mode":0,
"outputs":[
{
"name":"CONDITIONING",
"links":[
116
],
"label":"CONDITIONING",
"type":"CONDITIONING",
"localized_name":"CONDITIONING"
}
],
"size":[
218.65975952148438,
88
],
"pos":[
485.42388916015625,
2368.1533203125
],
"widgets_values":[
"masterpiece, best quality, 1girl, fern , sousou no frieren, @izei1337, purple hair, black robe, lips, sidelocks, feet out of frame, very long hair, puffy sleeves, white dress, butterfly on hand, eyelashes, simple background, closed mouth, mage staff, arm at side, straight hair, blush, solo, purple eyes, chromatic aberration, purple pupils, looking at viewer, hand up, standing, bug, robe, black background, signature, bright pupils, black coat, coat, long sleeves, blue butterfly, upturned eyes, wide sleeves, blunt bangs, from above, dress, blunt ends, long hair, purple butterfly, butterfly, tsurime, half updo"
],
"inputs":[
{
"name":"clip",
"link":7,
"label":"clip",
"type":"CLIP",
"localized_name":"clip"
},
{
"widget":{
"name":"text"
},
"name":"text",
"link":192,
"label":"text",
"type":"STRING",
"localized_name":"text"
}
],
"flags":{
},
"id":4,
"type":"CLIPTextEncode",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.65",
"widget_ue_connectable":{
"text":true
},
"Node name for S&R":"CLIPTextEncode"
},
"order":9
},
{
"mode":0,
"outputs":[
{
"name":"CONDITIONING",
"links":[
117
],
"label":"CONDITIONING",
"type":"CONDITIONING",
"localized_name":"CONDITIONING"
}
],
"size":[
218.65975952148438,
88
],
"pos":[
494.9789733886719,
2520.118896484375
],
"widgets_values":[
"worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts"
],
"inputs":[
{
"name":"clip",
"link":5,
"label":"clip",
"type":"CLIP",
"localized_name":"clip"
},
{
"widget":{
"name":"text"
},
"name":"text",
"link":6,
"label":"text",
"type":"STRING",
"localized_name":"text"
}
],
"flags":{
},
"id":3,
"type":"CLIPTextEncode",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.65",
"widget_ue_connectable":{
"text":true
},
"Node name for S&R":"CLIPTextEncode"
},
"order":6
},
{
"mode":0,
"outputs":[
{
"name":"CLIP",
"slot_index":0,
"links":[
5,
7
],
"label":"CLIP",
"type":"CLIP",
"localized_name":"CLIP"
}
],
"size":[
315,
106
],
"pos":[
88.00989532470703,
2369.926025390625
],
"widgets_values":[
"qwen_3_06b_base.safetensors",
"stable_diffusion",
"default"
],
"inputs":[
{
"widget":{
"name":"clip_name"
},
"name":"clip_name",
"label":"clip_name",
"type":"COMBO",
"localized_name":"clip_name"
},
{
"widget":{
"name":"type"
},
"name":"type",
"label":"type",
"type":"COMBO",
"localized_name":"type"
},
{
"widget":{
"name":"device"
},
"shape":7,
"name":"device",
"label":"device",
"type":"COMBO",
"localized_name":"device"
}
],
"flags":{
},
"id":70,
"type":"CLIPLoader",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.27",
"widget_ue_connectable":{
"clip_name":true,
"type":true,
"device":true
},
"Node name for S&R":"CLIPLoader"
},
"order":0
},
{
"mode":0,
"outputs":[
{
"widget":{
"name":"text"
},
"name":"STRING",
"links":[
6
],
"label":"STRING",
"type":"STRING"
}
],
"size":[
332.37677001953125,
88
],
"pos":[
92.76673126220703,
2531.88232421875
],
"widgets_values":[
"worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts"
],
"inputs":[
],
"flags":{
},
"id":59,
"type":"PrimitiveNode",
"title":"Negative",
"properties":{
"widget_ue_connectable":{
},
"Run widget replace on values":false
},
"order":1
},
{
"mode":0,
"outputs":[
{
"name":"LATENT",
"links":[
118
],
"label":"LATENT",
"type":"LATENT",
"localized_name":"LATENT"
}
],
"size":[
210,
106
],
"pos":[
496.80511474609375,
2656.417724609375
],
"widgets_values":[
896,
1152,
1
],
"inputs":[
{
"widget":{
"name":"width"
},
"name":"width",
"label":"width",
"type":"INT",
"localized_name":"width"
},
{
"widget":{
"name":"height"
},
"name":"height",
"label":"height",
"type":"INT",
"localized_name":"height"
},
{
"widget":{
"name":"batch_size"
},
"name":"batch_size",
"label":"batch_size",
"type":"INT",
"localized_name":"batch_size"
}
],
"flags":{
},
"id":75,
"type":"EmptyLatentImage",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.40",
"widget_ue_connectable":{
"batch_size":true,
"width":true,
"height":true
},
"Node name for S&R":"EmptyLatentImage"
},
"order":2
},
{
"mode":0,
"outputs":[
{
"name":"MODEL",
"links":[
115
],
"label":"MODEL",
"type":"MODEL",
"localized_name":"MODEL"
}
],
"size":[
270,
58
],
"pos":[
463.354248046875,
2236.69482421875
],
"widgets_values":[
3
],
"inputs":[
{
"name":"model",
"link":102,
"label":"model",
"type":"MODEL",
"localized_name":"model"
},
{
"widget":{
"name":"shift"
},
"name":"shift",
"label":"shift",
"type":"FLOAT",
"localized_name":"shift"
}
],
"flags":{
},
"id":57,
"type":"ModelSamplingAuraFlow",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.58",
"widget_ue_connectable":{
"shift":true
},
"Node name for S&R":"ModelSamplingAuraFlow"
},
"order":7
},
{
"mode":0,
"outputs":[
{
"name":"MODEL",
"links":[
102
],
"label":"MODEL",
"type":"MODEL",
"localized_name":"MODEL"
}
],
"size":[
342.6000061035156,
82
],
"pos":[
80.98896026611328,
2234.7490234375
],
"widgets_values":[
"anima-preview.safetensors",
"default"
],
"inputs":[
{
"widget":{
"name":"unet_name"
},
"name":"unet_name",
"label":"unet_name",
"type":"COMBO",
"localized_name":"unet_name"
},
{
"widget":{
"name":"weight_dtype"
},
"name":"weight_dtype",
"label":"weight_dtype",
"type":"COMBO",
"localized_name":"weight_dtype"
}
],
"flags":{
},
"id":67,
"type":"UNETLoader",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.10.0",
"widget_ue_connectable":{
"weight_dtype":true,
"unet_name":true
},
"Node name for S&R":"UNETLoader"
},
"order":3
},
{
"mode":0,
"outputs":[
{
"name":"LATENT",
"slot_index":0,
"links":[
131
],
"label":"LATENT",
"type":"LATENT",
"localized_name":"LATENT"
}
],
"size":[
297.15631103515625,
266.5079040527344
],
"pos":[
771.1995239257812,
2244.23974609375
],
"widgets_values":[
472013844840276,
"fixed",
30,
4,
"er_sde",
"simple",
1
],
"inputs":[
{
"name":"model",
"link":115,
"label":"model",
"type":"MODEL",
"localized_name":"model"
},
{
"name":"positive",
"link":116,
"label":"positive",
"type":"CONDITIONING",
"localized_name":"positive"
},
{
"name":"negative",
"link":117,
"label":"negative",
"type":"CONDITIONING",
"localized_name":"negative"
},
{
"name":"latent_image",
"link":118,
"label":"latent_image",
"type":"LATENT",
"localized_name":"latent_image"
},
{
"widget":{
"name":"seed"
},
"name":"seed",
"label":"seed",
"type":"INT",
"localized_name":"seed"
},
{
"widget":{
"name":"steps"
},
"name":"steps",
"label":"steps",
"type":"INT",
"localized_name":"steps"
},
{
"widget":{
"name":"cfg"
},
"name":"cfg",
"label":"cfg",
"type":"FLOAT",
"localized_name":"cfg"
},
{
"widget":{
"name":"sampler_name"
},
"name":"sampler_name",
"label":"sampler_name",
"type":"COMBO",
"localized_name":"sampler_name"
},
{
"widget":{
"name":"scheduler"
},
"name":"scheduler",
"label":"scheduler",
"type":"COMBO",
"localized_name":"scheduler"
},
{
"widget":{
"name":"denoise"
},
"name":"denoise",
"label":"denoise",
"type":"FLOAT",
"localized_name":"denoise"
}
],
"flags":{
},
"id":63,
"type":"KSampler",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.40",
"widget_ue_connectable":{
"scheduler":true,
"denoise":true,
"seed":true,
"cfg":true,
"sampler_name":true,
"steps":true
},
"Node name for S&R":"KSampler"
},
"order":10
},
{
"mode":0,
"outputs":[
{
"name":"VAE",
"links":[
132
],
"label":"VAE",
"type":"VAE",
"localized_name":"VAE"
}
],
"size":[
270,
58
],
"pos":[
789.0482788085938,
2559.177978515625
],
"widgets_values":[
"qwen_image_vae.safetensors"
],
"inputs":[
{
"widget":{
"name":"vae_name"
},
"name":"vae_name",
"label":"vae_name",
"type":"COMBO",
"localized_name":"vae_name"
}
],
"flags":{
},
"id":29,
"type":"VAELoader",
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.40",
"widget_ue_connectable":{
"vae_name":true
},
"Node name for S&R":"VAELoader"
},
"order":4
},
{
"outputs":[
{
"name":"IMAGE",
"slot_index":0,
"links":[
179
],
"label":"IMAGE",
"type":"IMAGE",
"localized_name":"IMAGE"
}
],
"color":"#223",
"widgets_values":[
],
"inputs":[
{
"name":"samples",
"link":131,
"label":"samples",
"type":"LATENT",
"localized_name":"samples"
},
{
"name":"vae",
"link":132,
"label":"vae",
"type":"VAE",
"localized_name":"vae"
}
],
"flags":{
},
"type":"VAEDecode",
"title":"Anima",
"mode":0,
"bgcolor":"#335",
"size":[
140,
46
],
"pos":[
1103.06591796875,
2246.83642578125
],
"id":66,
"properties":{
"cnr_id":"comfy-core",
"ver":"0.3.40",
"widget_ue_connectable":{
},
"Node name for S&R":"VAEDecode"
},
"order":11
},
{
"mode":0,
"outputs":[
{
"name":"image_urls",
"label":"image_urls",
"type":"STRING",
"localized_name":"image_urls"
}
],
"size":[
270,
270
],
"pos":[
1260.83837890625,
2250.049560546875
],
"widgets_values":[
"ComfyUI"
],
"inputs":[
{
"name":"images",
"link":179,
"label":"images",
"type":"IMAGE",
"localized_name":"images"
},
{
"widget":{
"name":"filename_prefix"
},
"name":"filename_prefix",
"label":"filename_prefix",
"type":"STRING",
"localized_name":"filename_prefix"
}
],
"flags":{
},
"id":90,
"type":"SaveImage",
"properties":{
"widget_ue_connectable":{
},
"Node name for S&R":"SaveImage"
},
"order":12
},
{
"mode":0,
"outputs":[
{
"name":"text",
"links":[
192
],
"label":"text",
"type":"STRING",
"localized_name":"text"
}
],
"size":[
400,
276
],
"pos":[
-326.22235107421875,
2380.611328125
],
"widgets_values":[
"Qwen3-VL-4B-Instruct",
"8-bit (Balanced)",
"Describe this image in detail.",
"Describe this image in detail, remove the watermark in the image.",
1024,
true,
633408216313757,
"randomize"
],
"inputs":[
{
"shape":7,
"name":"image",
"link":193,
"label":"image",
"type":"IMAGE",
"localized_name":"image"
},
{
"shape":7,
"name":"video",
"label":"video",
"type":"IMAGE",
"localized_name":"video"
},
{
"widget":{
"name":"model_name"
},
"name":"model_name",
"label":"model_name",
"type":"COMBO",
"localized_name":"model_name"
},
{
"widget":{
"name":"quantization"
},
"name":"quantization",
"label":"quantization",
"type":"COMBO",
"localized_name":"quantization"
},
{
"widget":{
"name":"preset_prompt"
},
"name":"preset_prompt",
"label":"preset_prompt",
"type":"COMBO",
"localized_name":"preset_prompt"
},
{
"widget":{
"name":"custom_prompt"
},
"name":"custom_prompt",
"label":"custom_prompt",
"type":"STRING",
"localized_name":"custom_prompt"
},
{
"widget":{
"name":"max_tokens"
},
"name":"max_tokens",
"label":"max_tokens",
"type":"INT",
"localized_name":"max_tokens"
},
{
"widget":{
"name":"keep_model_loaded"
},
"name":"keep_model_loaded",
"label":"keep_model_loaded",
"type":"BOOLEAN",
"localized_name":"keep_model_loaded"
},
{
"widget":{
"name":"seed"
},
"name":"seed",
"label":"seed",
"type":"INT",
"localized_name":"seed"
}
],
"flags":{
},
"id":92,
"type":"AILab_QwenVL",
"properties":{
"widget_ue_connectable":{
},
"Node name for S&R":"AILab_QwenVL"
},
"order":8
},
{
"mode":0,
"outputs":[
{
"name":"IMAGE",
"links":[
193
],
"label":"IMAGE",
"type":"IMAGE",
"localized_name":"IMAGE"
},
{
"name":"MASK",
"label":"MASK",
"type":"MASK",
"localized_name":"MASK"
}
],
"size":[
274.080078125,
314
],
"pos":[
-613.7443237304688,
2378.125732421875
],
"widgets_values":[
"c952ea7d39f79267a1e89b847dad7f90fb5466d62145087ca606881d083a5274.png",
"image"
],
"inputs":[
{
"widget":{
"name":"image"
},
"name":"image",
"label":"image",
"type":"COMBO",
"localized_name":"image"
},
{
"widget":{
"name":"upload"
},
"name":"upload",
"label":"upload",
"type":"IMAGEUPLOAD",
"localized_name":"choose file to upload"
}
],
"flags":{
},
"id":91,
"type":"LoadImage",
"properties":{
"widget_ue_connectable":{
},
"Node name for S&R":"LoadImage"
},
"order":5
}
],
"extra":{
"links_added_by_ue":[
],
"ue_links":[
],
"0246.VERSION":[
0,
0,
4
],
"workflowRendererVersion":"LG",
"ds":{
"offset":[
793.6788560856493,
-1777.1841907414987
],
"scale":0.5989500000000003
}
},
"groups":[
],
"links":[
[
5,
70,
0,
3,
0,
"CLIP"
],
[
6,
59,
0,
3,
1,
"STRING"
],
[
7,
70,
0,
4,
0,
"CLIP"
],
[
102,
67,
0,
57,
0,
"MODEL"
],
[
115,
57,
0,
63,
0,
"MODEL"
],
[
116,
4,
0,
63,
1,
"CONDITIONING"
],
[
117,
3,
0,
63,
2,
"CONDITIONING"
],
[
118,
75,
0,
63,
3,
"LATENT"
],
[
131,
63,
0,
66,
0,
"LATENT"
],
[
132,
29,
0,
66,
1,
"VAE"
],
[
179,
66,
0,
90,
0,
"IMAGE"
],
[
192,
92,
0,
4,
1,
"STRING"
],
[
193,
91,
0,
92,
0,
"IMAGE"
]
],
"id":"353006e1-36b9-49e9-a613-f2674646f636",
"config":{
},
"version":0.4,
"last_node_id":93,
"revision":0
}